Token | be |
Token ID | 307 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ilers | +0.650 |
VIDIA | +0.646 |
irtual | +0.643 |
endi | +0.616 |
LET | +0.578 |
Neg logit contributions | |
threat | -0.745 |
credit | -0.719 |
aligned | -0.717 |
strength | -0.707 |
bang | -0.693 |
Token | involved |
Token ID | 2950 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ilers | +0.668 |
VIDIA | +0.661 |
irtual | +0.658 |
endi | +0.635 |
ually | +0.601 |
Neg logit contributions | |
threat | -0.609 |
credit | -0.586 |
aligned | -0.585 |
strength | -0.577 |
bang | -0.561 |
Token | , |
Token ID | 11 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
threat | +0.252 |
credit | +0.243 |
aligned | +0.242 |
strength | +0.238 |
bang | +0.233 |
Neg logit contributions | |
ilers | -0.244 |
VIDIA | -0.242 |
irtual | -0.241 |
endi | -0.231 |
ually | -0.217 |
Token | with |
Token ID | 351 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
ilers | +0.072 |
VIDIA | +0.071 |
irtual | +0.071 |
endi | +0.068 |
ually | +0.064 |
Neg logit contributions | |
threat | -0.065 |
credit | -0.063 |
aligned | -0.063 |
strength | -0.062 |
bang | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
ilers | +0.137 |
VIDIA | +0.135 |
irtual | +0.135 |
endi | +0.130 |
ually | +0.123 |
Neg logit contributions | |
threat | -0.115 |
credit | -0.111 |
aligned | -0.110 |
strength | -0.109 |
bang | -0.106 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ilers | +0.149 |
VIDIA | +0.147 |
irtual | +0.147 |
endi | +0.141 |
ually | +0.133 |
Neg logit contributions | |
threat | -0.144 |
credit | -0.139 |
aligned | -0.138 |
strength | -0.137 |
bang | -0.133 |
Token | only |
Token ID | 691 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ilers | +2.648 |
VIDIA | +2.589 |
irtual | +2.559 |
endi | +2.519 |
ually | +2.394 |
Neg logit contributions | |
threat | -3.059 |
aligned | -2.963 |
credit | -2.953 |
strength | -2.947 |
bang | -2.838 |
Token | coming |
Token ID | 2406 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
threat | +0.249 |
credit | +0.240 |
aligned | +0.240 |
strength | +0.237 |
bang | +0.231 |
Neg logit contributions | |
ilers | -0.221 |
VIDIA | -0.218 |
irtual | -0.217 |
endi | -0.208 |
ually | -0.195 |
Token | in |
Token ID | 287 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
threat | +0.624 |
credit | +0.600 |
aligned | +0.598 |
strength | +0.590 |
bang | +0.573 |
Neg logit contributions | |
ilers | -0.706 |
VIDIA | -0.697 |
irtual | -0.695 |
endi | -0.672 |
ually | -0.636 |
Token | for |
Token ID | 329 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
threat | +0.209 |
credit | +0.202 |
aligned | +0.201 |
strength | +0.198 |
bang | +0.193 |
Neg logit contributions | |
ilers | -0.231 |
VIDIA | -0.228 |
irtual | -0.227 |
endi | -0.219 |
ually | -0.207 |
Token | a |
Token ID | 257 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
ilers | +0.020 |
VIDIA | +0.020 |
irtual | +0.019 |
endi | +0.019 |
ually | +0.018 |
Neg logit contributions | |
threat | -0.020 |
credit | -0.019 |
aligned | -0.019 |
strength | -0.019 |
bang | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ilers | +0.186 |
VIDIA | +0.183 |
irtual | +0.183 |
endi | +0.176 |
ually | +0.166 |
Neg logit contributions | |
threat | -0.189 |
credit | -0.183 |
aligned | -0.182 |
strength | -0.180 |
bang | -0.175 |
Token | The |
Token ID | 383 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ilers | +0.076 |
VIDIA | +0.075 |
irtual | +0.074 |
endi | +0.072 |
ually | +0.068 |
Neg logit contributions | |
threat | -0.078 |
credit | -0.075 |
aligned | -0.075 |
strength | -0.074 |
bang | -0.072 |
Token | combination |
Token ID | 6087 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
threat | +0.410 |
credit | +0.397 |
aligned | +0.395 |
strength | +0.390 |
bang | +0.380 |
Neg logit contributions | |
ilers | -0.365 |
VIDIA | -0.361 |
irtual | -0.359 |
endi | -0.345 |
LET | -0.323 |
Token | of |
Token ID | 286 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
ilers | +0.044 |
VIDIA | +0.044 |
irtual | +0.044 |
endi | +0.042 |
LET | +0.039 |
Neg logit contributions | |
threat | -0.043 |
credit | -0.042 |
aligned | -0.041 |
strength | -0.041 |
bang | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
threat | +0.133 |
credit | +0.129 |
aligned | +0.128 |
strength | +0.127 |
bang | +0.123 |
Neg logit contributions | |
ilers | -0.122 |
VIDIA | -0.121 |
irtual | -0.120 |
endi | -0.115 |
LET | -0.108 |
Token | mov |
Token ID | 1409 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
threat | +0.111 |
credit | +0.107 |
aligned | +0.107 |
strength | +0.105 |
bang | +0.103 |
Neg logit contributions | |
ilers | -0.105 |
VIDIA | -0.104 |
irtual | -0.103 |
endi | -0.099 |
ually | -0.093 |
Token | able |
Token ID | 540 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ilers | +1.856 |
irtual | +1.825 |
VIDIA | +1.759 |
endi | +1.752 |
ually | +1.573 |
Neg logit contributions | |
threat | -3.685 |
credit | -3.593 |
aligned | -3.558 |
strength | -3.539 |
bang | -3.466 |
Token | command |
Token ID | 3141 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
ilers | +0.513 |
VIDIA | +0.506 |
irtual | +0.504 |
endi | +0.484 |
ually | +0.454 |
Neg logit contributions | |
threat | -0.603 |
credit | -0.583 |
aligned | -0.582 |
strength | -0.575 |
bang | -0.561 |
Token | center |
Token ID | 3641 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
ilers | +0.135 |
VIDIA | +0.133 |
irtual | +0.133 |
endi | +0.128 |
ually | +0.121 |
Neg logit contributions | |
threat | -0.142 |
credit | -0.137 |
aligned | -0.137 |
strength | -0.135 |
bang | -0.132 |
Token | with |
Token ID | 351 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
threat | +0.467 |
aligned | +0.450 |
credit | +0.448 |
strength | +0.442 |
bang | +0.434 |
Neg logit contributions | |
ilers | -0.486 |
VIDIA | -0.482 |
irtual | -0.477 |
endi | -0.461 |
eln | -0.433 |
Token | a |
Token ID | 257 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
threat | +0.314 |
credit | +0.303 |
aligned | +0.303 |
strength | +0.298 |
bang | +0.291 |
Neg logit contributions | |
ilers | -0.310 |
VIDIA | -0.306 |
irtual | -0.305 |
endi | -0.294 |
LET | -0.276 |
Token | it |
Token ID | 340 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
ilers | +0.557 |
VIDIA | +0.549 |
irtual | +0.547 |
endi | +0.526 |
ually | +0.495 |
Neg logit contributions | |
threat | -0.626 |
credit | -0.605 |
aligned | -0.603 |
strength | -0.596 |
bang | -0.581 |
Token | 's |
Token ID | 338 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
ilers | +0.402 |
VIDIA | +0.398 |
irtual | +0.396 |
endi | +0.381 |
ually | +0.358 |
Neg logit contributions | |
threat | -0.415 |
credit | -0.401 |
aligned | -0.399 |
strength | -0.395 |
bang | -0.385 |
Token | not |
Token ID | 407 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ilers | +0.806 |
VIDIA | +0.795 |
irtual | +0.792 |
endi | +0.762 |
ually | +0.718 |
Neg logit contributions | |
threat | -0.850 |
credit | -0.821 |
aligned | -0.818 |
strength | -0.809 |
bang | -0.788 |
Token | an |
Token ID | 281 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
ilers | +0.594 |
VIDIA | +0.586 |
irtual | +0.584 |
endi | +0.567 |
ually | +0.539 |
Neg logit contributions | |
threat | -0.518 |
credit | -0.498 |
aligned | -0.495 |
strength | -0.490 |
bang | -0.475 |
Token | int |
Token ID | 493 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
ilers | +0.124 |
VIDIA | +0.123 |
irtual | +0.122 |
endi | +0.118 |
ually | +0.111 |
Neg logit contributions | |
threat | -0.126 |
credit | -0.122 |
aligned | -0.122 |
strength | -0.120 |
bang | -0.117 |
Token | ract |
Token ID | 974 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
threat | +0.054 |
credit | +0.053 |
aligned | +0.052 |
strength | +0.052 |
bang | +0.050 |
Neg logit contributions | |
ilers | -0.060 |
VIDIA | -0.059 |
irtual | -0.059 |
endi | -0.057 |
ually | -0.054 |
Token | able |
Token ID | 540 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
ilers | +1.810 |
irtual | +1.775 |
VIDIA | +1.749 |
endi | +1.669 |
ually | +1.571 |
Neg logit contributions | |
threat | -3.679 |
credit | -3.609 |
aligned | -3.600 |
strength | -3.572 |
武 | -3.483 |
Token | issue |
Token ID | 2071 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ilers | +1.143 |
VIDIA | +1.129 |
irtual | +1.123 |
endi | +1.086 |
ually | +1.025 |
Neg logit contributions | |
threat | -1.340 |
credit | -1.303 |
aligned | -1.301 |
strength | -1.286 |
bang | -1.253 |
Token | , |
Token ID | 11 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
ilers | +0.422 |
VIDIA | +0.414 |
irtual | +0.414 |
endi | +0.400 |
ually | +0.378 |
Neg logit contributions | |
threat | -0.467 |
credit | -0.451 |
aligned | -0.449 |
strength | -0.445 |
bang | -0.433 |
Token | it |
Token ID | 340 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ilers | +0.140 |
VIDIA | +0.139 |
irtual | +0.138 |
endi | +0.133 |
ually | +0.125 |
Neg logit contributions | |
threat | -0.143 |
credit | -0.138 |
aligned | -0.138 |
strength | -0.136 |
bang | -0.133 |
Token | 's |
Token ID | 338 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
ilers | +0.367 |
irtual | +0.361 |
VIDIA | +0.360 |
endi | +0.348 |
ually | +0.329 |
Neg logit contributions | |
threat | -0.409 |
credit | -0.396 |
aligned | -0.395 |
strength | -0.391 |
bang | -0.379 |
Token | � |
Token ID | 247 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
threat | +0.077 |
credit | +0.074 |
aligned | +0.074 |
strength | +0.073 |
bang | +0.071 |
Neg logit contributions | |
irtual | -0.120 |
ilers | -0.120 |
VIDIA | -0.119 |
endi | -0.114 |
eln | -0.109 |
Token | s |
Token ID | 82 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
VIDIA | +0.097 |
ilers | +0.096 |
irtual | +0.096 |
endi | +0.091 |
LET | +0.087 |
Neg logit contributions | |
threat | -0.087 |
credit | -0.084 |
aligned | -0.083 |
strength | -0.083 |
bang | -0.080 |
Token | very |
Token ID | 845 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
threat | +0.038 |
credit | +0.037 |
aligned | +0.037 |
strength | +0.037 |
bang | +0.036 |
Neg logit contributions | |
ilers | -0.032 |
VIDIA | -0.032 |
irtual | -0.031 |
endi | -0.030 |
LET | -0.028 |
Token | physiology |
Token ID | 38033 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
threat | +0.047 |
credit | +0.046 |
aligned | +0.046 |
strength | +0.045 |
bang | +0.044 |
Neg logit contributions | |
ilers | -0.041 |
VIDIA | -0.041 |
irtual | -0.041 |
endi | -0.039 |
LET | -0.037 |
Token | pre |
Token ID | 662 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
threat | +0.555 |
credit | +0.534 |
aligned | +0.532 |
strength | +0.527 |
bang | +0.511 |
Neg logit contributions | |
ilers | -0.558 |
VIDIA | -0.553 |
irtual | -0.551 |
endi | -0.526 |
LET | -0.497 |
Token | cluded |
Token ID | 10341 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ilers | +0.691 |
VIDIA | +0.684 |
irtual | +0.679 |
endi | +0.646 |
ually | +0.605 |
Neg logit contributions | |
threat | -0.918 |
aligned | -0.891 |
credit | -0.889 |
strength | -0.880 |
bang | -0.857 |
Token | her |
Token ID | 607 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
ilers | +2.814 |
VIDIA | +2.756 |
irtual | +2.738 |
endi | +2.667 |
ually | +2.541 |
Neg logit contributions | |
threat | -2.723 |
aligned | -2.605 |
credit | -2.603 |
strength | -2.547 |
bang | -2.504 |
Token | ability |
Token ID | 2694 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
threat | +0.101 |
credit | +0.097 |
aligned | +0.097 |
strength | +0.096 |
bang | +0.093 |
Neg logit contributions | |
ilers | -0.107 |
irtual | -0.106 |
VIDIA | -0.106 |
endi | -0.102 |
LET | -0.096 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ilers | +0.046 |
VIDIA | +0.045 |
irtual | +0.045 |
endi | +0.044 |
ually | +0.042 |
Neg logit contributions | |
threat | -0.033 |
credit | -0.032 |
aligned | -0.031 |
strength | -0.031 |
bang | -0.030 |
Token | survive |
Token ID | 7866 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ilers | +0.248 |
VIDIA | +0.247 |
irtual | +0.246 |
endi | +0.236 |
LET | +0.222 |
Neg logit contributions | |
threat | -0.282 |
credit | -0.273 |
aligned | -0.271 |
strength | -0.269 |
bang | -0.262 |
Token | the |
Token ID | 262 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
threat | +0.263 |
credit | +0.253 |
aligned | +0.252 |
strength | +0.250 |
bang | +0.243 |
Neg logit contributions | |
ilers | -0.263 |
VIDIA | -0.259 |
irtual | -0.259 |
endi | -0.248 |
LET | -0.234 |
Token | struct |
Token ID | 2878 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ilers | +0.977 |
VIDIA | +0.963 |
irtual | +0.960 |
endi | +0.927 |
ually | +0.877 |
Neg logit contributions | |
threat | -0.903 |
credit | -0.870 |
aligned | -0.865 |
strength | -0.856 |
bang | -0.830 |
Token | Board |
Token ID | 5926 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
ilers | +0.556 |
VIDIA | +0.548 |
irtual | +0.546 |
endi | +0.525 |
ually | +0.494 |
Neg logit contributions | |
threat | -0.629 |
credit | -0.607 |
aligned | -0.605 |
strength | -0.598 |
bang | -0.583 |
Token | { |
Token ID | 1391 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ilers | +1.169 |
VIDIA | +1.154 |
irtual | +1.151 |
endi | +1.108 |
LET | +1.048 |
Neg logit contributions | |
threat | -1.206 |
credit | -1.161 |
aligned | -1.150 |
strength | -1.141 |
bang | -1.109 |
Token | | |
Token ID | 930 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
threat | +0.023 |
credit | +0.022 |
aligned | +0.022 |
strength | +0.022 |
bang | +0.021 |
Neg logit contributions | |
ilers | -0.020 |
VIDIA | -0.020 |
irtual | -0.020 |
endi | -0.019 |
ually | -0.018 |
Token | ^ |
Token ID | 10563 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ilers | +1.215 |
VIDIA | +1.197 |
irtual | +1.194 |
endi | +1.149 |
ually | +1.084 |
Neg logit contributions | |
threat | -1.291 |
credit | -1.245 |
aligned | -1.240 |
strength | -1.226 |
bang | -1.194 |
Token | ^^^^ |
Token ID | 39397 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ilers | +1.972 |
VIDIA | +1.942 |
irtual | +1.936 |
endi | +1.874 |
LET | +1.769 |
Neg logit contributions | |
threat | -1.969 |
credit | -1.892 |
aligned | -1.877 |
strength | -1.866 |
bang | -1.811 |
Token | ^^^^ |
Token ID | 39397 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ilers | +2.704 |
VIDIA | +2.659 |
irtual | +2.638 |
endi | +2.567 |
LET | +2.426 |
Neg logit contributions | |
threat | -2.725 |
credit | -2.618 |
aligned | -2.598 |
strength | -2.589 |
bang | -2.501 |
Token | ^^ |
Token ID | 18237 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
ilers | +2.507 |
VIDIA | +2.454 |
irtual | +2.443 |
endi | +2.373 |
LET | +2.245 |
Neg logit contributions | |
threat | -2.553 |
credit | -2.463 |
aligned | -2.448 |
strength | -2.431 |
bang | -2.348 |
Token | ^ |
Token ID | 61 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ilers | +1.393 |
VIDIA | +1.368 |
irtual | +1.363 |
endi | +1.313 |
ually | +1.234 |
Neg logit contributions | |
threat | -1.575 |
credit | -1.518 |
aligned | -1.511 |
strength | -1.498 |
bang | -1.455 |
Token | recursive |
Token ID | 45115 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
ilers | +0.345 |
VIDIA | +0.341 |
irtual | +0.339 |
endi | +0.325 |
ually | +0.305 |
Neg logit contributions | |
threat | -0.422 |
credit | -0.408 |
aligned | -0.407 |
strength | -0.403 |
bang | -0.393 |
Token | type |
Token ID | 2099 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
ilers | +1.017 |
VIDIA | +1.001 |
irtual | +0.998 |
endi | +0.958 |
ually | +0.902 |
Neg logit contributions | |
threat | -1.160 |
credit | -1.121 |
aligned | -1.116 |
strength | -1.105 |
bang | -1.075 |
Token | to |
Token ID | 284 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
ilers | +0.044 |
VIDIA | +0.044 |
irtual | +0.043 |
endi | +0.042 |
ually | +0.040 |
Neg logit contributions | |
threat | -0.033 |
credit | -0.032 |
aligned | -0.032 |
strength | -0.031 |
bang | -0.030 |
Token | work |
Token ID | 670 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
threat | +0.101 |
credit | +0.097 |
aligned | +0.097 |
strength | +0.096 |
bang | +0.094 |
Neg logit contributions | |
ilers | -0.094 |
VIDIA | -0.093 |
irtual | -0.093 |
endi | -0.089 |
LET | -0.084 |
Token | together |
Token ID | 1978 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
threat | +0.353 |
credit | +0.340 |
aligned | +0.339 |
strength | +0.336 |
bang | +0.327 |
Neg logit contributions | |
ilers | -0.319 |
VIDIA | -0.316 |
irtual | -0.314 |
endi | -0.304 |
ually | -0.287 |
Token | if |
Token ID | 611 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ilers | +1.098 |
irtual | +1.083 |
VIDIA | +1.080 |
endi | +1.066 |
ually | +1.010 |
Neg logit contributions | |
threat | -1.124 |
credit | -1.085 |
aligned | -1.080 |
strength | -1.070 |
bang | -1.040 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
threat | +0.363 |
credit | +0.349 |
aligned | +0.348 |
strength | +0.344 |
bang | +0.334 |
Neg logit contributions | |
ilers | -0.392 |
VIDIA | -0.387 |
irtual | -0.386 |
endi | -0.372 |
ually | -0.351 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
ilers | +0.322 |
VIDIA | +0.317 |
irtual | +0.316 |
endi | +0.307 |
ually | +0.291 |
Neg logit contributions | |
threat | -0.260 |
credit | -0.250 |
aligned | -0.249 |
strength | -0.246 |
bang | -0.238 |
Token | was |
Token ID | 373 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ilers | +2.592 |
VIDIA | +2.526 |
irtual | +2.514 |
endi | +2.447 |
ually | +2.345 |
Neg logit contributions | |
threat | -2.815 |
credit | -2.743 |
strength | -2.727 |
aligned | -2.714 |
bang | -2.643 |
Token | also |
Token ID | 635 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
ilers | +0.392 |
irtual | +0.384 |
VIDIA | +0.384 |
endi | +0.374 |
ually | +0.354 |
Neg logit contributions | |
threat | -0.367 |
credit | -0.356 |
aligned | -0.353 |
strength | -0.350 |
bang | -0.341 |
Token | sovereign |
Token ID | 18901 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
threat | +0.391 |
credit | +0.376 |
aligned | +0.375 |
strength | +0.370 |
bang | +0.360 |
Neg logit contributions | |
ilers | -0.423 |
VIDIA | -0.418 |
irtual | -0.416 |
endi | -0.401 |
ually | -0.379 |
Token | . |
Token ID | 13 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
threat | +0.021 |
credit | +0.020 |
aligned | +0.020 |
strength | +0.020 |
bang | +0.019 |
Neg logit contributions | |
ilers | -0.017 |
VIDIA | -0.017 |
irtual | -0.017 |
endi | -0.016 |
ually | -0.015 |
Token | Who |
Token ID | 5338 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ilers | +0.099 |
VIDIA | +0.098 |
irtual | +0.098 |
endi | +0.094 |
ually | +0.089 |
Neg logit contributions | |
threat | -0.097 |
credit | -0.094 |
aligned | -0.094 |
strength | -0.093 |
bang | -0.090 |
Token | have |
Token ID | 423 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ilers | +0.044 |
VIDIA | +0.044 |
irtual | +0.044 |
endi | +0.042 |
LET | +0.040 |
Neg logit contributions | |
threat | -0.048 |
credit | -0.047 |
aligned | -0.047 |
strength | -0.046 |
bang | -0.045 |
Token | decided |
Token ID | 3066 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ilers | +0.500 |
VIDIA | +0.494 |
irtual | +0.492 |
endi | +0.472 |
ually | +0.444 |
Neg logit contributions | |
threat | -0.558 |
credit | -0.539 |
aligned | -0.538 |
strength | -0.532 |
bang | -0.518 |
Token | to |
Token ID | 284 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ilers | +0.899 |
VIDIA | +0.887 |
irtual | +0.884 |
endi | +0.853 |
ually | +0.806 |
Neg logit contributions | |
threat | -0.858 |
credit | -0.827 |
aligned | -0.824 |
strength | -0.814 |
bang | -0.792 |
Token | do |
Token ID | 466 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
ilers | +0.356 |
VIDIA | +0.355 |
irtual | +0.352 |
endi | +0.340 |
LET | +0.318 |
Neg logit contributions | |
threat | -0.370 |
credit | -0.358 |
aligned | -0.356 |
strength | -0.351 |
bang | -0.343 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ilers | +0.416 |
VIDIA | +0.411 |
irtual | +0.410 |
endi | +0.396 |
ually | +0.375 |
Neg logit contributions | |
threat | -0.365 |
credit | -0.351 |
aligned | -0.350 |
strength | -0.345 |
bang | -0.335 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ilers | +0.307 |
VIDIA | +0.303 |
irtual | +0.302 |
endi | +0.292 |
LET | +0.274 |
Neg logit contributions | |
threat | -0.298 |
credit | -0.288 |
aligned | -0.287 |
strength | -0.283 |
bang | -0.276 |
Token | and |
Token ID | 290 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ilers | +2.380 |
VIDIA | +2.338 |
irtual | +2.335 |
endi | +2.247 |
ually | +2.142 |
Neg logit contributions | |
threat | -2.982 |
aligned | -2.894 |
credit | -2.884 |
strength | -2.870 |
bang | -2.774 |
Token | will |
Token ID | 481 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ilers | +0.212 |
VIDIA | +0.209 |
irtual | +0.209 |
endi | +0.200 |
LET | +0.188 |
Neg logit contributions | |
threat | -0.232 |
credit | -0.224 |
aligned | -0.223 |
strength | -0.221 |
bang | -0.215 |
Token | work |
Token ID | 670 |
Feature activation | +1.92e-03 |
Pos logit contributions | |
VIDIA | +0.272 |
ilers | +0.271 |
irtual | +0.271 |
endi | +0.259 |
LET | +0.242 |
Neg logit contributions | |
threat | -0.305 |
credit | -0.295 |
aligned | -0.294 |
strength | -0.290 |
bang | -0.284 |
Token | to |
Token ID | 284 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ilers | +0.004 |
VIDIA | +0.004 |
irtual | +0.004 |
endi | +0.004 |
ually | +0.003 |
Neg logit contributions | |
threat | -0.003 |
credit | -0.003 |
aligned | -0.003 |
strength | -0.003 |
bang | -0.003 |
Token | put |
Token ID | 1234 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
ilers | +0.347 |
VIDIA | +0.345 |
irtual | +0.343 |
endi | +0.330 |
LET | +0.309 |
Neg logit contributions | |
threat | -0.379 |
credit | -0.366 |
aligned | -0.366 |
strength | -0.361 |
bang | -0.352 |
Token | who |
Token ID | 508 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ilers | +0.215 |
VIDIA | +0.211 |
irtual | +0.211 |
endi | +0.204 |
ually | +0.192 |
Neg logit contributions | |
threat | -0.236 |
credit | -0.228 |
aligned | -0.227 |
strength | -0.225 |
bang | -0.219 |
Token | consume |
Token ID | 15000 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
threat | +0.282 |
credit | +0.272 |
aligned | +0.272 |
strength | +0.268 |
bang | +0.263 |
Neg logit contributions | |
VIDIA | -0.215 |
ilers | -0.213 |
irtual | -0.211 |
endi | -0.201 |
LET | -0.188 |
Token | toxin |
Token ID | 43026 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
ilers | +0.958 |
VIDIA | +0.943 |
irtual | +0.938 |
endi | +0.909 |
ually | +0.856 |
Neg logit contributions | |
threat | -1.053 |
credit | -1.020 |
aligned | -1.015 |
strength | -1.005 |
bang | -0.977 |
Token | - |
Token ID | 12 |
Feature activation | +4.75e-03 |
Pos logit contributions | |
threat | +0.780 |
aligned | +0.748 |
credit | +0.743 |
strength | +0.736 |
bang | +0.719 |
Neg logit contributions | |
ilers | -0.861 |
VIDIA | -0.861 |
irtual | -0.855 |
endi | -0.817 |
LET | -0.775 |
Token | cont |
Token ID | 3642 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ilers | +0.010 |
VIDIA | +0.010 |
irtual | +0.010 |
endi | +0.010 |
ually | +0.009 |
Neg logit contributions | |
threat | -0.008 |
credit | -0.007 |
aligned | -0.007 |
strength | -0.007 |
bang | -0.007 |
Token | am |
Token ID | 321 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
threat | +0.693 |
aligned | +0.659 |
credit | +0.658 |
strength | +0.647 |
bang | +0.623 |
Neg logit contributions | |
VIDIA | -1.012 |
ilers | -0.996 |
irtual | -0.996 |
endi | -0.955 |
LET | -0.923 |
Token | inated |
Token ID | 3898 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
ilers | +2.153 |
irtual | +2.094 |
VIDIA | +2.083 |
endi | +2.014 |
ually | +1.882 |
Neg logit contributions | |
threat | -3.180 |
credit | -3.089 |
aligned | -3.080 |
strength | -3.062 |
bang | -2.990 |
Token | shell |
Token ID | 7582 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ilers | +0.835 |
VIDIA | +0.823 |
irtual | +0.820 |
endi | +0.791 |
ually | +0.746 |
Neg logit contributions | |
threat | -0.851 |
credit | -0.822 |
aligned | -0.819 |
strength | -0.810 |
bang | -0.788 |
Token | fish |
Token ID | 11084 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
threat | +0.244 |
credit | +0.232 |
aligned | +0.231 |
strength | +0.228 |
bang | +0.219 |
Neg logit contributions | |
ilers | -0.414 |
VIDIA | -0.410 |
irtual | -0.409 |
endi | -0.397 |
ually | -0.379 |
Token | and |
Token ID | 290 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ilers | +0.033 |
VIDIA | +0.032 |
irtual | +0.032 |
endi | +0.031 |
ually | +0.029 |
Neg logit contributions | |
threat | -0.037 |
credit | -0.035 |
aligned | -0.035 |
strength | -0.035 |
bang | -0.034 |
Token | can |
Token ID | 460 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ilers | +0.183 |
VIDIA | +0.181 |
irtual | +0.181 |
endi | +0.172 |
LET | +0.163 |
Neg logit contributions | |
threat | -0.198 |
credit | -0.190 |
aligned | -0.190 |
strength | -0.188 |
bang | -0.183 |
Token | it |
Token ID | 340 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
threat | +0.024 |
credit | +0.023 |
aligned | +0.023 |
strength | +0.023 |
bang | +0.022 |
Neg logit contributions | |
ilers | -0.022 |
VIDIA | -0.022 |
irtual | -0.022 |
endi | -0.021 |
LET | -0.020 |
Token | as |
Token ID | 355 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
ilers | +0.290 |
VIDIA | +0.285 |
irtual | +0.285 |
endi | +0.275 |
ually | +0.260 |
Neg logit contributions | |
threat | -0.298 |
credit | -0.288 |
aligned | -0.287 |
strength | -0.284 |
bang | -0.277 |
Token | more |
Token ID | 517 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
threat | +0.006 |
credit | +0.005 |
aligned | +0.005 |
strength | +0.005 |
bang | +0.005 |
Neg logit contributions | |
ilers | -0.006 |
VIDIA | -0.006 |
irtual | -0.006 |
endi | -0.006 |
ually | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
ilers | +0.272 |
VIDIA | +0.268 |
irtual | +0.267 |
endi | +0.258 |
ually | +0.244 |
Neg logit contributions | |
threat | -0.278 |
credit | -0.268 |
aligned | -0.268 |
strength | -0.264 |
bang | -0.256 |
Token | the |
Token ID | 262 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
ilers | +0.125 |
VIDIA | +0.123 |
irtual | +0.123 |
endi | +0.119 |
ually | +0.112 |
Neg logit contributions | |
threat | -0.115 |
credit | -0.111 |
aligned | -0.111 |
strength | -0.109 |
bang | -0.106 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ilers | +0.064 |
VIDIA | +0.063 |
irtual | +0.062 |
endi | +0.060 |
ually | +0.057 |
Neg logit contributions | |
threat | -0.069 |
credit | -0.067 |
aligned | -0.066 |
strength | -0.066 |
bang | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
ilers | +2.394 |
VIDIA | +2.352 |
irtual | +2.327 |
endi | +2.264 |
ually | +2.167 |
Neg logit contributions | |
threat | -2.883 |
aligned | -2.797 |
credit | -2.781 |
strength | -2.767 |
bang | -2.679 |
Token | It |
Token ID | 632 |
Feature activation | +4.22e-04 |
Pos logit contributions | |
ilers | +0.089 |
VIDIA | +0.088 |
irtual | +0.088 |
endi | +0.084 |
ually | +0.079 |
Neg logit contributions | |
threat | -0.098 |
credit | -0.095 |
aligned | -0.094 |
strength | -0.093 |
bang | -0.091 |
Token | seems |
Token ID | 2331 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ilers | +0.001 |
VIDIA | +0.001 |
irtual | +0.001 |
endi | +0.001 |
ually | +0.001 |
Neg logit contributions | |
threat | -0.001 |
credit | -0.001 |
aligned | -0.001 |
strength | -0.001 |
bang | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ilers | +0.465 |
VIDIA | +0.457 |
irtual | +0.456 |
endi | +0.442 |
ually | +0.419 |
Neg logit contributions | |
threat | -0.425 |
credit | -0.410 |
aligned | -0.408 |
strength | -0.403 |
bang | -0.392 |
Token | De |
Token ID | 1024 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
ilers | +0.321 |
VIDIA | +0.317 |
irtual | +0.316 |
endi | +0.304 |
ually | +0.286 |
Neg logit contributions | |
threat | -0.336 |
credit | -0.325 |
aligned | -0.324 |
strength | -0.320 |
bang | -0.312 |
Token | unf |
Token ID | 3684 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ilers | +0.178 |
VIDIA | +0.175 |
irtual | +0.175 |
endi | +0.169 |
ually | +0.160 |
Neg logit contributions | |
threat | -0.165 |
credit | -0.159 |
aligned | -0.158 |
strength | -0.156 |
bang | -0.152 |
Token | il |
Token ID | 346 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
VIDIA | +0.312 |
ilers | +0.309 |
irtual | +0.307 |
endi | +0.293 |
LET | +0.276 |
Neg logit contributions | |
threat | -0.391 |
credit | -0.377 |
aligned | -0.376 |
strength | -0.371 |
bang | -0.362 |
Token | tered |
Token ID | 4400 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
ilers | +0.917 |
VIDIA | +0.904 |
irtual | +0.901 |
endi | +0.865 |
ually | +0.813 |
Neg logit contributions | |
threat | -1.053 |
credit | -1.017 |
aligned | -1.014 |
strength | -1.003 |
bang | -0.978 |
Token | , |
Token ID | 11 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ilers | +0.882 |
VIDIA | +0.871 |
irtual | +0.867 |
endi | +0.835 |
ually | +0.786 |
Neg logit contributions | |
threat | -0.928 |
credit | -0.896 |
aligned | -0.893 |
strength | -0.883 |
bang | -0.860 |
Token | unp |
Token ID | 8593 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
ilers | +0.333 |
VIDIA | +0.329 |
irtual | +0.328 |
endi | +0.316 |
ually | +0.298 |
Neg logit contributions | |
threat | -0.331 |
credit | -0.319 |
aligned | -0.318 |
strength | -0.314 |
bang | -0.306 |
Token | aste |
Token ID | 4594 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
threat | +0.238 |
credit | +0.225 |
aligned | +0.225 |
strength | +0.223 |
bang | +0.211 |
Neg logit contributions | |
VIDIA | -0.413 |
ilers | -0.412 |
irtual | -0.408 |
endi | -0.396 |
ually | -0.379 |
Token | ur |
Token ID | 333 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
ilers | +2.510 |
irtual | +2.448 |
VIDIA | +2.428 |
endi | +2.345 |
ually | +2.235 |
Neg logit contributions | |
threat | -2.803 |
credit | -2.726 |
aligned | -2.705 |
strength | -2.678 |
bang | -2.608 |
Token | ised |
Token ID | 1417 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
ilers | +1.158 |
irtual | +1.143 |
VIDIA | +1.142 |
endi | +1.107 |
ually | +1.054 |
Neg logit contributions | |
threat | -0.850 |
credit | -0.816 |
aligned | -0.813 |
strength | -0.799 |
bang | -0.775 |
Token | , |
Token ID | 11 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ilers | +0.891 |
VIDIA | +0.880 |
irtual | +0.877 |
endi | +0.844 |
ually | +0.796 |
Neg logit contributions | |
threat | -0.912 |
credit | -0.880 |
aligned | -0.877 |
strength | -0.866 |
bang | -0.844 |
Token | and |
Token ID | 290 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ilers | +0.353 |
VIDIA | +0.349 |
irtual | +0.347 |
endi | +0.334 |
ually | +0.315 |
Neg logit contributions | |
threat | -0.359 |
credit | -0.346 |
aligned | -0.345 |
strength | -0.341 |
bang | -0.332 |
Token | brewed |
Token ID | 40163 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ilers | +0.357 |
VIDIA | +0.353 |
irtual | +0.351 |
endi | +0.338 |
ually | +0.319 |
Neg logit contributions | |
threat | -0.347 |
credit | -0.334 |
aligned | -0.333 |
strength | -0.330 |
bang | -0.321 |
Token | on |
Token ID | 319 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
ilers | +1.570 |
VIDIA | +1.544 |
irtual | +1.540 |
endi | +1.503 |
ually | +1.419 |
Neg logit contributions | |
threat | -1.583 |
credit | -1.530 |
aligned | -1.517 |
strength | -1.502 |
bang | -1.460 |
Token | the |
Token ID | 262 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
ilers | +0.057 |
VIDIA | +0.056 |
irtual | +0.056 |
endi | +0.054 |
ually | +0.051 |
Neg logit contributions | |
threat | -0.057 |
credit | -0.055 |
aligned | -0.055 |
strength | -0.054 |
bang | -0.053 |
Token | ground |
Token ID | 2323 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
ilers | +0.033 |
VIDIA | +0.032 |
irtual | +0.031 |
endi | +0.027 |
LET | +0.021 |
Neg logit contributions | |
threat | -0.174 |
credit | -0.170 |
aligned | -0.170 |
strength | -0.169 |
bang | -0.166 |
Token | — |
Token ID | 851 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
ilers | +1.099 |
VIDIA | +1.080 |
irtual | +1.077 |
endi | +1.041 |
ually | +0.985 |
Neg logit contributions | |
threat | -1.201 |
credit | -1.163 |
aligned | -1.156 |
strength | -1.145 |
bang | -1.116 |
Token | the |
Token ID | 262 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ilers | +0.128 |
VIDIA | +0.127 |
irtual | +0.126 |
endi | +0.122 |
ually | +0.115 |
Neg logit contributions | |
threat | -0.118 |
credit | -0.114 |
aligned | -0.113 |
strength | -0.112 |
bang | -0.109 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
threat | +0.019 |
credit | +0.018 |
aligned | +0.018 |
strength | +0.018 |
bang | +0.017 |
Neg logit contributions | |
ilers | -0.021 |
VIDIA | -0.021 |
irtual | -0.021 |
endi | -0.020 |
ually | -0.019 |
Token | is |
Token ID | 318 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ilers | +2.583 |
VIDIA | +2.530 |
irtual | +2.505 |
endi | +2.457 |
ually | +2.370 |
Neg logit contributions | |
threat | -2.607 |
credit | -2.547 |
aligned | -2.534 |
strength | -2.509 |
bang | -2.443 |
Token | what |
Token ID | 644 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ilers | +0.046 |
VIDIA | +0.045 |
irtual | +0.045 |
endi | +0.044 |
ually | +0.041 |
Neg logit contributions | |
threat | -0.048 |
credit | -0.046 |
aligned | -0.046 |
strength | -0.046 |
bang | -0.044 |
Token | matters |
Token ID | 6067 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ilers | +0.248 |
VIDIA | +0.246 |
irtual | +0.245 |
endi | +0.236 |
ually | +0.223 |
Neg logit contributions | |
threat | -0.218 |
credit | -0.209 |
aligned | -0.209 |
strength | -0.206 |
bang | -0.200 |
Token | most |
Token ID | 749 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
threat | +0.391 |
credit | +0.377 |
aligned | +0.376 |
strength | +0.371 |
bang | +0.361 |
Neg logit contributions | |
ilers | -0.402 |
VIDIA | -0.397 |
irtual | -0.396 |
endi | -0.382 |
ually | -0.360 |
Token | in |
Token ID | 287 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
ilers | +0.726 |
VIDIA | +0.709 |
irtual | +0.708 |
endi | +0.689 |
ually | +0.656 |
Neg logit contributions | |
threat | -0.672 |
credit | -0.651 |
aligned | -0.647 |
strength | -0.641 |
bang | -0.624 |
Token | The |
Token ID | 383 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ilers | +0.138 |
VIDIA | +0.137 |
irtual | +0.136 |
endi | +0.131 |
ually | +0.123 |
Neg logit contributions | |
threat | -0.136 |
credit | -0.131 |
aligned | -0.131 |
strength | -0.129 |
bang | -0.125 |
Token | opening |
Token ID | 4756 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
threat | +0.235 |
credit | +0.227 |
aligned | +0.225 |
strength | +0.224 |
bang | +0.217 |
Neg logit contributions | |
ilers | -0.200 |
irtual | -0.198 |
VIDIA | -0.198 |
endi | -0.188 |
LET | -0.177 |
Token | mission |
Token ID | 4365 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ilers | +0.112 |
irtual | +0.111 |
VIDIA | +0.110 |
endi | +0.105 |
LET | +0.098 |
Neg logit contributions | |
threat | -0.132 |
credit | -0.129 |
aligned | -0.126 |
strength | -0.125 |
bang | -0.122 |
Token | of |
Token ID | 286 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
ilers | +0.377 |
VIDIA | +0.372 |
irtual | +0.371 |
endi | +0.357 |
ually | +0.336 |
Neg logit contributions | |
threat | -0.363 |
credit | -0.349 |
aligned | -0.348 |
strength | -0.343 |
bang | -0.335 |
Token | the |
Token ID | 262 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
threat | +0.185 |
credit | +0.179 |
aligned | +0.178 |
strength | +0.176 |
bang | +0.172 |
Neg logit contributions | |
ilers | -0.181 |
VIDIA | -0.179 |
irtual | -0.178 |
endi | -0.171 |
LET | -0.161 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
threat | +0.130 |
credit | +0.126 |
aligned | +0.125 |
strength | +0.124 |
bang | +0.121 |
Neg logit contributions | |
ilers | -0.105 |
VIDIA | -0.104 |
irtual | -0.104 |
endi | -0.099 |
LET | -0.093 |
Token | title |
Token ID | 3670 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
ilers | +2.601 |
VIDIA | +2.575 |
irtual | +2.554 |
endi | +2.474 |
ually | +2.379 |
Neg logit contributions | |
threat | -2.613 |
aligned | -2.534 |
strength | -2.515 |
credit | -2.511 |
bang | -2.430 |
Token | is |
Token ID | 318 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
threat | +0.151 |
credit | +0.145 |
aligned | +0.144 |
strength | +0.142 |
bang | +0.139 |
Neg logit contributions | |
ilers | -0.159 |
VIDIA | -0.157 |
irtual | -0.156 |
endi | -0.151 |
LET | -0.142 |
Token | especially |
Token ID | 2592 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ilers | +0.028 |
VIDIA | +0.028 |
irtual | +0.028 |
endi | +0.027 |
LET | +0.025 |
Neg logit contributions | |
threat | -0.029 |
credit | -0.028 |
aligned | -0.027 |
strength | -0.027 |
bang | -0.027 |
Token | appealing |
Token ID | 16403 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
threat | +0.276 |
credit | +0.268 |
aligned | +0.266 |
strength | +0.263 |
bang | +0.258 |
Neg logit contributions | |
ilers | -0.256 |
irtual | -0.252 |
VIDIA | -0.252 |
endi | -0.241 |
LET | -0.226 |
Token | , |
Token ID | 11 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
threat | +0.138 |
credit | +0.133 |
aligned | +0.133 |
strength | +0.131 |
bang | +0.128 |
Neg logit contributions | |
ilers | -0.136 |
VIDIA | -0.135 |
irtual | -0.134 |
endi | -0.129 |
ually | -0.122 |
Token | it |
Token ID | 340 |
Feature activation | +3.56e-03 |
Pos logit contributions | |
ilers | +0.125 |
VIDIA | +0.124 |
irtual | +0.123 |
endi | +0.119 |
ually | +0.112 |
Neg logit contributions | |
threat | -0.127 |
credit | -0.123 |
aligned | -0.122 |
strength | -0.121 |
bang | -0.118 |
Token | is |
Token ID | 318 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
ilers | +0.007 |
VIDIA | +0.007 |
irtual | +0.007 |
endi | +0.006 |
ually | +0.006 |
Neg logit contributions | |
threat | -0.007 |
credit | -0.006 |
aligned | -0.006 |
strength | -0.006 |
bang | -0.006 |
Token | for |
Token ID | 329 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ilers | +0.542 |
VIDIA | +0.535 |
irtual | +0.533 |
endi | +0.512 |
ually | +0.482 |
Neg logit contributions | |
threat | -0.590 |
credit | -0.569 |
aligned | -0.568 |
strength | -0.561 |
bang | -0.547 |
Token | making |
Token ID | 1642 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ilers | +0.233 |
VIDIA | +0.231 |
irtual | +0.230 |
endi | +0.220 |
ually | +0.207 |
Neg logit contributions | |
threat | -0.261 |
credit | -0.252 |
aligned | -0.251 |
strength | -0.249 |
bang | -0.242 |
Token | the |
Token ID | 262 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
ilers | +0.355 |
VIDIA | +0.351 |
irtual | +0.350 |
endi | +0.335 |
ually | +0.314 |
Neg logit contributions | |
threat | -0.423 |
credit | -0.409 |
aligned | -0.408 |
strength | -0.404 |
bang | -0.394 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ilers | +0.086 |
VIDIA | +0.085 |
irtual | +0.085 |
endi | +0.082 |
ually | +0.077 |
Neg logit contributions | |
threat | -0.080 |
credit | -0.077 |
aligned | -0.077 |
strength | -0.076 |
bang | -0.074 |
Token | argument |
Token ID | 4578 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
ilers | +2.694 |
VIDIA | +2.666 |
irtual | +2.621 |
endi | +2.555 |
ually | +2.468 |
Neg logit contributions | |
threat | -2.484 |
credit | -2.422 |
aligned | -2.409 |
strength | -2.380 |
bang | -2.315 |
Token | — |
Token ID | 960 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
threat | +0.705 |
credit | +0.680 |
aligned | +0.678 |
strength | +0.671 |
bang | +0.653 |
Neg logit contributions | |
ilers | -0.622 |
irtual | -0.615 |
VIDIA | -0.612 |
endi | -0.581 |
LET | -0.547 |
Token | that |
Token ID | 5562 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
threat | +0.351 |
credit | +0.337 |
aligned | +0.335 |
strength | +0.331 |
bang | +0.320 |
Neg logit contributions | |
ilers | -0.469 |
VIDIA | -0.464 |
irtual | -0.462 |
endi | -0.448 |
ually | -0.426 |
Token | it |
Token ID | 340 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
ilers | +0.667 |
VIDIA | +0.658 |
irtual | +0.655 |
endi | +0.631 |
ually | +0.595 |
Neg logit contributions | |
threat | -0.704 |
credit | -0.681 |
aligned | -0.678 |
strength | -0.670 |
bang | -0.653 |
Token | was |
Token ID | 373 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
ilers | +0.063 |
VIDIA | +0.062 |
irtual | +0.062 |
endi | +0.060 |
ually | +0.057 |
Neg logit contributions | |
threat | -0.060 |
credit | -0.058 |
aligned | -0.058 |
strength | -0.057 |
bang | -0.056 |
Token | places |
Token ID | 4113 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
threat | +0.290 |
credit | +0.281 |
aligned | +0.279 |
strength | +0.277 |
bang | +0.270 |
Neg logit contributions | |
ilers | -0.224 |
VIDIA | -0.221 |
irtual | -0.220 |
endi | -0.211 |
ually | -0.195 |
Token | — |
Token ID | 960 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ilers | +0.768 |
irtual | +0.747 |
VIDIA | +0.744 |
endi | +0.723 |
ually | +0.687 |
Neg logit contributions | |
threat | -0.871 |
credit | -0.843 |
aligned | -0.840 |
strength | -0.833 |
bang | -0.808 |
Token | but |
Token ID | 4360 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
threat | +0.435 |
credit | +0.414 |
aligned | +0.412 |
strength | +0.406 |
bang | +0.391 |
Neg logit contributions | |
ilers | -0.739 |
VIDIA | -0.732 |
irtual | -0.730 |
endi | -0.709 |
ually | -0.677 |
Token | only |
Token ID | 691 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ilers | +0.088 |
VIDIA | +0.087 |
irtual | +0.087 |
endi | +0.083 |
LET | +0.078 |
Neg logit contributions | |
threat | -0.086 |
credit | -0.083 |
aligned | -0.083 |
strength | -0.082 |
bang | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
threat | +0.379 |
credit | +0.363 |
aligned | +0.361 |
strength | +0.357 |
bang | +0.346 |
Neg logit contributions | |
ilers | -0.495 |
VIDIA | -0.492 |
irtual | -0.490 |
endi | -0.472 |
LET | -0.448 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
threat | +0.184 |
credit | +0.178 |
aligned | +0.177 |
strength | +0.175 |
bang | +0.170 |
Neg logit contributions | |
ilers | -0.202 |
VIDIA | -0.200 |
irtual | -0.199 |
endi | -0.192 |
ually | -0.181 |
Token | was |
Token ID | 373 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ilers | +2.597 |
VIDIA | +2.548 |
irtual | +2.525 |
endi | +2.464 |
ually | +2.375 |
Neg logit contributions | |
threat | -2.585 |
aligned | -2.499 |
credit | -2.483 |
strength | -2.483 |
bang | -2.397 |
Token | able |
Token ID | 1498 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
threat | +0.316 |
credit | +0.305 |
aligned | +0.303 |
strength | +0.299 |
bang | +0.292 |
Neg logit contributions | |
ilers | -0.324 |
VIDIA | -0.320 |
irtual | -0.319 |
endi | -0.307 |
LET | -0.288 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ilers | +0.126 |
irtual | +0.124 |
VIDIA | +0.124 |
endi | +0.120 |
ually | +0.115 |
Neg logit contributions | |
threat | -0.089 |
credit | -0.085 |
aligned | -0.085 |
strength | -0.084 |
bang | -0.081 |
Token | capitalize |
Token ID | 35160 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
VIDIA | +0.261 |
ilers | +0.260 |
irtual | +0.259 |
endi | +0.250 |
LET | +0.235 |
Neg logit contributions | |
threat | -0.269 |
credit | -0.260 |
aligned | -0.258 |
strength | -0.255 |
bang | -0.249 |
Token | on |
Token ID | 319 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
ilers | +0.732 |
VIDIA | +0.725 |
irtual | +0.724 |
endi | +0.698 |
ually | +0.670 |
Neg logit contributions | |
threat | -0.568 |
aligned | -0.544 |
credit | -0.543 |
strength | -0.536 |
bang | -0.519 |
Token | across |
Token ID | 1973 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
ilers | +0.819 |
VIDIA | +0.797 |
irtual | +0.793 |
endi | +0.775 |
ually | +0.729 |
Neg logit contributions | |
threat | -0.956 |
credit | -0.933 |
aligned | -0.920 |
strength | -0.916 |
bang | -0.892 |
Token | the |
Token ID | 262 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
ilers | +0.120 |
VIDIA | +0.118 |
irtual | +0.118 |
endi | +0.114 |
ually | +0.108 |
Neg logit contributions | |
threat | -0.114 |
credit | -0.110 |
aligned | -0.109 |
strength | -0.108 |
bang | -0.105 |
Token | globe |
Token ID | 13342 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ilers | +0.209 |
VIDIA | +0.207 |
irtual | +0.206 |
endi | +0.200 |
ually | +0.191 |
Neg logit contributions | |
threat | -0.135 |
credit | -0.129 |
aligned | -0.128 |
strength | -0.127 |
bang | -0.122 |
Token | . |
Token ID | 13 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
threat | +0.026 |
credit | +0.025 |
aligned | +0.025 |
strength | +0.025 |
bang | +0.024 |
Neg logit contributions | |
ilers | -0.019 |
VIDIA | -0.019 |
irtual | -0.019 |
endi | -0.018 |
ually | -0.017 |
Token | The |
Token ID | 383 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ilers | +0.085 |
VIDIA | +0.084 |
irtual | +0.084 |
endi | +0.081 |
LET | +0.077 |
Neg logit contributions | |
threat | -0.082 |
credit | -0.079 |
aligned | -0.079 |
strength | -0.078 |
bang | -0.076 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
threat | +0.209 |
credit | +0.202 |
aligned | +0.201 |
strength | +0.198 |
bang | +0.193 |
Neg logit contributions | |
ilers | -0.242 |
VIDIA | -0.239 |
irtual | -0.238 |
endi | -0.230 |
ually | -0.218 |
Token | two |
Token ID | 734 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ilers | +2.454 |
VIDIA | +2.402 |
irtual | +2.370 |
endi | +2.337 |
ually | +2.223 |
Neg logit contributions | |
threat | -2.659 |
credit | -2.601 |
aligned | -2.584 |
strength | -2.570 |
bang | -2.512 |
Token | problems |
Token ID | 2761 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ilers | +0.657 |
VIDIA | +0.649 |
irtual | +0.646 |
endi | +0.624 |
ually | +0.590 |
Neg logit contributions | |
threat | -0.612 |
credit | -0.590 |
aligned | -0.587 |
strength | -0.581 |
bang | -0.564 |
Token | — |
Token ID | 851 |
Feature activation | +9.80e-02 |
Pos logit contributions | |
ilers | +0.258 |
VIDIA | +0.255 |
irtual | +0.254 |
endi | +0.243 |
LET | +0.228 |
Neg logit contributions | |
threat | -0.299 |
credit | -0.288 |
aligned | -0.287 |
strength | -0.284 |
bang | -0.276 |
Token | how |
Token ID | 703 |
Feature activation | -6.79e-03 |
Pos logit contributions | |
ilers | +0.196 |
VIDIA | +0.194 |
irtual | +0.193 |
endi | +0.187 |
ually | +0.177 |
Neg logit contributions | |
threat | -0.175 |
credit | -0.168 |
aligned | -0.168 |
strength | -0.166 |
bang | -0.161 |
Token | to |
Token ID | 284 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
threat | +0.011 |
credit | +0.011 |
aligned | +0.011 |
strength | +0.011 |
bang | +0.010 |
Neg logit contributions | |
ilers | -0.014 |
VIDIA | -0.014 |
irtual | -0.014 |
endi | -0.014 |
ually | -0.013 |
Token | Ancient |
Token ID | 13406 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
ilers | +0.020 |
VIDIA | +0.020 |
irtual | +0.020 |
endi | +0.019 |
LET | +0.017 |
Neg logit contributions | |
threat | -0.022 |
credit | -0.021 |
aligned | -0.021 |
strength | -0.021 |
bang | -0.020 |
Token | Greece |
Token ID | 10315 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
ilers | +0.870 |
VIDIA | +0.860 |
irtual | +0.857 |
endi | +0.829 |
ually | +0.790 |
Neg logit contributions | |
threat | -0.668 |
credit | -0.640 |
aligned | -0.638 |
strength | -0.628 |
bang | -0.609 |
Token | focused |
Token ID | 5670 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
ilers | +0.693 |
VIDIA | +0.684 |
irtual | +0.682 |
endi | +0.660 |
ually | +0.626 |
Neg logit contributions | |
threat | -0.663 |
credit | -0.640 |
aligned | -0.637 |
strength | -0.630 |
bang | -0.612 |
Token | un |
Token ID | 555 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
threat | +0.064 |
credit | +0.062 |
aligned | +0.062 |
strength | +0.061 |
bang | +0.059 |
Neg logit contributions | |
ilers | -0.079 |
VIDIA | -0.078 |
irtual | -0.078 |
endi | -0.075 |
ually | -0.071 |
Token | ash |
Token ID | 1077 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
threat | +0.097 |
credit | +0.093 |
aligned | +0.092 |
strength | +0.092 |
bang | +0.089 |
Neg logit contributions | |
ilers | -0.132 |
irtual | -0.131 |
VIDIA | -0.130 |
endi | -0.127 |
ually | -0.121 |
Token | amed |
Token ID | 2434 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ilers | +0.674 |
VIDIA | +0.664 |
irtual | +0.662 |
endi | +0.635 |
ually | +0.596 |
Neg logit contributions | |
threat | -0.835 |
credit | -0.809 |
aligned | -0.805 |
strength | -0.798 |
bang | -0.777 |
Token | ly |
Token ID | 306 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ilers | +1.400 |
VIDIA | +1.349 |
irtual | +1.344 |
endi | +1.254 |
ually | +1.221 |
Neg logit contributions | |
threat | -3.760 |
aligned | -3.670 |
credit | -3.639 |
strength | -3.606 |
武 | -3.548 |
Token | on |
Token ID | 319 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
threat | +0.318 |
aligned | +0.304 |
credit | +0.304 |
strength | +0.299 |
bang | +0.289 |
Neg logit contributions | |
ilers | -0.422 |
VIDIA | -0.416 |
irtual | -0.416 |
endi | -0.403 |
ually | -0.385 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ilers | +0.068 |
VIDIA | +0.068 |
irtual | +0.068 |
endi | +0.064 |
LET | +0.060 |
Neg logit contributions | |
threat | -0.081 |
credit | -0.078 |
aligned | -0.078 |
strength | -0.078 |
bang | -0.075 |
Token | naked |
Token ID | 12105 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
ilers | +0.180 |
VIDIA | +0.178 |
irtual | +0.177 |
endi | +0.170 |
LET | +0.159 |
Neg logit contributions | |
threat | -0.214 |
credit | -0.207 |
aligned | -0.206 |
strength | -0.205 |
bang | -0.199 |
Token | body |
Token ID | 1767 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
ilers | +0.130 |
VIDIA | +0.128 |
irtual | +0.128 |
endi | +0.122 |
LET | +0.114 |
Neg logit contributions | |
threat | -0.150 |
credit | -0.145 |
aligned | -0.144 |
strength | -0.143 |
bang | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
ilers | +0.209 |
irtual | +0.204 |
VIDIA | +0.203 |
endi | +0.197 |
LET | +0.187 |
Neg logit contributions | |
threat | -0.210 |
credit | -0.202 |
aligned | -0.202 |
strength | -0.200 |
bang | -0.195 |
Token |
|
Token ID | 198 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
ilers | +0.080 |
irtual | +0.078 |
VIDIA | +0.078 |
endi | +0.076 |
ually | +0.072 |
Neg logit contributions | |
threat | -0.079 |
aligned | -0.075 |
credit | -0.075 |
strength | -0.074 |
bang | -0.072 |
Token | It |
Token ID | 1026 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ilers | +0.082 |
VIDIA | +0.081 |
irtual | +0.080 |
endi | +0.078 |
LET | +0.074 |
Neg logit contributions | |
threat | -0.074 |
credit | -0.071 |
aligned | -0.071 |
strength | -0.070 |
bang | -0.068 |
Token | is |
Token ID | 318 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
ilers | +0.218 |
VIDIA | +0.216 |
irtual | +0.215 |
endi | +0.207 |
ually | +0.195 |
Neg logit contributions | |
threat | -0.219 |
credit | -0.211 |
aligned | -0.210 |
strength | -0.208 |
bang | -0.202 |
Token | the |
Token ID | 262 |
Feature activation | +7.05e-02 |
Pos logit contributions | |
ilers | +0.486 |
VIDIA | +0.482 |
irtual | +0.480 |
endi | +0.459 |
ually | +0.432 |
Neg logit contributions | |
threat | -0.516 |
credit | -0.498 |
aligned | -0.497 |
strength | -0.491 |
bang | -0.479 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ilers | +0.138 |
VIDIA | +0.136 |
irtual | +0.136 |
endi | +0.131 |
ually | +0.124 |
Neg logit contributions | |
threat | -0.129 |
credit | -0.124 |
aligned | -0.124 |
strength | -0.122 |
bang | -0.119 |
Token | case |
Token ID | 1339 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
ilers | +2.331 |
VIDIA | +2.291 |
irtual | +2.282 |
endi | +2.213 |
ually | +2.117 |
Neg logit contributions | |
threat | -2.756 |
credit | -2.676 |
aligned | -2.674 |
strength | -2.654 |
bang | -2.573 |
Token | that |
Token ID | 326 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
ilers | +0.046 |
VIDIA | +0.045 |
irtual | +0.045 |
endi | +0.043 |
ually | +0.040 |
Neg logit contributions | |
threat | -0.054 |
credit | -0.052 |
aligned | -0.052 |
strength | -0.051 |
bang | -0.050 |
Token | is |
Token ID | 318 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ilers | +0.151 |
VIDIA | +0.150 |
irtual | +0.149 |
endi | +0.144 |
ually | +0.135 |
Neg logit contributions | |
threat | -0.143 |
credit | -0.137 |
aligned | -0.137 |
strength | -0.135 |
bang | -0.131 |
Token | already |
Token ID | 1541 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ilers | +0.308 |
VIDIA | +0.305 |
irtual | +0.304 |
endi | +0.292 |
ually | +0.275 |
Neg logit contributions | |
threat | -0.315 |
credit | -0.303 |
aligned | -0.302 |
strength | -0.299 |
bang | -0.291 |
Token | causing |
Token ID | 6666 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
threat | +0.565 |
credit | +0.542 |
aligned | +0.542 |
strength | +0.533 |
bang | +0.522 |
Neg logit contributions | |
ilers | -0.553 |
VIDIA | -0.549 |
irtual | -0.547 |
endi | -0.522 |
LET | -0.493 |
Token | f |
Token ID | 69 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
threat | +0.146 |
credit | +0.141 |
aligned | +0.140 |
strength | +0.139 |
bang | +0.135 |
Neg logit contributions | |
ilers | -0.162 |
VIDIA | -0.161 |
irtual | -0.160 |
endi | -0.154 |
ually | -0.146 |
Token | ); |
Token ID | 1776 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ilers | +0.333 |
VIDIA | +0.329 |
irtual | +0.328 |
endi | +0.317 |
ually | +0.300 |
Neg logit contributions | |
threat | -0.293 |
credit | -0.281 |
aligned | -0.280 |
strength | -0.277 |
bang | -0.269 |
Token | RAW |
Token ID | 33782 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
threat | +0.319 |
aligned | +0.308 |
credit | +0.308 |
strength | +0.303 |
bang | +0.296 |
Neg logit contributions | |
ilers | -0.316 |
VIDIA | -0.313 |
irtual | -0.311 |
endi | -0.300 |
ually | -0.282 |
Token | _ |
Token ID | 62 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ilers | +0.701 |
VIDIA | +0.691 |
irtual | +0.688 |
endi | +0.658 |
ually | +0.614 |
Neg logit contributions | |
threat | -0.942 |
credit | -0.912 |
aligned | -0.910 |
strength | -0.901 |
bang | -0.880 |
Token | ASS |
Token ID | 10705 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
ilers | +0.214 |
VIDIA | +0.212 |
irtual | +0.211 |
endi | +0.204 |
LET | +0.193 |
Neg logit contributions | |
threat | -0.192 |
credit | -0.185 |
aligned | -0.184 |
strength | -0.182 |
bang | -0.177 |
Token | ERT |
Token ID | 17395 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ilers | +0.888 |
VIDIA | +0.878 |
irtual | +0.876 |
endi | +0.840 |
ually | +0.790 |
Neg logit contributions | |
threat | -0.985 |
credit | -0.951 |
aligned | -0.947 |
strength | -0.938 |
bang | -0.913 |
Token | ( |
Token ID | 7 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ilers | +2.215 |
irtual | +2.190 |
VIDIA | +2.184 |
endi | +2.078 |
LET | +1.966 |
Neg logit contributions | |
threat | -2.907 |
credit | -2.818 |
aligned | -2.795 |
strength | -2.777 |
bang | -2.707 |
Token | it |
Token ID | 270 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ilers | +0.489 |
VIDIA | +0.483 |
irtual | +0.482 |
endi | +0.467 |
ually | +0.444 |
Neg logit contributions | |
threat | -0.355 |
credit | -0.340 |
aligned | -0.339 |
strength | -0.334 |
bang | -0.323 |
Token | -> |
Token ID | 3784 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
ilers | +0.302 |
VIDIA | +0.296 |
irtual | +0.294 |
endi | +0.276 |
ually | +0.248 |
Neg logit contributions | |
threat | -0.707 |
credit | -0.689 |
aligned | -0.688 |
strength | -0.682 |
bang | -0.669 |
Token | vec |
Token ID | 35138 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
ilers | +0.641 |
irtual | +0.631 |
VIDIA | +0.630 |
endi | +0.610 |
ually | +0.582 |
Neg logit contributions | |
threat | -0.467 |
credit | -0.448 |
aligned | -0.443 |
strength | -0.438 |
bang | -0.424 |
Token | () |
Token ID | 3419 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
ilers | +0.618 |
VIDIA | +0.610 |
irtual | +0.609 |
endi | +0.587 |
ually | +0.556 |
Neg logit contributions | |
threat | -0.572 |
credit | -0.551 |
aligned | -0.548 |
strength | -0.541 |
bang | -0.527 |
Token | in |
Token ID | 287 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
threat | +0.308 |
credit | +0.297 |
aligned | +0.296 |
strength | +0.292 |
bang | +0.285 |
Neg logit contributions | |
ilers | -0.303 |
VIDIA | -0.300 |
irtual | -0.299 |
endi | -0.287 |
ually | -0.271 |
Token | human |
Token ID | 1692 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
ilers | +0.119 |
VIDIA | +0.118 |
irtual | +0.117 |
endi | +0.113 |
ually | +0.106 |
Neg logit contributions | |
threat | -0.126 |
credit | -0.122 |
aligned | -0.121 |
strength | -0.120 |
bang | -0.117 |
Token | rights |
Token ID | 2489 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
threat | +0.353 |
credit | +0.340 |
aligned | +0.339 |
strength | +0.337 |
bang | +0.325 |
Neg logit contributions | |
ilers | -0.339 |
VIDIA | -0.336 |
irtual | -0.335 |
endi | -0.321 |
LET | -0.302 |
Token | . |
Token ID | 13 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
ilers | +0.281 |
VIDIA | +0.277 |
irtual | +0.276 |
endi | +0.265 |
ually | +0.248 |
Neg logit contributions | |
threat | -0.366 |
credit | -0.356 |
aligned | -0.353 |
strength | -0.350 |
bang | -0.343 |
Token | The |
Token ID | 383 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
ilers | +0.081 |
irtual | +0.080 |
VIDIA | +0.080 |
endi | +0.077 |
ually | +0.073 |
Neg logit contributions | |
threat | -0.079 |
credit | -0.076 |
aligned | -0.076 |
strength | -0.075 |
bang | -0.073 |
Token | latter |
Token ID | 6846 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
threat | +0.094 |
credit | +0.090 |
aligned | +0.090 |
strength | +0.089 |
bang | +0.086 |
Neg logit contributions | |
ilers | -0.095 |
VIDIA | -0.094 |
irtual | -0.094 |
endi | -0.090 |
ually | -0.085 |
Token | two |
Token ID | 734 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ilers | +2.521 |
VIDIA | +2.470 |
irtual | +2.461 |
endi | +2.403 |
ually | +2.314 |
Neg logit contributions | |
threat | -2.551 |
credit | -2.475 |
aligned | -2.463 |
strength | -2.451 |
bang | -2.382 |
Token | were |
Token ID | 547 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ilers | +0.493 |
VIDIA | +0.489 |
irtual | +0.486 |
endi | +0.466 |
LET | +0.438 |
Neg logit contributions | |
threat | -0.519 |
aligned | -0.500 |
credit | -0.500 |
strength | -0.492 |
bang | -0.479 |
Token | very |
Token ID | 845 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
threat | +0.227 |
credit | +0.219 |
aligned | +0.219 |
strength | +0.216 |
bang | +0.210 |
Neg logit contributions | |
ilers | -0.216 |
VIDIA | -0.214 |
irtual | -0.213 |
endi | -0.204 |
LET | -0.192 |
Token | much |
Token ID | 881 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ilers | +0.151 |
VIDIA | +0.149 |
irtual | +0.149 |
endi | +0.144 |
ually | +0.136 |
Neg logit contributions | |
threat | -0.139 |
credit | -0.133 |
aligned | -0.133 |
strength | -0.131 |
bang | -0.128 |
Token | to |
Token ID | 284 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ilers | +1.048 |
irtual | +1.026 |
VIDIA | +1.025 |
endi | +0.995 |
ually | +0.944 |
Neg logit contributions | |
threat | -1.040 |
credit | -1.010 |
aligned | -0.996 |
strength | -0.994 |
bang | -0.964 |
Token | f |
Token ID | 69 |
Feature activation | +9.69e-02 |
Pos logit contributions | |
threat | +0.217 |
credit | +0.204 |
aligned | +0.203 |
strength | +0.199 |
bang | +0.190 |
Neg logit contributions | |
ilers | -0.483 |
VIDIA | -0.478 |
irtual | -0.477 |
endi | -0.464 |
ually | -0.446 |
Token | ); |
Token ID | 1776 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ilers | +0.165 |
VIDIA | +0.163 |
irtual | +0.162 |
endi | +0.156 |
ually | +0.146 |
Neg logit contributions | |
threat | -0.202 |
credit | -0.195 |
aligned | -0.195 |
strength | -0.192 |
bang | -0.188 |
Token | RAW |
Token ID | 33782 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
threat | +0.243 |
aligned | +0.234 |
credit | +0.234 |
strength | +0.230 |
bang | +0.225 |
Neg logit contributions | |
ilers | -0.239 |
VIDIA | -0.236 |
irtual | -0.235 |
endi | -0.226 |
ually | -0.213 |
Token | _ |
Token ID | 62 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
ilers | +0.581 |
VIDIA | +0.565 |
irtual | +0.565 |
endi | +0.535 |
ually | +0.491 |
Neg logit contributions | |
threat | -1.130 |
credit | -1.098 |
aligned | -1.096 |
strength | -1.087 |
bang | -1.064 |
Token | ASS |
Token ID | 10705 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
ilers | +0.172 |
VIDIA | +0.170 |
irtual | +0.170 |
endi | +0.164 |
LET | +0.156 |
Neg logit contributions | |
threat | -0.131 |
credit | -0.126 |
aligned | -0.125 |
strength | -0.124 |
bang | -0.120 |
Token | ERT |
Token ID | 17395 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ilers | +0.911 |
VIDIA | +0.895 |
irtual | +0.894 |
endi | +0.860 |
LET | +0.812 |
Neg logit contributions | |
threat | -1.027 |
credit | -0.991 |
aligned | -0.988 |
strength | -0.980 |
bang | -0.955 |
Token | ( |
Token ID | 7 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ilers | +2.713 |
VIDIA | +2.699 |
irtual | +2.695 |
endi | +2.580 |
LET | +2.478 |
Neg logit contributions | |
threat | -2.367 |
credit | -2.268 |
aligned | -2.250 |
strength | -2.233 |
bang | -2.170 |
Token | it |
Token ID | 270 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ilers | +0.481 |
VIDIA | +0.475 |
irtual | +0.473 |
endi | +0.455 |
ually | +0.429 |
Neg logit contributions | |
threat | -0.497 |
credit | -0.480 |
aligned | -0.478 |
strength | -0.472 |
bang | -0.460 |
Token | -> |
Token ID | 3784 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
ilers | +0.342 |
VIDIA | +0.340 |
irtual | +0.335 |
endi | +0.313 |
ually | +0.280 |
Neg logit contributions | |
threat | -0.811 |
credit | -0.792 |
aligned | -0.790 |
strength | -0.783 |
bang | -0.769 |
Token | vec |
Token ID | 35138 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ilers | +0.731 |
irtual | +0.720 |
VIDIA | +0.718 |
endi | +0.696 |
ually | +0.662 |
Neg logit contributions | |
threat | -0.569 |
credit | -0.546 |
aligned | -0.541 |
strength | -0.534 |
bang | -0.518 |
Token | () |
Token ID | 3419 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
ilers | +0.653 |
irtual | +0.637 |
VIDIA | +0.635 |
endi | +0.618 |
LET | +0.587 |
Neg logit contributions | |
threat | -0.607 |
credit | -0.584 |
aligned | -0.580 |
strength | -0.574 |
bang | -0.559 |
Token | ce |
Token ID | 344 |
Feature activation | -4.32e-03 |
Pos logit contributions | |
threat | +0.302 |
aligned | +0.289 |
credit | +0.286 |
strength | +0.282 |
bang | +0.275 |
Neg logit contributions | |
ilers | -0.608 |
VIDIA | -0.592 |
irtual | -0.589 |
endi | -0.583 |
LET | -0.560 |
Token | / |
Token ID | 14 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
threat | +0.010 |
credit | +0.009 |
aligned | +0.009 |
strength | +0.009 |
bang | +0.009 |
Neg logit contributions | |
ilers | -0.007 |
VIDIA | -0.007 |
irtual | -0.007 |
endi | -0.006 |
ually | -0.006 |
Token | edd |
Token ID | 6048 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
threat | +0.024 |
credit | +0.023 |
aligned | +0.023 |
strength | +0.022 |
bang | +0.022 |
Neg logit contributions | |
ilers | -0.034 |
VIDIA | -0.033 |
irtual | -0.033 |
endi | -0.032 |
ually | -0.031 |
Token | 75 |
Token ID | 2425 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
ilers | +1.024 |
VIDIA | +1.008 |
irtual | +1.006 |
endi | +0.976 |
ually | +0.932 |
Neg logit contributions | |
threat | -0.722 |
credit | -0.691 |
aligned | -0.690 |
strength | -0.678 |
bang | -0.655 |
Token | / |
Token ID | 14 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
ilers | +0.570 |
VIDIA | +0.559 |
irtual | +0.558 |
endi | +0.536 |
ually | +0.503 |
Neg logit contributions | |
threat | -0.694 |
credit | -0.671 |
aligned | -0.671 |
strength | -0.662 |
bang | -0.645 |
Token | AUT |
Token ID | 39371 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
threat | +0.157 |
credit | +0.151 |
aligned | +0.150 |
strength | +0.148 |
bang | +0.143 |
Neg logit contributions | |
ilers | -0.216 |
VIDIA | -0.214 |
irtual | -0.213 |
endi | -0.206 |
ually | -0.195 |
Token | OC |
Token ID | 4503 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
threat | +1.522 |
credit | +1.399 |
aligned | +1.399 |
strength | +1.358 |
bang | +1.295 |
Neg logit contributions | |
ilers | -4.498 |
VIDIA | -4.466 |
irtual | -4.450 |
endi | -4.340 |
LET | -4.202 |
Token | R |
Token ID | 49 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
threat | +0.325 |
credit | +0.310 |
aligned | +0.309 |
strength | +0.304 |
bang | +0.293 |
Neg logit contributions | |
ilers | -0.506 |
VIDIA | -0.501 |
irtual | -0.500 |
endi | -0.485 |
ually | -0.463 |
Token | OP |
Token ID | 3185 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
threat | +0.046 |
aligned | +0.043 |
credit | +0.043 |
strength | +0.042 |
bang | +0.040 |
Neg logit contributions | |
ilers | -0.119 |
VIDIA | -0.119 |
irtual | -0.118 |
endi | -0.115 |
eln | -0.111 |
Token | / |
Token ID | 14 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
threat | +0.861 |
credit | +0.835 |
aligned | +0.834 |
strength | +0.815 |
bang | +0.797 |
Neg logit contributions | |
ilers | -0.765 |
VIDIA | -0.756 |
irtual | -0.737 |
endi | -0.711 |
ually | -0.676 |
Token | h |
Token ID | 71 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ilers | +0.123 |
VIDIA | +0.122 |
irtual | +0.121 |
endi | +0.118 |
LET | +0.114 |
Neg logit contributions | |
threat | -0.066 |
credit | -0.062 |
aligned | -0.062 |
strength | -0.061 |
bang | -0.058 |
Token | Customer |
Token ID | 22092 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ilers | +0.119 |
VIDIA | +0.118 |
irtual | +0.117 |
endi | +0.113 |
ually | +0.107 |
Neg logit contributions | |
threat | -0.122 |
credit | -0.118 |
aligned | -0.118 |
strength | -0.116 |
bang | -0.113 |
Token | Prem |
Token ID | 6929 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
threat | +0.249 |
credit | +0.240 |
aligned | +0.239 |
strength | +0.236 |
bang | +0.229 |
Neg logit contributions | |
ilers | -0.255 |
VIDIA | -0.252 |
irtual | -0.251 |
endi | -0.242 |
ually | -0.228 |
Token | ise |
Token ID | 786 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ilers | +0.553 |
irtual | +0.546 |
VIDIA | +0.542 |
endi | +0.530 |
ually | +0.508 |
Neg logit contributions | |
threat | -0.272 |
credit | -0.257 |
aligned | -0.255 |
strength | -0.251 |
bang | -0.242 |
Token | Equipment |
Token ID | 22412 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
threat | +0.511 |
aligned | +0.489 |
credit | +0.488 |
strength | +0.483 |
bang | +0.466 |
Neg logit contributions | |
ilers | -0.571 |
VIDIA | -0.569 |
irtual | -0.560 |
endi | -0.545 |
eln | -0.513 |
Token | ( |
Token ID | 357 |
Feature activation | -9.83e-03 |
Pos logit contributions | |
threat | +0.629 |
credit | +0.601 |
aligned | +0.600 |
strength | +0.595 |
bang | +0.575 |
Neg logit contributions | |
VIDIA | -0.589 |
ilers | -0.588 |
irtual | -0.579 |
endi | -0.561 |
eln | -0.525 |
Token | CP |
Token ID | 8697 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
threat | +0.020 |
credit | +0.019 |
aligned | +0.019 |
strength | +0.019 |
bang | +0.019 |
Neg logit contributions | |
ilers | -0.017 |
VIDIA | -0.017 |
irtual | -0.017 |
endi | -0.016 |
ually | -0.015 |
Token | E |
Token ID | 36 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
threat | +2.831 |
aligned | +2.728 |
credit | +2.708 |
strength | +2.682 |
� | +2.580 |
Neg logit contributions | |
VIDIA | -2.788 |
ilers | -2.773 |
irtual | -2.744 |
endi | -2.624 |
eln | -2.464 |
Token | ) |
Token ID | 8 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
threat | +1.173 |
credit | +1.117 |
aligned | +1.114 |
strength | +1.100 |
bang | +1.060 |
Neg logit contributions | |
VIDIA | -1.627 |
ilers | -1.626 |
irtual | -1.615 |
endi | -1.562 |
ually | -1.481 |
Token | mitigation |
Token ID | 33585 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
threat | +0.454 |
aligned | +0.436 |
credit | +0.436 |
strength | +0.431 |
bang | +0.417 |
Neg logit contributions | |
ilers | -0.420 |
VIDIA | -0.419 |
irtual | -0.414 |
endi | -0.400 |
ually | -0.375 |
Token | devices |
Token ID | 4410 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
ilers | +0.144 |
VIDIA | +0.142 |
irtual | +0.141 |
endi | +0.136 |
ually | +0.128 |
Neg logit contributions | |
threat | -0.157 |
credit | -0.151 |
aligned | -0.151 |
strength | -0.150 |
bang | -0.145 |
Token | that |
Token ID | 326 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
threat | +1.021 |
aligned | +0.985 |
credit | +0.982 |
strength | +0.971 |
bang | +0.943 |
Neg logit contributions | |
ilers | -0.912 |
VIDIA | -0.911 |
irtual | -0.898 |
endi | -0.863 |
LET | -0.809 |
Token | local |
Token ID | 1957 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
ilers | +0.014 |
VIDIA | +0.014 |
irtual | +0.014 |
endi | +0.014 |
ually | +0.013 |
Neg logit contributions | |
threat | -0.014 |
credit | -0.014 |
aligned | -0.014 |
strength | -0.013 |
bang | -0.013 |
Token | mayor |
Token ID | 9591 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
threat | +0.726 |
credit | +0.698 |
aligned | +0.693 |
strength | +0.688 |
bang | +0.667 |
Neg logit contributions | |
ilers | -0.793 |
VIDIA | -0.788 |
irtual | -0.783 |
endi | -0.755 |
LET | -0.710 |
Token | describing |
Token ID | 12059 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
threat | +0.294 |
credit | +0.283 |
aligned | +0.282 |
strength | +0.279 |
bang | +0.272 |
Neg logit contributions | |
ilers | -0.290 |
VIDIA | -0.287 |
irtual | -0.286 |
endi | -0.275 |
ually | -0.259 |
Token | a |
Token ID | 257 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
threat | +0.275 |
credit | +0.266 |
aligned | +0.265 |
strength | +0.262 |
bang | +0.256 |
Neg logit contributions | |
ilers | -0.235 |
VIDIA | -0.232 |
irtual | -0.231 |
endi | -0.222 |
ually | -0.208 |
Token | " |
Token ID | 366 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
threat | +0.107 |
credit | +0.103 |
aligned | +0.103 |
strength | +0.101 |
bang | +0.099 |
Neg logit contributions | |
ilers | -0.098 |
VIDIA | -0.097 |
irtual | -0.097 |
endi | -0.093 |
ually | -0.087 |
Token | dis |
Token ID | 6381 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
threat | +0.060 |
aligned | +0.058 |
credit | +0.058 |
strength | +0.057 |
bang | +0.055 |
Neg logit contributions | |
ilers | -0.096 |
irtual | -0.094 |
VIDIA | -0.094 |
endi | -0.092 |
ually | -0.087 |
Token | aster |
Token ID | 1603 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
threat | +1.985 |
credit | +1.883 |
aligned | +1.879 |
strength | +1.850 |
bang | +1.768 |
Neg logit contributions | |
VIDIA | -3.659 |
ilers | -3.623 |
irtual | -3.603 |
endi | -3.487 |
LET | -3.353 |
Token | area |
Token ID | 1989 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
threat | +0.618 |
credit | +0.592 |
aligned | +0.590 |
strength | +0.582 |
bang | +0.566 |
Neg logit contributions | |
ilers | -0.792 |
VIDIA | -0.785 |
irtual | -0.779 |
endi | -0.753 |
LET | -0.715 |
Token | " |
Token ID | 1 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
threat | +0.640 |
credit | +0.614 |
aligned | +0.611 |
strength | +0.603 |
bang | +0.584 |
Neg logit contributions | |
ilers | -0.843 |
VIDIA | -0.833 |
irtual | -0.831 |
endi | -0.804 |
ually | -0.765 |
Token | that |
Token ID | 326 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
ilers | +0.653 |
irtual | +0.643 |
VIDIA | +0.638 |
endi | +0.622 |
ually | +0.590 |
Neg logit contributions | |
threat | -0.615 |
credit | -0.596 |
aligned | -0.592 |
strength | -0.585 |
bang | -0.568 |
Token | had |
Token ID | 550 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ilers | +0.138 |
VIDIA | +0.136 |
irtual | +0.135 |
endi | +0.131 |
ually | +0.124 |
Neg logit contributions | |
threat | -0.141 |
credit | -0.136 |
aligned | -0.136 |
strength | -0.134 |
bang | -0.130 |
Token | wo |
Token ID | 21638 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
threat | +0.085 |
credit | +0.082 |
aligned | +0.082 |
strength | +0.081 |
bang | +0.078 |
Neg logit contributions | |
ilers | -0.091 |
VIDIA | -0.090 |
irtual | -0.089 |
endi | -0.086 |
ually | -0.082 |
Token | ofer |
Token ID | 30288 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
threat | +0.064 |
credit | +0.061 |
aligned | +0.060 |
strength | +0.060 |
bang | +0.058 |
Neg logit contributions | |
ilers | -0.097 |
VIDIA | -0.096 |
irtual | -0.096 |
endi | -0.093 |
ually | -0.088 |
Token | is |
Token ID | 318 |
Feature activation | -6.30e-03 |
Pos logit contributions | |
ilers | +0.031 |
VIDIA | +0.030 |
irtual | +0.030 |
endi | +0.029 |
ually | +0.027 |
Neg logit contributions | |
threat | -0.028 |
credit | -0.027 |
aligned | -0.027 |
strength | -0.027 |
bang | -0.026 |
Token | worth |
Token ID | 2861 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
threat | +0.012 |
credit | +0.012 |
aligned | +0.012 |
strength | +0.011 |
bang | +0.011 |
Neg logit contributions | |
ilers | -0.012 |
VIDIA | -0.012 |
irtual | -0.012 |
endi | -0.011 |
ually | -0.011 |
Token | every |
Token ID | 790 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
threat | +0.447 |
credit | +0.429 |
aligned | +0.427 |
strength | +0.421 |
bang | +0.409 |
Neg logit contributions | |
ilers | -0.613 |
VIDIA | -0.607 |
irtual | -0.604 |
endi | -0.585 |
ually | -0.556 |
Token | penny |
Token ID | 26369 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
threat | +0.982 |
credit | +0.954 |
aligned | +0.949 |
strength | +0.940 |
bang | +0.922 |
Neg logit contributions | |
ilers | -0.661 |
VIDIA | -0.651 |
irtual | -0.647 |
endi | -0.617 |
ually | -0.574 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
threat | +2.819 |
credit | +2.746 |
aligned | +2.680 |
bang | +2.679 |
strength | +2.676 |
Neg logit contributions | |
ilers | -2.427 |
irtual | -2.392 |
VIDIA | -2.375 |
endi | -2.255 |
eln | -2.129 |
Token | It |
Token ID | 632 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
threat | +0.240 |
credit | +0.233 |
aligned | +0.232 |
strength | +0.229 |
bang | +0.224 |
Neg logit contributions | |
ilers | -0.217 |
VIDIA | -0.215 |
irtual | -0.213 |
endi | -0.205 |
ually | -0.192 |
Token | makes |
Token ID | 1838 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
threat | +0.526 |
credit | +0.504 |
aligned | +0.503 |
strength | +0.497 |
bang | +0.487 |
Neg logit contributions | |
ilers | -0.575 |
VIDIA | -0.571 |
irtual | -0.566 |
endi | -0.545 |
LET | -0.514 |
Token | my |
Token ID | 616 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
ilers | +0.127 |
VIDIA | +0.126 |
irtual | +0.126 |
endi | +0.121 |
LET | +0.113 |
Neg logit contributions | |
threat | -0.134 |
credit | -0.129 |
aligned | -0.129 |
strength | -0.127 |
bang | -0.125 |
Token | house |
Token ID | 2156 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
threat | +0.962 |
credit | +0.928 |
aligned | +0.923 |
strength | +0.917 |
bang | +0.899 |
Neg logit contributions | |
ilers | -0.846 |
VIDIA | -0.841 |
irtual | -0.836 |
endi | -0.799 |
LET | -0.748 |
Token | phan |
Token ID | 19080 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
threat | +0.569 |
credit | +0.551 |
aligned | +0.549 |
strength | +0.543 |
bang | +0.531 |
Neg logit contributions | |
ilers | -0.451 |
VIDIA | -0.446 |
irtual | -0.445 |
endi | -0.424 |
ually | -0.397 |
Token | Black |
Token ID | 2619 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
ilers | +0.320 |
VIDIA | +0.316 |
irtual | +0.314 |
endi | +0.303 |
ually | +0.288 |
Neg logit contributions | |
threat | -0.308 |
credit | -0.295 |
aligned | -0.295 |
strength | -0.291 |
bang | -0.283 |
Token | and |
Token ID | 290 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
threat | +0.108 |
credit | +0.104 |
aligned | +0.103 |
strength | +0.102 |
bang | +0.100 |
Neg logit contributions | |
ilers | -0.105 |
VIDIA | -0.104 |
irtual | -0.103 |
endi | -0.099 |
ually | -0.094 |
Token | The |
Token ID | 383 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
ilers | +0.142 |
VIDIA | +0.140 |
irtual | +0.140 |
endi | +0.135 |
ually | +0.127 |
Neg logit contributions | |
threat | -0.126 |
credit | -0.121 |
aligned | -0.121 |
strength | -0.119 |
bang | -0.116 |
Token | Vampire |
Token ID | 21463 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
threat | +0.095 |
aligned | +0.092 |
credit | +0.091 |
strength | +0.091 |
bang | +0.088 |
Neg logit contributions | |
ilers | -0.095 |
VIDIA | -0.093 |
irtual | -0.092 |
endi | -0.090 |
ually | -0.085 |
Token | Di |
Token ID | 6031 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
threat | +0.311 |
credit | +0.297 |
aligned | +0.296 |
strength | +0.292 |
bang | +0.282 |
Neg logit contributions | |
ilers | -0.452 |
VIDIA | -0.447 |
irtual | -0.445 |
endi | -0.432 |
ually | -0.411 |
Token | aries |
Token ID | 3166 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
threat | +2.926 |
credit | +2.859 |
aligned | +2.832 |
strength | +2.772 |
� | +2.748 |
Neg logit contributions | |
VIDIA | -2.264 |
irtual | -2.260 |
ilers | -2.080 |
endi | -1.981 |
ALLY | -1.878 |
Token | exist |
Token ID | 2152 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
threat | +0.208 |
credit | +0.201 |
aligned | +0.200 |
strength | +0.197 |
bang | +0.192 |
Neg logit contributions | |
ilers | -0.182 |
VIDIA | -0.180 |
irtual | -0.180 |
endi | -0.172 |
LET | -0.161 |
Token | , |
Token ID | 11 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
threat | +0.366 |
credit | +0.352 |
aligned | +0.351 |
strength | +0.347 |
bang | +0.337 |
Neg logit contributions | |
ilers | -0.396 |
VIDIA | -0.391 |
irtual | -0.389 |
endi | -0.376 |
ually | -0.357 |
Token | female |
Token ID | 4048 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ilers | +0.037 |
VIDIA | +0.037 |
irtual | +0.037 |
endi | +0.035 |
ually | +0.033 |
Neg logit contributions | |
threat | -0.038 |
credit | -0.036 |
aligned | -0.036 |
strength | -0.036 |
bang | -0.035 |
Token | - |
Token ID | 12 |
Feature activation | -3.72e-03 |
Pos logit contributions | |
ilers | +0.458 |
VIDIA | +0.450 |
irtual | +0.449 |
endi | +0.428 |
ually | +0.398 |
Neg logit contributions | |
threat | -0.657 |
credit | -0.637 |
aligned | -0.635 |
strength | -0.629 |
bang | -0.615 |
Token | 2007 |
Token ID | 4343 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
threat | +0.230 |
credit | +0.222 |
aligned | +0.220 |
strength | +0.217 |
bang | +0.211 |
Neg logit contributions | |
VIDIA | -0.276 |
ilers | -0.276 |
irtual | -0.273 |
endi | -0.263 |
ually | -0.248 |
Token | ). |
Token ID | 6739 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
threat | +0.299 |
credit | +0.288 |
aligned | +0.286 |
strength | +0.283 |
bang | +0.276 |
Neg logit contributions | |
ilers | -0.316 |
VIDIA | -0.312 |
irtual | -0.311 |
endi | -0.300 |
ually | -0.283 |
Token | Person |
Token ID | 7755 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
threat | +0.208 |
credit | +0.201 |
aligned | +0.200 |
strength | +0.197 |
bang | +0.192 |
Neg logit contributions | |
ilers | -0.223 |
VIDIA | -0.221 |
irtual | -0.220 |
endi | -0.212 |
LET | -0.199 |
Token | - |
Token ID | 12 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
threat | +0.571 |
credit | +0.549 |
aligned | +0.548 |
strength | +0.541 |
bang | +0.525 |
Neg logit contributions | |
ilers | -0.640 |
VIDIA | -0.633 |
irtual | -0.631 |
endi | -0.608 |
LET | -0.575 |
Token | group |
Token ID | 8094 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ilers | +0.106 |
VIDIA | +0.104 |
irtual | +0.104 |
endi | +0.101 |
ually | +0.098 |
Neg logit contributions | |
threat | -0.057 |
credit | -0.054 |
aligned | -0.054 |
strength | -0.053 |
bang | -0.051 |
Token | diss |
Token ID | 6249 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ilers | +0.251 |
VIDIA | +0.247 |
irtual | +0.247 |
endi | +0.237 |
ually | +0.223 |
Neg logit contributions | |
threat | -0.272 |
credit | -0.263 |
aligned | -0.262 |
strength | -0.259 |
bang | -0.252 |
Token | imilar |
Token ID | 49941 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
threat | +1.873 |
credit | +1.789 |
aligned | +1.785 |
strength | +1.733 |
bang | +1.662 |
Neg logit contributions | |
ilers | -3.147 |
VIDIA | -3.142 |
irtual | -3.094 |
endi | -3.007 |
LET | -2.935 |
Token | ity |
Token ID | 414 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
threat | +0.033 |
credit | +0.032 |
aligned | +0.032 |
strength | +0.032 |
bang | +0.031 |
Neg logit contributions | |
ilers | -0.033 |
VIDIA | -0.033 |
irtual | -0.033 |
endi | -0.032 |
LET | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
ilers | +0.465 |
VIDIA | +0.459 |
irtual | +0.458 |
endi | +0.441 |
ually | +0.417 |
Neg logit contributions | |
threat | -0.455 |
credit | -0.438 |
aligned | -0.437 |
strength | -0.432 |
bang | -0.420 |
Token | involvement |
Token ID | 9750 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
threat | +0.180 |
credit | +0.173 |
aligned | +0.173 |
strength | +0.171 |
bang | +0.167 |
Neg logit contributions | |
ilers | -0.152 |
VIDIA | -0.151 |
irtual | -0.150 |
endi | -0.144 |
LET | -0.135 |
Token | in |
Token ID | 287 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
threat | +1.593 |
credit | +1.525 |
aligned | +1.520 |
strength | +1.505 |
bang | +1.446 |
Neg logit contributions | |
ilers | -1.684 |
irtual | -1.672 |
VIDIA | -1.669 |
endi | -1.597 |
eln | -1.520 |
Token | as |
Token ID | 355 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
threat | +0.215 |
credit | +0.207 |
aligned | +0.207 |
strength | +0.204 |
bang | +0.198 |
Neg logit contributions | |
ilers | -0.238 |
VIDIA | -0.236 |
irtual | -0.234 |
endi | -0.226 |
ually | -0.214 |
Token | scrap |
Token ID | 15881 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
threat | +0.256 |
credit | +0.246 |
aligned | +0.245 |
strength | +0.242 |
bang | +0.235 |
Neg logit contributions | |
ilers | -0.288 |
VIDIA | -0.284 |
irtual | -0.283 |
endi | -0.274 |
ually | -0.259 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
ilers | +0.540 |
irtual | +0.528 |
VIDIA | +0.527 |
endi | +0.511 |
ually | +0.487 |
Neg logit contributions | |
threat | -0.578 |
credit | -0.558 |
aligned | -0.558 |
strength | -0.549 |
bang | -0.531 |
Token |
|
Token ID | 198 |
Feature activation | -5.00e-03 |
Pos logit contributions | |
ilers | +0.056 |
VIDIA | +0.056 |
irtual | +0.055 |
endi | +0.053 |
ually | +0.050 |
Neg logit contributions | |
threat | -0.056 |
credit | -0.054 |
aligned | -0.054 |
strength | -0.053 |
bang | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
threat | +0.009 |
credit | +0.009 |
aligned | +0.009 |
strength | +0.009 |
bang | +0.009 |
Neg logit contributions | |
ilers | -0.010 |
VIDIA | -0.009 |
irtual | -0.009 |
endi | -0.009 |
ually | -0.009 |
Token | Article |
Token ID | 14906 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ilers | +0.011 |
VIDIA | +0.011 |
irtual | +0.011 |
endi | +0.010 |
ually | +0.010 |
Neg logit contributions | |
threat | -0.009 |
credit | -0.009 |
aligned | -0.009 |
strength | -0.008 |
bang | -0.008 |
Token | Continued |
Token ID | 22168 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
threat | +2.619 |
credit | +2.546 |
aligned | +2.534 |
strength | +2.478 |
bang | +2.432 |
Neg logit contributions | |
ilers | -2.383 |
irtual | -2.380 |
VIDIA | -2.361 |
endi | -2.232 |
LET | -2.098 |
Token | Below |
Token ID | 10383 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
threat | +0.089 |
credit | +0.084 |
aligned | +0.084 |
strength | +0.083 |
bang | +0.081 |
Neg logit contributions | |
ilers | -0.138 |
irtual | -0.134 |
VIDIA | -0.133 |
endi | -0.130 |
ually | -0.126 |
Token |
|
Token ID | 198 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ilers | +0.523 |
irtual | +0.505 |
VIDIA | +0.501 |
endi | +0.494 |
LET | +0.469 |
Neg logit contributions | |
threat | -0.529 |
aligned | -0.507 |
credit | -0.506 |
strength | -0.502 |
bang | -0.488 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ilers | +0.293 |
irtual | +0.285 |
VIDIA | +0.285 |
endi | +0.278 |
ually | +0.264 |
Neg logit contributions | |
threat | -0.287 |
aligned | -0.275 |
credit | -0.275 |
strength | -0.272 |
bang | -0.264 |
Token | The |
Token ID | 464 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ilers | +0.286 |
VIDIA | +0.283 |
irtual | +0.281 |
endi | +0.272 |
ually | +0.258 |
Neg logit contributions | |
threat | -0.249 |
credit | -0.239 |
aligned | -0.239 |
strength | -0.236 |
bang | -0.229 |
Token | mainstream |
Token ID | 8661 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
threat | +0.378 |
credit | +0.364 |
aligned | +0.363 |
strength | +0.358 |
bang | +0.348 |
Neg logit contributions | |
ilers | -0.418 |
VIDIA | -0.413 |
irtual | -0.411 |
endi | -0.397 |
ually | -0.375 |
Token | UK |
Token ID | 3482 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
threat | +0.332 |
credit | +0.319 |
aligned | +0.318 |
strength | +0.315 |
bang | +0.305 |
Neg logit contributions | |
ilers | -0.373 |
VIDIA | -0.369 |
irtual | -0.367 |
endi | -0.355 |
ually | -0.336 |
Token | media |
Token ID | 2056 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
threat | +0.126 |
credit | +0.121 |
aligned | +0.121 |
strength | +0.119 |
bang | +0.116 |
Neg logit contributions | |
ilers | -0.139 |
VIDIA | -0.137 |
irtual | -0.136 |
endi | -0.132 |
ually | -0.125 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
threat | +0.228 |
credit | +0.219 |
aligned | +0.218 |
strength | +0.215 |
bang | +0.210 |
Neg logit contributions | |
ilers | -0.239 |
VIDIA | -0.237 |
irtual | -0.236 |
endi | -0.227 |
ually | -0.214 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
threat | +0.278 |
credit | +0.267 |
aligned | +0.267 |
strength | +0.263 |
bang | +0.256 |
Neg logit contributions | |
ilers | -0.291 |
VIDIA | -0.288 |
irtual | -0.287 |
endi | -0.276 |
ually | -0.261 |
Token | diss |
Token ID | 6249 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
threat | +0.346 |
credit | +0.332 |
aligned | +0.331 |
strength | +0.327 |
bang | +0.317 |
Neg logit contributions | |
ilers | -0.423 |
VIDIA | -0.418 |
irtual | -0.417 |
endi | -0.403 |
ually | -0.383 |
Token | ident |
Token ID | 738 |
Feature activation | -7.00e-04 |
Pos logit contributions | |
threat | +2.465 |
aligned | +2.385 |
credit | +2.363 |
strength | +2.332 |
bang | +2.271 |
Neg logit contributions | |
ilers | -2.483 |
VIDIA | -2.476 |
irtual | -2.451 |
endi | -2.356 |
LET | -2.243 |
Token | Real |
Token ID | 6416 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
threat | +0.001 |
credit | +0.001 |
aligned | +0.001 |
strength | +0.001 |
bang | +0.001 |
Neg logit contributions | |
ilers | -0.001 |
VIDIA | -0.001 |
irtual | -0.001 |
endi | -0.001 |
ually | -0.001 |
Token | News |
Token ID | 3000 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ilers | +0.533 |
VIDIA | +0.527 |
irtual | +0.525 |
endi | +0.511 |
ually | +0.485 |
Neg logit contributions | |
threat | -0.407 |
credit | -0.391 |
aligned | -0.389 |
strength | -0.383 |
bang | -0.370 |
Token | Network |
Token ID | 7311 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
ilers | +0.025 |
VIDIA | +0.024 |
irtual | +0.024 |
endi | +0.023 |
ually | +0.022 |
Neg logit contributions | |
threat | -0.026 |
credit | -0.025 |
aligned | -0.025 |
strength | -0.025 |
bang | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ilers | +0.091 |
VIDIA | +0.090 |
irtual | +0.090 |
endi | +0.086 |
ually | +0.081 |
Neg logit contributions | |
threat | -0.105 |
credit | -0.102 |
aligned | -0.101 |
strength | -0.100 |
bang | -0.097 |
Token | the |
Token ID | 262 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
threat | +0.328 |
credit | +0.316 |
aligned | +0.314 |
strength | +0.311 |
bang | +0.302 |
Neg logit contributions | |
ilers | -0.358 |
VIDIA | -0.354 |
irtual | -0.353 |
endi | -0.341 |
ually | -0.322 |
Token | club |
Token ID | 3430 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ilers | +0.106 |
VIDIA | +0.105 |
irtual | +0.105 |
endi | +0.101 |
ually | +0.095 |
Neg logit contributions | |
threat | -0.111 |
credit | -0.107 |
aligned | -0.107 |
strength | -0.106 |
bang | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
ilers | +0.239 |
VIDIA | +0.236 |
irtual | +0.236 |
endi | +0.225 |
ually | +0.211 |
Neg logit contributions | |
threat | -0.287 |
credit | -0.278 |
aligned | -0.276 |
strength | -0.274 |
bang | -0.267 |
Token |
|
Token ID | 198 |
Feature activation | -6.38e-03 |
Pos logit contributions | |
threat | +0.090 |
credit | +0.086 |
aligned | +0.086 |
strength | +0.085 |
bang | +0.083 |
Neg logit contributions | |
ilers | -0.099 |
VIDIA | -0.098 |
irtual | -0.097 |
endi | -0.094 |
ually | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
threat | +0.012 |
credit | +0.011 |
aligned | +0.011 |
strength | +0.011 |
bang | +0.011 |
Neg logit contributions | |
ilers | -0.012 |
irtual | -0.012 |
VIDIA | -0.012 |
endi | -0.012 |
ually | -0.011 |
Token | Story |
Token ID | 11605 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ilers | +0.052 |
VIDIA | +0.052 |
irtual | +0.051 |
endi | +0.050 |
ually | +0.048 |
Neg logit contributions | |
threat | -0.035 |
credit | -0.033 |
aligned | -0.033 |
strength | -0.032 |
bang | -0.031 |
Token | continues |
Token ID | 4477 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
threat | +2.246 |
credit | +2.172 |
aligned | +2.160 |
strength | +2.114 |
bang | +2.076 |
Neg logit contributions | |
VIDIA | -2.723 |
irtual | -2.693 |
ilers | -2.666 |
endi | -2.549 |
LET | -2.421 |
Token | below |
Token ID | 2174 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
threat | +0.523 |
credit | +0.502 |
aligned | +0.501 |
strength | +0.492 |
bang | +0.475 |
Neg logit contributions | |
ilers | -0.740 |
VIDIA | -0.737 |
irtual | -0.734 |
endi | -0.708 |
LET | -0.671 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
ilers | +0.792 |
VIDIA | +0.769 |
irtual | +0.765 |
endi | +0.738 |
ually | +0.690 |
Neg logit contributions | |
threat | -1.187 |
credit | -1.149 |
aligned | -1.147 |
strength | -1.138 |
bang | -1.111 |
Token |
|
Token ID | 198 |
Feature activation | +6.01e-03 |
Pos logit contributions | |
threat | +1.461 |
credit | +1.418 |
aligned | +1.407 |
strength | +1.386 |
bang | +1.347 |
Neg logit contributions | |
VIDIA | -1.748 |
irtual | -1.717 |
ilers | -1.711 |
endi | -1.630 |
eln | -1.537 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
ilers | +0.012 |
irtual | +0.011 |
VIDIA | +0.011 |
endi | +0.011 |
ually | +0.010 |
Neg logit contributions | |
threat | -0.011 |
credit | -0.011 |
aligned | -0.011 |
strength | -0.011 |
bang | -0.010 |
Token | big |
Token ID | 1263 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
ilers | +0.124 |
VIDIA | +0.123 |
irtual | +0.122 |
endi | +0.117 |
LET | +0.110 |
Neg logit contributions | |
threat | -0.121 |
credit | -0.117 |
aligned | -0.116 |
strength | -0.115 |
bang | -0.112 |
Token | stage |
Token ID | 3800 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ilers | +0.104 |
VIDIA | +0.103 |
irtual | +0.102 |
endi | +0.098 |
ually | +0.093 |
Neg logit contributions | |
threat | -0.092 |
credit | -0.089 |
aligned | -0.088 |
strength | -0.087 |
bang | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
ilers | +0.779 |
VIDIA | +0.767 |
irtual | +0.764 |
endi | +0.735 |
ually | +0.694 |
Neg logit contributions | |
threat | -0.935 |
credit | -0.907 |
aligned | -0.902 |
strength | -0.892 |
bang | -0.869 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
threat | +0.045 |
credit | +0.043 |
aligned | +0.043 |
strength | +0.043 |
bang | +0.041 |
Neg logit contributions | |
ilers | -0.049 |
VIDIA | -0.048 |
irtual | -0.048 |
endi | -0.046 |
ually | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
threat | +0.194 |
credit | +0.187 |
aligned | +0.186 |
strength | +0.184 |
bang | +0.179 |
Neg logit contributions | |
ilers | -0.208 |
VIDIA | -0.205 |
irtual | -0.204 |
endi | -0.197 |
ually | -0.186 |
Token | Story |
Token ID | 11605 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
threat | +0.162 |
credit | +0.156 |
aligned | +0.155 |
strength | +0.153 |
bang | +0.148 |
Neg logit contributions | |
ilers | -0.216 |
VIDIA | -0.214 |
irtual | -0.214 |
endi | -0.206 |
ually | -0.196 |
Token | continues |
Token ID | 4477 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
threat | +2.311 |
credit | +2.235 |
aligned | +2.218 |
strength | +2.181 |
bang | +2.132 |
Neg logit contributions | |
ilers | -2.614 |
VIDIA | -2.597 |
irtual | -2.593 |
endi | -2.477 |
eln | -2.347 |
Token | below |
Token ID | 2174 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
threat | +0.743 |
credit | +0.712 |
aligned | +0.709 |
strength | +0.699 |
bang | +0.677 |
Neg logit contributions | |
ilers | -1.010 |
VIDIA | -0.998 |
irtual | -0.995 |
endi | -0.964 |
ually | -0.917 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
ilers | +0.853 |
VIDIA | +0.831 |
irtual | +0.831 |
endi | +0.794 |
ually | +0.741 |
Neg logit contributions | |
threat | -1.257 |
credit | -1.219 |
aligned | -1.218 |
strength | -1.205 |
bang | -1.178 |
Token |
|
Token ID | 198 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
threat | +1.502 |
credit | +1.456 |
aligned | +1.442 |
strength | +1.423 |
bang | +1.380 |
Neg logit contributions | |
VIDIA | -1.784 |
irtual | -1.754 |
ilers | -1.752 |
endi | -1.670 |
eln | -1.573 |
Token |
|
Token ID | 198 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
ilers | +0.016 |
irtual | +0.015 |
VIDIA | +0.015 |
endi | +0.015 |
ually | +0.014 |
Neg logit contributions | |
threat | -0.015 |
credit | -0.015 |
aligned | -0.015 |
strength | -0.014 |
bang | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
threat | +0.671 |
credit | +0.648 |
aligned | +0.646 |
strength | +0.637 |
bang | +0.621 |
Neg logit contributions | |
ilers | -0.621 |
VIDIA | -0.618 |
irtual | -0.613 |
endi | -0.591 |
ually | -0.551 |
Token |
|
Token ID | 198 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
ilers | +0.147 |
irtual | +0.143 |
VIDIA | +0.143 |
endi | +0.139 |
ually | +0.132 |
Neg logit contributions | |
threat | -0.142 |
credit | -0.137 |
aligned | -0.137 |
strength | -0.135 |
bang | -0.131 |
Token | More |
Token ID | 5167 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
ilers | +0.094 |
VIDIA | +0.093 |
irtual | +0.092 |
endi | +0.089 |
ually | +0.085 |
Neg logit contributions | |
threat | -0.078 |
credit | -0.075 |
aligned | -0.075 |
strength | -0.074 |
bang | -0.072 |
Token | : |
Token ID | 25 |
Feature activation | +3.42e-03 |
Pos logit contributions | |
threat | +0.056 |
aligned | +0.053 |
credit | +0.053 |
strength | +0.052 |
bang | +0.050 |
Neg logit contributions | |
ilers | -0.086 |
VIDIA | -0.085 |
irtual | -0.085 |
endi | -0.082 |
ually | -0.079 |
Token | Law |
Token ID | 3854 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ilers | +0.007 |
VIDIA | +0.007 |
irtual | +0.007 |
endi | +0.007 |
ually | +0.006 |
Neg logit contributions | |
threat | -0.006 |
credit | -0.006 |
aligned | -0.006 |
strength | -0.006 |
bang | -0.005 |
Token | suit |
Token ID | 6063 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ilers | +0.555 |
VIDIA | +0.548 |
irtual | +0.547 |
endi | +0.529 |
ually | +0.505 |
Neg logit contributions | |
threat | -0.454 |
credit | -0.435 |
aligned | -0.435 |
strength | -0.431 |
bang | -0.416 |
Token | : |
Token ID | 25 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
threat | +2.300 |
credit | +2.200 |
aligned | +2.191 |
strength | +2.130 |
rattled | +2.088 |
Neg logit contributions | |
ilers | -2.616 |
VIDIA | -2.607 |
irtual | -2.585 |
endi | -2.476 |
LET | -2.329 |
Token | UC |
Token ID | 14417 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
ilers | +0.099 |
VIDIA | +0.098 |
irtual | +0.098 |
endi | +0.095 |
ually | +0.089 |
Neg logit contributions | |
threat | -0.086 |
credit | -0.083 |
aligned | -0.082 |
strength | -0.081 |
bang | -0.079 |
Token | has |
Token ID | 468 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ilers | +0.177 |
VIDIA | +0.175 |
irtual | +0.174 |
endi | +0.168 |
ually | +0.158 |
Neg logit contributions | |
threat | -0.182 |
credit | -0.176 |
aligned | -0.175 |
strength | -0.173 |
bang | -0.168 |
Token | ' |
Token ID | 705 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
threat | +0.278 |
credit | +0.267 |
aligned | +0.265 |
strength | +0.262 |
bang | +0.255 |
Neg logit contributions | |
ilers | -0.285 |
irtual | -0.283 |
VIDIA | -0.282 |
endi | -0.270 |
LET | -0.254 |
Token | anti |
Token ID | 17096 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
threat | +0.441 |
credit | +0.420 |
aligned | +0.418 |
strength | +0.412 |
bang | +0.398 |
Neg logit contributions | |
ilers | -0.672 |
VIDIA | -0.667 |
irtual | -0.663 |
endi | -0.642 |
ually | -0.612 |
Token | She |
Token ID | 1375 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
ilers | +0.321 |
VIDIA | +0.319 |
irtual | +0.318 |
endi | +0.305 |
ually | +0.289 |
Neg logit contributions | |
threat | -0.274 |
credit | -0.264 |
aligned | -0.262 |
strength | -0.259 |
bang | -0.253 |
Token | pell |
Token ID | 23506 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ilers | +0.212 |
VIDIA | +0.208 |
irtual | +0.208 |
endi | +0.203 |
ually | +0.195 |
Neg logit contributions | |
threat | -0.099 |
credit | -0.093 |
aligned | -0.092 |
strength | -0.091 |
bang | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
threat | +0.545 |
credit | +0.528 |
aligned | +0.525 |
strength | +0.520 |
bang | +0.510 |
Neg logit contributions | |
ilers | -0.462 |
VIDIA | -0.459 |
irtual | -0.456 |
endi | -0.436 |
ually | -0.409 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
threat | +0.021 |
credit | +0.021 |
aligned | +0.021 |
strength | +0.020 |
bang | +0.020 |
Neg logit contributions | |
ilers | -0.022 |
VIDIA | -0.021 |
irtual | -0.021 |
endi | -0.021 |
LET | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
threat | +0.020 |
aligned | +0.019 |
credit | +0.019 |
strength | +0.019 |
bang | +0.018 |
Neg logit contributions | |
ilers | -0.020 |
irtual | -0.020 |
VIDIA | -0.020 |
endi | -0.019 |
ually | -0.018 |
Token | Story |
Token ID | 11605 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ilers | +0.023 |
VIDIA | +0.023 |
irtual | +0.023 |
endi | +0.022 |
LET | +0.021 |
Neg logit contributions | |
threat | -0.017 |
aligned | -0.016 |
credit | -0.016 |
strength | -0.016 |
bang | -0.015 |
Token | continues |
Token ID | 4477 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
threat | +2.310 |
credit | +2.225 |
aligned | +2.215 |
strength | +2.174 |
bang | +2.129 |
Neg logit contributions | |
VIDIA | -2.591 |
ilers | -2.587 |
irtual | -2.581 |
endi | -2.457 |
LET | -2.324 |
Token | below |
Token ID | 2174 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
threat | +0.659 |
credit | +0.631 |
aligned | +0.629 |
strength | +0.619 |
bang | +0.598 |
Neg logit contributions | |
ilers | -0.923 |
VIDIA | -0.918 |
irtual | -0.913 |
endi | -0.883 |
ually | -0.838 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
ilers | +0.921 |
VIDIA | +0.891 |
irtual | +0.884 |
endi | +0.856 |
ually | +0.802 |
Neg logit contributions | |
threat | -1.408 |
credit | -1.364 |
aligned | -1.363 |
strength | -1.353 |
bang | -1.318 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
threat | +1.416 |
credit | +1.374 |
aligned | +1.362 |
strength | +1.341 |
bang | +1.303 |
Neg logit contributions | |
VIDIA | -1.696 |
irtual | -1.667 |
ilers | -1.661 |
endi | -1.582 |
eln | -1.492 |
Token |
|
Token ID | 198 |
Feature activation | -7.99e-03 |
Pos logit contributions | |
ilers | +0.042 |
irtual | +0.041 |
VIDIA | +0.041 |
endi | +0.040 |
ually | +0.038 |
Neg logit contributions | |
threat | -0.041 |
aligned | -0.040 |
credit | -0.040 |
strength | -0.039 |
bang | -0.038 |
Token | stating |
Token ID | 12316 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
threat | +0.070 |
credit | +0.067 |
aligned | +0.067 |
strength | +0.066 |
bang | +0.064 |
Neg logit contributions | |
ilers | -0.065 |
VIDIA | -0.064 |
irtual | -0.064 |
endi | -0.061 |
LET | -0.057 |
Token | : |
Token ID | 25 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
threat | +0.352 |
credit | +0.339 |
aligned | +0.338 |
strength | +0.334 |
bang | +0.325 |
Neg logit contributions | |
ilers | -0.335 |
VIDIA | -0.331 |
irtual | -0.330 |
endi | -0.316 |
ually | -0.297 |
Token | � |
Token ID | 564 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
threat | +0.030 |
credit | +0.029 |
aligned | +0.029 |
strength | +0.029 |
bang | +0.028 |
Neg logit contributions | |
ilers | -0.025 |
VIDIA | -0.025 |
irtual | -0.025 |
endi | -0.024 |
ually | -0.023 |
Token | � |
Token ID | 250 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
ilers | +0.149 |
VIDIA | +0.147 |
irtual | +0.146 |
endi | +0.141 |
ually | +0.134 |
Neg logit contributions | |
threat | -0.117 |
credit | -0.112 |
aligned | -0.111 |
strength | -0.110 |
bang | -0.107 |
Token | The |
Token ID | 464 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
threat | +0.080 |
credit | +0.077 |
aligned | +0.076 |
strength | +0.076 |
bang | +0.073 |
Neg logit contributions | |
ilers | -0.085 |
VIDIA | -0.084 |
irtual | -0.084 |
endi | -0.080 |
ually | -0.076 |
Token | separatists |
Token ID | 34214 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
threat | +0.244 |
credit | +0.235 |
aligned | +0.234 |
strength | +0.231 |
bang | +0.225 |
Neg logit contributions | |
ilers | -0.276 |
VIDIA | -0.273 |
irtual | -0.272 |
endi | -0.262 |
ually | -0.248 |
Token | are |
Token ID | 389 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
threat | +2.531 |
aligned | +2.423 |
credit | +2.376 |
strength | +2.349 |
bang | +2.314 |
Neg logit contributions | |
VIDIA | -2.363 |
irtual | -2.363 |
ilers | -2.358 |
endi | -2.249 |
LET | -2.119 |
Token | saying |
Token ID | 2282 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
threat | +0.174 |
aligned | +0.167 |
credit | +0.167 |
strength | +0.165 |
bang | +0.161 |
Neg logit contributions | |
ilers | -0.168 |
VIDIA | -0.167 |
irtual | -0.167 |
endi | -0.159 |
LET | -0.150 |
Token | there |
Token ID | 612 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
threat | +1.126 |
aligned | +1.083 |
credit | +1.078 |
strength | +1.068 |
bang | +1.041 |
Neg logit contributions | |
ilers | -1.053 |
VIDIA | -1.043 |
irtual | -1.042 |
endi | -0.992 |
LET | -0.930 |
Token | are |
Token ID | 389 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
threat | +0.581 |
credit | +0.559 |
aligned | +0.559 |
strength | +0.551 |
bang | +0.537 |
Neg logit contributions | |
ilers | -0.549 |
VIDIA | -0.543 |
irtual | -0.541 |
endi | -0.519 |
ually | -0.489 |
Token | 1 |
Token ID | 352 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
threat | +0.018 |
credit | +0.018 |
aligned | +0.018 |
strength | +0.017 |
bang | +0.017 |
Neg logit contributions | |
ilers | -0.021 |
VIDIA | -0.021 |
irtual | -0.021 |
endi | -0.020 |
LET | -0.019 |
Token | disclosure |
Token ID | 13019 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
ilers | +0.241 |
VIDIA | +0.240 |
irtual | +0.238 |
endi | +0.227 |
ually | +0.213 |
Neg logit contributions | |
threat | -0.295 |
credit | -0.286 |
aligned | -0.285 |
strength | -0.281 |
bang | -0.274 |
Token | statement |
Token ID | 2643 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
ilers | +0.925 |
VIDIA | +0.899 |
irtual | +0.888 |
endi | +0.850 |
ually | +0.781 |
Neg logit contributions | |
threat | -1.978 |
credit | -1.926 |
aligned | -1.923 |
strength | -1.906 |
bang | -1.873 |
Token | . |
Token ID | 13 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
threat | +0.033 |
credit | +0.032 |
aligned | +0.032 |
strength | +0.031 |
bang | +0.030 |
Neg logit contributions | |
ilers | -0.026 |
VIDIA | -0.025 |
irtual | -0.025 |
endi | -0.024 |
ually | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
ilers | +0.158 |
VIDIA | +0.155 |
irtual | +0.155 |
endi | +0.149 |
ually | +0.141 |
Neg logit contributions | |
threat | -0.149 |
credit | -0.143 |
aligned | -0.143 |
strength | -0.141 |
bang | -0.137 |
Token |
|
Token ID | 198 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
ilers | +0.168 |
irtual | +0.163 |
VIDIA | +0.162 |
endi | +0.158 |
ually | +0.151 |
Neg logit contributions | |
threat | -0.166 |
aligned | -0.159 |
credit | -0.159 |
strength | -0.157 |
bang | -0.153 |
Token | Story |
Token ID | 11605 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ilers | +0.168 |
VIDIA | +0.166 |
irtual | +0.164 |
endi | +0.160 |
LET | +0.153 |
Neg logit contributions | |
threat | -0.121 |
aligned | -0.115 |
credit | -0.115 |
strength | -0.114 |
bang | -0.110 |
Token | continues |
Token ID | 4477 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
threat | +2.302 |
credit | +2.220 |
aligned | +2.208 |
strength | +2.167 |
bang | +2.125 |
Neg logit contributions | |
VIDIA | -2.591 |
ilers | -2.582 |
irtual | -2.574 |
endi | -2.457 |
LET | -2.322 |
Token | below |
Token ID | 2174 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
threat | +0.629 |
credit | +0.602 |
aligned | +0.600 |
strength | +0.590 |
bang | +0.571 |
Neg logit contributions | |
ilers | -0.877 |
VIDIA | -0.872 |
irtual | -0.868 |
endi | -0.839 |
ually | -0.796 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
ilers | +0.947 |
VIDIA | +0.916 |
irtual | +0.910 |
endi | +0.882 |
ually | +0.827 |
Neg logit contributions | |
threat | -1.454 |
credit | -1.407 |
aligned | -1.406 |
strength | -1.397 |
bang | -1.361 |
Token |
|
Token ID | 198 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
threat | +1.516 |
credit | +1.472 |
aligned | +1.459 |
strength | +1.436 |
bang | +1.397 |
Neg logit contributions | |
VIDIA | -1.833 |
irtual | -1.799 |
ilers | -1.790 |
endi | -1.706 |
eln | -1.609 |
Token |
|
Token ID | 198 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
ilers | +0.117 |
irtual | +0.114 |
VIDIA | +0.113 |
endi | +0.111 |
ually | +0.105 |
Neg logit contributions | |
threat | -0.115 |
aligned | -0.110 |
credit | -0.110 |
strength | -0.109 |
bang | -0.106 |
Token | ' |
Token ID | 705 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
threat | +0.025 |
credit | +0.025 |
aligned | +0.025 |
strength | +0.024 |
bang | +0.024 |
Neg logit contributions | |
ilers | -0.024 |
VIDIA | -0.023 |
irtual | -0.023 |
endi | -0.023 |
ually | -0.021 |
Token | keeper |
Token ID | 13884 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
threat | +0.562 |
credit | +0.541 |
aligned | +0.539 |
strength | +0.533 |
bang | +0.518 |
Neg logit contributions | |
ilers | -0.618 |
VIDIA | -0.613 |
irtual | -0.609 |
endi | -0.586 |
ually | -0.556 |
Token | . |
Token ID | 13 |
Feature activation | -9.98e-02 |
Pos logit contributions | |
threat | +0.361 |
credit | +0.348 |
aligned | +0.347 |
strength | +0.342 |
bang | +0.333 |
Neg logit contributions | |
ilers | -0.366 |
VIDIA | -0.359 |
irtual | -0.359 |
endi | -0.347 |
ually | -0.328 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
threat | +0.179 |
credit | +0.173 |
aligned | +0.172 |
strength | +0.170 |
bang | +0.165 |
Neg logit contributions | |
ilers | -0.199 |
VIDIA | -0.197 |
irtual | -0.196 |
endi | -0.189 |
ually | -0.179 |
Token |
|
Token ID | 198 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
threat | +0.194 |
credit | +0.187 |
aligned | +0.186 |
strength | +0.184 |
bang | +0.179 |
Neg logit contributions | |
ilers | -0.204 |
VIDIA | -0.200 |
irtual | -0.200 |
endi | -0.194 |
ually | -0.183 |
Token | Story |
Token ID | 11605 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
threat | +0.120 |
credit | +0.115 |
aligned | +0.114 |
strength | +0.113 |
bang | +0.109 |
Neg logit contributions | |
ilers | -0.174 |
VIDIA | -0.172 |
irtual | -0.171 |
endi | -0.166 |
ually | -0.158 |
Token | continues |
Token ID | 4477 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
threat | +2.227 |
credit | +2.152 |
aligned | +2.142 |
strength | +2.097 |
bang | +2.060 |
Neg logit contributions | |
VIDIA | -2.662 |
irtual | -2.642 |
ilers | -2.618 |
endi | -2.493 |
LET | -2.369 |
Token | below |
Token ID | 2174 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
threat | +0.672 |
credit | +0.644 |
aligned | +0.642 |
strength | +0.631 |
bang | +0.610 |
Neg logit contributions | |
ilers | -0.948 |
VIDIA | -0.944 |
irtual | -0.939 |
endi | -0.907 |
LET | -0.860 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
ilers | +0.718 |
VIDIA | +0.700 |
irtual | +0.696 |
endi | +0.670 |
ually | +0.626 |
Neg logit contributions | |
threat | -1.067 |
credit | -1.033 |
aligned | -1.032 |
strength | -1.023 |
bang | -0.998 |
Token |
|
Token ID | 198 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
threat | +1.570 |
credit | +1.525 |
aligned | +1.511 |
strength | +1.489 |
bang | +1.445 |
Neg logit contributions | |
VIDIA | -1.893 |
irtual | -1.857 |
ilers | -1.849 |
endi | -1.763 |
eln | -1.662 |
Token |
|
Token ID | 198 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
threat | +0.083 |
credit | +0.080 |
aligned | +0.079 |
strength | +0.079 |
bang | +0.076 |
Neg logit contributions | |
ilers | -0.086 |
VIDIA | -0.084 |
irtual | -0.084 |
endi | -0.082 |
ually | -0.077 |
Token | be |
Token ID | 307 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
VIDIA | +0.159 |
irtual | +0.159 |
ilers | +0.158 |
endi | +0.150 |
LET | +0.141 |
Neg logit contributions | |
threat | -0.182 |
credit | -0.177 |
aligned | -0.174 |
strength | -0.172 |
bang | -0.169 |
Token | let |
Token ID | 1309 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
threat | +0.230 |
credit | +0.221 |
aligned | +0.220 |
strength | +0.217 |
bang | +0.211 |
Neg logit contributions | |
ilers | -0.255 |
VIDIA | -0.253 |
irtual | -0.251 |
endi | -0.242 |
LET | -0.228 |
Token | off |
Token ID | 572 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ilers | +1.299 |
VIDIA | +1.273 |
irtual | +1.272 |
endi | +1.226 |
ually | +1.169 |
Neg logit contributions | |
threat | -1.318 |
credit | -1.268 |
aligned | -1.267 |
strength | -1.252 |
bang | -1.212 |
Token | . |
Token ID | 13 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
ilers | +0.254 |
VIDIA | +0.251 |
irtual | +0.250 |
endi | +0.241 |
LET | +0.226 |
Neg logit contributions | |
threat | -0.261 |
credit | -0.253 |
aligned | -0.250 |
strength | -0.248 |
bang | -0.241 |
Token | The |
Token ID | 383 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ilers | +0.134 |
VIDIA | +0.131 |
irtual | +0.131 |
endi | +0.126 |
ually | +0.119 |
Neg logit contributions | |
threat | -0.147 |
aligned | -0.142 |
credit | -0.142 |
strength | -0.140 |
bang | -0.137 |
Token | sentence |
Token ID | 6827 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
threat | +0.214 |
credit | +0.206 |
aligned | +0.205 |
strength | +0.203 |
bang | +0.197 |
Neg logit contributions | |
ilers | -0.231 |
VIDIA | -0.228 |
irtual | -0.227 |
endi | -0.219 |
ually | -0.207 |
Token | of |
Token ID | 286 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
threat | +2.312 |
credit | +2.216 |
aligned | +2.196 |
strength | +2.187 |
bang | +2.129 |
Neg logit contributions | |
ilers | -2.555 |
VIDIA | -2.551 |
irtual | -2.549 |
endi | -2.383 |
eln | -2.270 |
Token | 20 |
Token ID | 1160 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
threat | +0.274 |
credit | +0.264 |
aligned | +0.262 |
strength | +0.259 |
bang | +0.252 |
Neg logit contributions | |
ilers | -0.328 |
VIDIA | -0.326 |
irtual | -0.324 |
endi | -0.312 |
LET | -0.295 |
Token | years |
Token ID | 812 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
threat | +0.024 |
credit | +0.024 |
aligned | +0.023 |
strength | +0.023 |
bang | +0.023 |
Neg logit contributions | |
ilers | -0.018 |
VIDIA | -0.018 |
irtual | -0.018 |
endi | -0.017 |
LET | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +6.65e-05 |
Pos logit contributions | |
ilers | +0.501 |
VIDIA | +0.491 |
irtual | +0.488 |
endi | +0.474 |
ually | +0.451 |
Neg logit contributions | |
threat | -0.507 |
aligned | -0.489 |
credit | -0.489 |
strength | -0.484 |
bang | -0.468 |
Token | or |
Token ID | 393 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
ilers | +0.000 |
VIDIA | +0.000 |
irtual | +0.000 |
endi | +0.000 |
ually | +0.000 |
Neg logit contributions | |
threat | -0.000 |
credit | -0.000 |
aligned | -0.000 |
strength | -0.000 |
bang | -0.000 |
Token | only |
Token ID | 691 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ilers | +0.461 |
VIDIA | +0.454 |
irtual | +0.452 |
endi | +0.437 |
ually | +0.412 |
Neg logit contributions | |
threat | -0.477 |
credit | -0.461 |
aligned | -0.460 |
strength | -0.455 |
bang | -0.443 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
threat | +0.293 |
credit | +0.281 |
aligned | +0.281 |
strength | +0.277 |
bang | +0.270 |
Neg logit contributions | |
ilers | -0.289 |
VIDIA | -0.287 |
irtual | -0.286 |
endi | -0.274 |
LET | -0.258 |
Token | sense |
Token ID | 2565 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ilers | +0.345 |
VIDIA | +0.341 |
irtual | +0.339 |
endi | +0.327 |
ually | +0.309 |
Neg logit contributions | |
threat | -0.353 |
credit | -0.341 |
aligned | -0.340 |
strength | -0.336 |
bang | -0.327 |
Token | as |
Token ID | 355 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ilers | +0.458 |
VIDIA | +0.450 |
irtual | +0.449 |
endi | +0.436 |
ually | +0.415 |
Neg logit contributions | |
threat | -0.450 |
credit | -0.435 |
aligned | -0.432 |
strength | -0.428 |
bang | -0.415 |
Token | youth |
Token ID | 6205 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
threat | +0.243 |
credit | +0.233 |
aligned | +0.233 |
strength | +0.230 |
bang | +0.223 |
Neg logit contributions | |
ilers | -0.268 |
VIDIA | -0.265 |
irtual | -0.264 |
endi | -0.255 |
LET | -0.240 |
Token | sentence |
Token ID | 6827 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ilers | +0.394 |
VIDIA | +0.388 |
irtual | +0.387 |
endi | +0.372 |
ually | +0.350 |
Neg logit contributions | |
threat | -0.439 |
credit | -0.425 |
aligned | -0.423 |
strength | -0.419 |
bang | -0.408 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
threat | +2.385 |
credit | +2.291 |
aligned | +2.284 |
strength | +2.275 |
bang | +2.193 |
Neg logit contributions | |
irtual | -2.435 |
ilers | -2.433 |
VIDIA | -2.425 |
endi | -2.290 |
LET | -2.179 |
Token | And |
Token ID | 843 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
threat | +0.039 |
credit | +0.038 |
aligned | +0.038 |
strength | +0.037 |
bang | +0.036 |
Neg logit contributions | |
ilers | -0.042 |
VIDIA | -0.041 |
irtual | -0.041 |
endi | -0.040 |
ually | -0.037 |
Token | because |
Token ID | 780 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
threat | +0.086 |
credit | +0.083 |
aligned | +0.083 |
strength | +0.082 |
bang | +0.079 |
Neg logit contributions | |
ilers | -0.090 |
VIDIA | -0.089 |
irtual | -0.088 |
endi | -0.085 |
ually | -0.080 |
Token | he |
Token ID | 339 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
threat | +0.431 |
credit | +0.414 |
aligned | +0.412 |
strength | +0.408 |
bang | +0.396 |
Neg logit contributions | |
ilers | -0.490 |
VIDIA | -0.485 |
irtual | -0.484 |
endi | -0.467 |
LET | -0.440 |
Token | � |
Token ID | 447 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
ilers | +0.041 |
VIDIA | +0.040 |
irtual | +0.040 |
endi | +0.039 |
ually | +0.037 |
Neg logit contributions | |
threat | -0.038 |
credit | -0.037 |
aligned | -0.037 |
strength | -0.036 |
bang | -0.035 |
Token | of |
Token ID | 286 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
ilers | +0.253 |
VIDIA | +0.248 |
irtual | +0.247 |
endi | +0.239 |
ually | +0.225 |
Neg logit contributions | |
threat | -0.299 |
credit | -0.288 |
aligned | -0.288 |
strength | -0.286 |
bang | -0.277 |
Token | dollars |
Token ID | 5054 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
ilers | +0.136 |
VIDIA | +0.136 |
irtual | +0.135 |
endi | +0.128 |
ually | +0.121 |
Neg logit contributions | |
threat | -0.150 |
credit | -0.146 |
aligned | -0.144 |
strength | -0.142 |
bang | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
threat | +0.997 |
credit | +0.966 |
aligned | +0.963 |
strength | +0.953 |
bang | +0.930 |
Neg logit contributions | |
ilers | -0.767 |
VIDIA | -0.756 |
irtual | -0.752 |
endi | -0.721 |
ually | -0.673 |
Token |
|
Token ID | 198 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
threat | +0.025 |
credit | +0.024 |
aligned | +0.024 |
strength | +0.024 |
bang | +0.023 |
Neg logit contributions | |
ilers | -0.026 |
VIDIA | -0.026 |
irtual | -0.026 |
endi | -0.025 |
ually | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -8.85e-03 |
Pos logit contributions | |
threat | +0.055 |
credit | +0.053 |
aligned | +0.053 |
strength | +0.053 |
bang | +0.051 |
Neg logit contributions | |
ilers | -0.057 |
irtual | -0.056 |
VIDIA | -0.056 |
endi | -0.054 |
ually | -0.051 |
Token | Story |
Token ID | 11605 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
threat | +0.014 |
aligned | +0.014 |
credit | +0.014 |
strength | +0.014 |
bang | +0.013 |
Neg logit contributions | |
ilers | -0.019 |
VIDIA | -0.019 |
irtual | -0.019 |
endi | -0.018 |
LET | -0.017 |
Token | continues |
Token ID | 4477 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
threat | +2.252 |
credit | +2.165 |
aligned | +2.156 |
strength | +2.106 |
bang | +2.067 |
Neg logit contributions | |
ilers | -2.553 |
VIDIA | -2.547 |
irtual | -2.543 |
endi | -2.421 |
eln | -2.298 |
Token | below |
Token ID | 2174 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
threat | +0.720 |
credit | +0.690 |
aligned | +0.687 |
strength | +0.678 |
bang | +0.657 |
Neg logit contributions | |
ilers | -0.964 |
VIDIA | -0.949 |
irtual | -0.947 |
endi | -0.918 |
ually | -0.875 |
Token | advertisement |
Token ID | 15422 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
ilers | +0.972 |
irtual | +0.943 |
VIDIA | +0.938 |
endi | +0.904 |
ually | +0.841 |
Neg logit contributions | |
threat | -1.490 |
credit | -1.446 |
aligned | -1.446 |
strength | -1.432 |
bang | -1.400 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
threat | +1.386 |
credit | +1.343 |
aligned | +1.331 |
strength | +1.312 |
bang | +1.274 |
Neg logit contributions | |
VIDIA | -1.642 |
irtual | -1.615 |
ilers | -1.612 |
endi | -1.537 |
eln | -1.448 |
Token |
|
Token ID | 198 |
Feature activation | -5.76e-03 |
Pos logit contributions | |
ilers | +0.061 |
irtual | +0.060 |
VIDIA | +0.060 |
endi | +0.058 |
ually | +0.055 |
Neg logit contributions | |
threat | -0.060 |
aligned | -0.058 |
credit | -0.058 |
strength | -0.057 |
bang | -0.056 |
Token | travel |
Token ID | 3067 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
ilers | +0.110 |
VIDIA | +0.109 |
irtual | +0.109 |
endi | +0.105 |
ually | +0.099 |
Neg logit contributions | |
threat | -0.110 |
credit | -0.106 |
aligned | -0.105 |
strength | -0.104 |
bang | -0.101 |
Token | season |
Token ID | 1622 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
threat | +0.778 |
credit | +0.749 |
aligned | +0.745 |
strength | +0.737 |
bang | +0.715 |
Neg logit contributions | |
ilers | -0.863 |
VIDIA | -0.856 |
irtual | -0.849 |
endi | -0.820 |
LET | -0.774 |
Token | ). |
Token ID | 737 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
ilers | +0.502 |
irtual | +0.495 |
VIDIA | +0.495 |
endi | +0.478 |
ually | +0.452 |
Neg logit contributions | |
threat | -0.465 |
credit | -0.449 |
aligned | -0.447 |
strength | -0.441 |
bang | -0.429 |
Token | Judge |
Token ID | 29511 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
threat | +0.407 |
credit | +0.395 |
aligned | +0.391 |
strength | +0.386 |
bang | +0.376 |
Neg logit contributions | |
ilers | -0.422 |
VIDIA | -0.420 |
irtual | -0.418 |
endi | -0.400 |
ually | -0.378 |
Token | Al |
Token ID | 978 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
threat | +0.872 |
credit | +0.836 |
aligned | +0.835 |
strength | +0.825 |
bang | +0.799 |
Neg logit contributions | |
ilers | -1.139 |
VIDIA | -1.124 |
irtual | -1.121 |
endi | -1.079 |
ually | -1.023 |
Token | sup |
Token ID | 37330 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
threat | +0.126 |
credit | +0.120 |
aligned | +0.119 |
strength | +0.117 |
bang | +0.113 |
Neg logit contributions | |
ilers | -0.204 |
VIDIA | -0.202 |
irtual | -0.202 |
endi | -0.196 |
ually | -0.187 |
Token | held |
Token ID | 2714 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
threat | +2.441 |
aligned | +2.350 |
credit | +2.324 |
strength | +2.285 |
� | +2.246 |
Neg logit contributions | |
ilers | -2.370 |
VIDIA | -2.348 |
irtual | -2.329 |
endi | -2.204 |
LET | -2.090 |
Token | a |
Token ID | 257 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
threat | +1.243 |
credit | +1.207 |
aligned | +1.196 |
strength | +1.184 |
bang | +1.153 |
Neg logit contributions | |
ilers | -1.160 |
VIDIA | -1.145 |
irtual | -1.133 |
endi | -1.089 |
LET | -1.028 |
Token | closed |
Token ID | 4838 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
ilers | +0.069 |
VIDIA | +0.068 |
irtual | +0.068 |
endi | +0.065 |
ually | +0.061 |
Neg logit contributions | |
threat | -0.085 |
credit | -0.083 |
aligned | -0.082 |
strength | -0.082 |
bang | -0.080 |
Token | hearing |
Token ID | 4854 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
ilers | +0.740 |
VIDIA | +0.729 |
irtual | +0.725 |
endi | +0.698 |
ually | +0.658 |
Neg logit contributions | |
threat | -0.859 |
aligned | -0.829 |
credit | -0.829 |
strength | -0.821 |
bang | -0.798 |
Token | about |
Token ID | 546 |
Feature activation | +3.48e-03 |
Pos logit contributions | |
threat | +1.114 |
credit | +1.068 |
aligned | +1.064 |
strength | +1.049 |
bang | +1.018 |
Neg logit contributions | |
ilers | -1.412 |
VIDIA | -1.402 |
irtual | -1.394 |
endi | -1.343 |
ually | -1.275 |
Token | he |
Token ID | 339 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
threat | +0.110 |
credit | +0.106 |
aligned | +0.106 |
strength | +0.104 |
bang | +0.101 |
Neg logit contributions | |
ilers | -0.130 |
VIDIA | -0.129 |
irtual | -0.128 |
endi | -0.124 |
ually | -0.117 |
Token | should |
Token ID | 815 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
ilers | +0.259 |
VIDIA | +0.257 |
irtual | +0.256 |
endi | +0.244 |
LET | +0.230 |
Neg logit contributions | |
threat | -0.286 |
credit | -0.276 |
aligned | -0.275 |
strength | -0.272 |
bang | -0.266 |
Token | be |
Token ID | 307 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
VIDIA | +0.777 |
ilers | +0.775 |
irtual | +0.771 |
endi | +0.736 |
LET | +0.689 |
Neg logit contributions | |
threat | -0.915 |
credit | -0.886 |
aligned | -0.881 |
strength | -0.872 |
bang | -0.852 |
Token | serving |
Token ID | 7351 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ilers | +0.037 |
VIDIA | +0.037 |
irtual | +0.036 |
endi | +0.035 |
LET | +0.033 |
Neg logit contributions | |
threat | -0.037 |
credit | -0.035 |
aligned | -0.035 |
strength | -0.035 |
bang | -0.034 |
Token | his |
Token ID | 465 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
ilers | +0.356 |
VIDIA | +0.352 |
irtual | +0.351 |
endi | +0.339 |
ually | +0.323 |
Neg logit contributions | |
threat | -0.297 |
credit | -0.286 |
aligned | -0.285 |
strength | -0.281 |
bang | -0.273 |
Token | sentence |
Token ID | 6827 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
threat | +0.040 |
credit | +0.038 |
aligned | +0.038 |
strength | +0.038 |
bang | +0.037 |
Neg logit contributions | |
ilers | -0.041 |
VIDIA | -0.040 |
irtual | -0.040 |
endi | -0.039 |
ually | -0.036 |
Token | in |
Token ID | 287 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
threat | +2.415 |
aligned | +2.321 |
credit | +2.318 |
strength | +2.297 |
bang | +2.229 |
Neg logit contributions | |
ilers | -2.374 |
VIDIA | -2.369 |
irtual | -2.353 |
endi | -2.222 |
LET | -2.105 |
Token | Canada |
Token ID | 3340 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
threat | +0.186 |
credit | +0.178 |
aligned | +0.178 |
strength | +0.175 |
bang | +0.170 |
Neg logit contributions | |
ilers | -0.226 |
VIDIA | -0.223 |
irtual | -0.222 |
endi | -0.215 |
ually | -0.204 |
Token | as |
Token ID | 355 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
threat | +0.146 |
credit | +0.141 |
aligned | +0.140 |
strength | +0.139 |
bang | +0.136 |
Neg logit contributions | |
ilers | -0.124 |
VIDIA | -0.122 |
irtual | -0.122 |
endi | -0.117 |
ually | -0.110 |
Token | a |
Token ID | 257 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
threat | +0.196 |
credit | +0.189 |
aligned | +0.188 |
strength | +0.186 |
bang | +0.181 |
Neg logit contributions | |
ilers | -0.207 |
VIDIA | -0.205 |
irtual | -0.204 |
endi | -0.197 |
LET | -0.185 |
Token | youth |
Token ID | 6205 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ilers | +0.151 |
VIDIA | +0.149 |
irtual | +0.148 |
endi | +0.143 |
ually | +0.136 |
Neg logit contributions | |
threat | -0.144 |
credit | -0.139 |
aligned | -0.139 |
strength | -0.137 |
bang | -0.134 |
Token | Gal |
Token ID | 26552 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
threat | +0.017 |
credit | +0.017 |
aligned | +0.016 |
strength | +0.016 |
bang | +0.016 |
Neg logit contributions | |
ilers | -0.021 |
VIDIA | -0.021 |
irtual | -0.020 |
endi | -0.020 |
ually | -0.019 |
Token | ar |
Token ID | 283 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ilers | +1.312 |
irtual | +1.289 |
VIDIA | +1.283 |
endi | +1.260 |
ually | +1.207 |
Neg logit contributions | |
threat | -0.705 |
credit | -0.666 |
aligned | -0.663 |
strength | -0.656 |
bang | -0.624 |
Token | za |
Token ID | 4496 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ilers | +0.474 |
irtual | +0.465 |
VIDIA | +0.464 |
endi | +0.457 |
ually | +0.439 |
Neg logit contributions | |
threat | -0.232 |
aligned | -0.219 |
credit | -0.218 |
strength | -0.214 |
bang | -0.204 |
Token | , |
Token ID | 11 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
ilers | +0.450 |
VIDIA | +0.446 |
irtual | +0.444 |
endi | +0.426 |
LET | +0.402 |
Neg logit contributions | |
threat | -0.441 |
credit | -0.425 |
aligned | -0.423 |
strength | -0.417 |
bang | -0.407 |
Token | a |
Token ID | 257 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ilers | +0.025 |
VIDIA | +0.025 |
irtual | +0.025 |
endi | +0.024 |
ually | +0.022 |
Neg logit contributions | |
threat | -0.024 |
credit | -0.023 |
aligned | -0.023 |
strength | -0.023 |
bang | -0.022 |
Token | Hispanic |
Token ID | 16949 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
ilers | +0.222 |
VIDIA | +0.219 |
irtual | +0.219 |
endi | +0.212 |
ually | +0.201 |
Neg logit contributions | |
threat | -0.186 |
credit | -0.179 |
aligned | -0.179 |
strength | -0.176 |
bang | -0.171 |
Token | man |
Token ID | 582 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
ilers | +1.643 |
VIDIA | +1.619 |
irtual | +1.610 |
endi | +1.556 |
ually | +1.476 |
Neg logit contributions | |
threat | -1.709 |
aligned | -1.646 |
credit | -1.645 |
strength | -1.623 |
bang | -1.580 |
Token | of |
Token ID | 286 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
ilers | +0.232 |
VIDIA | +0.227 |
irtual | +0.226 |
endi | +0.220 |
ually | +0.208 |
Neg logit contributions | |
threat | -0.252 |
credit | -0.243 |
aligned | -0.242 |
strength | -0.240 |
bang | -0.233 |
Token | Puerto |
Token ID | 15295 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ilers | +0.203 |
VIDIA | +0.200 |
irtual | +0.199 |
endi | +0.194 |
ually | +0.184 |
Neg logit contributions | |
threat | -0.157 |
credit | -0.150 |
aligned | -0.150 |
strength | -0.148 |
bang | -0.143 |
Token | Rican |
Token ID | 44459 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
ilers | +0.720 |
VIDIA | +0.705 |
irtual | +0.703 |
endi | +0.683 |
ually | +0.654 |
Neg logit contributions | |
threat | -0.485 |
credit | -0.463 |
aligned | -0.462 |
strength | -0.456 |
bang | -0.440 |
Token | heritage |
Token ID | 15012 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
ilers | +0.726 |
VIDIA | +0.713 |
irtual | +0.709 |
endi | +0.676 |
ually | +0.625 |
Neg logit contributions | |
threat | -1.194 |
credit | -1.158 |
aligned | -1.156 |
strength | -1.145 |
bang | -1.120 |
Token | that |
Token ID | 326 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
threat | +0.440 |
credit | +0.424 |
aligned | +0.423 |
strength | +0.417 |
bang | +0.404 |
Neg logit contributions | |
ilers | -0.449 |
VIDIA | -0.443 |
irtual | -0.442 |
endi | -0.423 |
LET | -0.399 |
Token | he |
Token ID | 339 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
threat | +0.103 |
credit | +0.099 |
aligned | +0.099 |
strength | +0.097 |
bang | +0.094 |
Neg logit contributions | |
ilers | -0.115 |
VIDIA | -0.115 |
irtual | -0.114 |
endi | -0.109 |
ually | -0.103 |
Token | will |
Token ID | 481 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ilers | +0.091 |
VIDIA | +0.091 |
irtual | +0.090 |
endi | +0.086 |
LET | +0.081 |
Neg logit contributions | |
threat | -0.085 |
credit | -0.081 |
aligned | -0.081 |
strength | -0.080 |
bang | -0.078 |
Token | always |
Token ID | 1464 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
VIDIA | +0.214 |
ilers | +0.212 |
irtual | +0.212 |
endi | +0.202 |
LET | +0.189 |
Neg logit contributions | |
threat | -0.254 |
credit | -0.246 |
aligned | -0.244 |
strength | -0.241 |
bang | -0.235 |
Token | support |
Token ID | 1104 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
threat | +0.040 |
credit | +0.038 |
aligned | +0.038 |
strength | +0.038 |
bang | +0.037 |
Neg logit contributions | |
VIDIA | -0.038 |
ilers | -0.038 |
irtual | -0.037 |
endi | -0.036 |
LET | -0.034 |
Token | Info |
Token ID | 14151 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
threat | +0.166 |
aligned | +0.160 |
credit | +0.159 |
strength | +0.157 |
bang | +0.152 |
Neg logit contributions | |
ilers | -0.198 |
VIDIA | -0.197 |
irtual | -0.196 |
endi | -0.188 |
LET | -0.179 |
Token | Wars |
Token ID | 6176 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ilers | +1.299 |
VIDIA | +1.274 |
irtual | +1.251 |
endi | +1.237 |
LET | +1.151 |
Neg logit contributions | |
threat | -1.615 |
credit | -1.572 |
aligned | -1.556 |
strength | -1.544 |
bang | -1.510 |
Token | and |
Token ID | 290 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
ilers | +0.453 |
VIDIA | +0.448 |
irtual | +0.446 |
endi | +0.428 |
ually | +0.403 |
Neg logit contributions | |
threat | -0.500 |
credit | -0.482 |
aligned | -0.481 |
strength | -0.476 |
bang | -0.463 |
Token | Alex |
Token ID | 4422 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ilers | +0.145 |
VIDIA | +0.144 |
irtual | +0.143 |
endi | +0.138 |
LET | +0.130 |
Neg logit contributions | |
threat | -0.146 |
aligned | -0.140 |
credit | -0.140 |
strength | -0.138 |
bang | -0.134 |
Token | Jones |
Token ID | 5437 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
threat | +0.132 |
credit | +0.125 |
aligned | +0.124 |
strength | +0.122 |
bang | +0.117 |
Neg logit contributions | |
ilers | -0.266 |
VIDIA | -0.263 |
irtual | -0.263 |
endi | -0.256 |
ually | -0.245 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
threat | +0.073 |
aligned | +0.070 |
credit | +0.070 |
strength | +0.069 |
bang | +0.067 |
Neg logit contributions | |
ilers | -0.066 |
VIDIA | -0.065 |
irtual | -0.065 |
endi | -0.062 |
ually | -0.058 |
Token | back |
Token ID | 736 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ilers | +0.141 |
VIDIA | +0.140 |
irtual | +0.139 |
endi | +0.133 |
ually | +0.125 |
Neg logit contributions | |
threat | -0.172 |
credit | -0.167 |
aligned | -0.166 |
strength | -0.165 |
bang | -0.161 |
Token | for |
Token ID | 329 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
ilers | +0.560 |
VIDIA | +0.551 |
irtual | +0.550 |
endi | +0.533 |
ually | +0.507 |
Neg logit contributions | |
threat | -0.450 |
credit | -0.431 |
aligned | -0.431 |
strength | -0.424 |
bang | -0.411 |
Token | � |
Token ID | 564 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
ilers | +0.130 |
VIDIA | +0.128 |
irtual | +0.128 |
endi | +0.123 |
LET | +0.115 |
Neg logit contributions | |
threat | -0.141 |
credit | -0.136 |
aligned | -0.136 |
strength | -0.134 |
bang | -0.131 |
Token | � |
Token ID | 250 |
Feature activation | +9.27e-03 |
Pos logit contributions | |
ilers | +0.046 |
VIDIA | +0.045 |
irtual | +0.045 |
endi | +0.043 |
ually | +0.041 |
Neg logit contributions | |
threat | -0.050 |
credit | -0.048 |
aligned | -0.048 |
strength | -0.048 |
bang | -0.046 |
Token | public |
Token ID | 11377 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
ilers | +0.021 |
VIDIA | +0.021 |
irtual | +0.021 |
endi | +0.020 |
ually | +0.019 |
Neg logit contributions | |
threat | -0.014 |
credit | -0.014 |
aligned | -0.014 |
strength | -0.013 |
bang | -0.013 |
Token | service |
Token ID | 2139 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
ilers | +0.170 |
VIDIA | +0.167 |
irtual | +0.167 |
endi | +0.161 |
LET | +0.151 |
Neg logit contributions | |
threat | -0.182 |
credit | -0.176 |
aligned | -0.175 |
strength | -0.173 |
bang | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ilers | +1.341 |
VIDIA | +1.327 |
irtual | +1.314 |
endi | +1.263 |
ually | +1.199 |
Neg logit contributions | |
threat | -1.731 |
credit | -1.680 |
aligned | -1.672 |
strength | -1.658 |
bang | -1.624 |
Token | � |
Token ID | 447 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
threat | +0.216 |
credit | +0.209 |
aligned | +0.208 |
strength | +0.205 |
bang | +0.199 |
Neg logit contributions | |
ilers | -0.238 |
VIDIA | -0.237 |
irtual | -0.235 |
endi | -0.226 |
ually | -0.213 |
Token | � |
Token ID | 251 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
ilers | +0.082 |
VIDIA | +0.081 |
irtual | +0.081 |
endi | +0.078 |
ually | +0.074 |
Neg logit contributions | |
threat | -0.075 |
credit | -0.072 |
aligned | -0.072 |
strength | -0.071 |
bang | -0.069 |
Token | He |
Token ID | 679 |
Feature activation | -6.92e-03 |
Pos logit contributions | |
threat | +0.020 |
credit | +0.019 |
aligned | +0.019 |
strength | +0.019 |
bang | +0.018 |
Neg logit contributions | |
ilers | -0.022 |
VIDIA | -0.022 |
irtual | -0.022 |
endi | -0.021 |
ually | -0.020 |
Token | � |
Token ID | 447 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
threat | +0.013 |
credit | +0.012 |
aligned | +0.012 |
strength | +0.012 |
bang | +0.012 |
Neg logit contributions | |
ilers | -0.014 |
VIDIA | -0.014 |
irtual | -0.013 |
endi | -0.013 |
ually | -0.012 |
Token | son |
Token ID | 3367 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
threat | +0.095 |
credit | +0.092 |
aligned | +0.091 |
strength | +0.089 |
bang | +0.088 |
Neg logit contributions | |
ilers | -0.091 |
irtual | -0.089 |
VIDIA | -0.089 |
endi | -0.085 |
LET | -0.080 |
Token | Andrew |
Token ID | 6858 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ilers | +0.104 |
VIDIA | +0.102 |
irtual | +0.102 |
endi | +0.098 |
LET | +0.092 |
Neg logit contributions | |
threat | -0.101 |
credit | -0.097 |
aligned | -0.097 |
strength | -0.095 |
bang | -0.093 |
Token | sat |
Token ID | 3332 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ilers | +0.200 |
VIDIA | +0.197 |
irtual | +0.196 |
endi | +0.188 |
ually | +0.178 |
Neg logit contributions | |
threat | -0.192 |
credit | -0.184 |
aligned | -0.184 |
strength | -0.181 |
bang | -0.177 |
Token | on |
Token ID | 319 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
ilers | +0.453 |
VIDIA | +0.447 |
irtual | +0.445 |
endi | +0.433 |
ually | +0.411 |
Neg logit contributions | |
threat | -0.379 |
credit | -0.366 |
aligned | -0.363 |
strength | -0.360 |
bang | -0.348 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
threat | +0.032 |
credit | +0.031 |
aligned | +0.030 |
strength | +0.030 |
bang | +0.029 |
Neg logit contributions | |
ilers | -0.040 |
VIDIA | -0.040 |
irtual | -0.040 |
endi | -0.038 |
ually | -0.037 |
Token | board |
Token ID | 3096 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
ilers | +0.181 |
VIDIA | +0.179 |
irtual | +0.178 |
endi | +0.171 |
ually | +0.160 |
Neg logit contributions | |
threat | -0.218 |
credit | -0.212 |
aligned | -0.211 |
strength | -0.208 |
bang | -0.203 |
Token | ; |
Token ID | 26 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ilers | +1.418 |
VIDIA | +1.400 |
irtual | +1.398 |
endi | +1.348 |
LET | +1.263 |
Neg logit contributions | |
threat | -1.497 |
credit | -1.447 |
aligned | -1.439 |
strength | -1.423 |
bang | -1.385 |
Token | the |
Token ID | 262 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
threat | +0.624 |
credit | +0.600 |
aligned | +0.598 |
strength | +0.584 |
bang | +0.570 |
Neg logit contributions | |
ilers | -0.739 |
VIDIA | -0.729 |
irtual | -0.726 |
endi | -0.696 |
ually | -0.662 |
Token | teen |
Token ID | 6036 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ilers | +0.117 |
VIDIA | +0.116 |
irtual | +0.115 |
endi | +0.111 |
ually | +0.105 |
Neg logit contributions | |
threat | -0.116 |
credit | -0.112 |
aligned | -0.111 |
strength | -0.110 |
bang | -0.107 |
Token | got |
Token ID | 1392 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
threat | +0.252 |
credit | +0.243 |
aligned | +0.242 |
strength | +0.238 |
bang | +0.234 |
Neg logit contributions | |
ilers | -0.252 |
VIDIA | -0.248 |
irtual | -0.247 |
endi | -0.236 |
LET | -0.222 |
Token | stock |
Token ID | 4283 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
threat | +0.289 |
credit | +0.279 |
aligned | +0.277 |
strength | +0.273 |
bang | +0.266 |
Neg logit contributions | |
ilers | -0.326 |
VIDIA | -0.323 |
irtual | -0.321 |
endi | -0.309 |
ually | -0.293 |
Token | get |
Token ID | 651 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
VIDIA | +0.049 |
irtual | +0.048 |
ilers | +0.048 |
endi | +0.046 |
LET | +0.043 |
Neg logit contributions | |
threat | -0.050 |
credit | -0.049 |
aligned | -0.048 |
strength | -0.048 |
bang | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ilers | +0.101 |
VIDIA | +0.101 |
irtual | +0.100 |
endi | +0.096 |
ually | +0.091 |
Neg logit contributions | |
threat | -0.084 |
credit | -0.081 |
aligned | -0.081 |
strength | -0.080 |
bang | -0.077 |
Token | nod |
Token ID | 18666 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
VIDIA | +0.020 |
ilers | +0.020 |
irtual | +0.020 |
endi | +0.019 |
ually | +0.018 |
Neg logit contributions | |
threat | -0.023 |
credit | -0.023 |
aligned | -0.022 |
strength | -0.022 |
bang | -0.022 |
Token | for |
Token ID | 329 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
ilers | +0.101 |
VIDIA | +0.100 |
irtual | +0.099 |
endi | +0.096 |
ually | +0.091 |
Neg logit contributions | |
threat | -0.089 |
credit | -0.086 |
aligned | -0.086 |
strength | -0.085 |
bang | -0.082 |
Token | his |
Token ID | 465 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
ilers | +0.031 |
VIDIA | +0.031 |
irtual | +0.031 |
endi | +0.030 |
ually | +0.028 |
Neg logit contributions | |
threat | -0.031 |
credit | -0.029 |
aligned | -0.029 |
strength | -0.029 |
bang | -0.028 |
Token | team |
Token ID | 1074 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
ilers | +0.126 |
VIDIA | +0.126 |
irtual | +0.125 |
endi | +0.119 |
LET | +0.112 |
Neg logit contributions | |
threat | -0.145 |
credit | -0.140 |
aligned | -0.139 |
strength | -0.138 |
bang | -0.134 |
Token | – |
Token ID | 784 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
ilers | +1.785 |
irtual | +1.744 |
VIDIA | +1.742 |
endi | +1.685 |
ually | +1.590 |
Neg logit contributions | |
threat | -1.857 |
aligned | -1.794 |
credit | -1.792 |
strength | -1.762 |
bang | -1.718 |
Token | but |
Token ID | 475 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
threat | +0.026 |
credit | +0.025 |
aligned | +0.025 |
strength | +0.024 |
bang | +0.024 |
Neg logit contributions | |
ilers | -0.028 |
VIDIA | -0.028 |
irtual | -0.028 |
endi | -0.027 |
ually | -0.025 |
Token | maybe |
Token ID | 3863 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
threat | +0.117 |
credit | +0.112 |
aligned | +0.112 |
strength | +0.111 |
bang | +0.107 |
Neg logit contributions | |
ilers | -0.108 |
VIDIA | -0.108 |
irtual | -0.108 |
endi | -0.103 |
ually | -0.096 |
Token | Kris |
Token ID | 27748 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
threat | +0.663 |
credit | +0.641 |
aligned | +0.633 |
strength | +0.631 |
bang | +0.610 |
Neg logit contributions | |
ilers | -0.626 |
VIDIA | -0.625 |
irtual | -0.621 |
endi | -0.595 |
ually | -0.558 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ilers | +0.170 |
VIDIA | +0.168 |
irtual | +0.167 |
endi | +0.160 |
ually | +0.149 |
Neg logit contributions | |
threat | -0.231 |
credit | -0.224 |
aligned | -0.223 |
strength | -0.221 |
bang | -0.216 |
Token | each |
Token ID | 1123 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ilers | +0.032 |
VIDIA | +0.032 |
irtual | +0.032 |
endi | +0.031 |
ually | +0.029 |
Neg logit contributions | |
threat | -0.029 |
credit | -0.028 |
aligned | -0.028 |
strength | -0.027 |
bang | -0.027 |
Token | other |
Token ID | 584 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ilers | +0.331 |
VIDIA | +0.326 |
irtual | +0.325 |
endi | +0.313 |
ually | +0.295 |
Neg logit contributions | |
threat | -0.349 |
credit | -0.336 |
aligned | -0.335 |
strength | -0.332 |
bang | -0.323 |
Token | � |
Token ID | 447 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
threat | +0.447 |
credit | +0.431 |
aligned | +0.430 |
strength | +0.425 |
bang | +0.414 |
Neg logit contributions | |
ilers | -0.419 |
VIDIA | -0.414 |
irtual | -0.411 |
endi | -0.396 |
ually | -0.372 |
Token | � |
Token ID | 247 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
threat | +0.336 |
credit | +0.322 |
aligned | +0.322 |
strength | +0.317 |
bang | +0.307 |
Neg logit contributions | |
ilers | -0.434 |
VIDIA | -0.431 |
irtual | -0.430 |
endi | -0.412 |
ually | -0.390 |
Token | s |
Token ID | 82 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
threat | +0.096 |
credit | +0.093 |
aligned | +0.092 |
strength | +0.091 |
bang | +0.089 |
Neg logit contributions | |
ilers | -0.101 |
VIDIA | -0.100 |
irtual | -0.099 |
endi | -0.096 |
ually | -0.091 |
Token | companies |
Token ID | 2706 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
threat | +0.185 |
credit | +0.179 |
aligned | +0.178 |
strength | +0.176 |
bang | +0.171 |
Neg logit contributions | |
ilers | -0.185 |
VIDIA | -0.183 |
irtual | -0.182 |
endi | -0.176 |
ually | -0.165 |
Token | through |
Token ID | 832 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
ilers | +0.427 |
VIDIA | +0.420 |
irtual | +0.420 |
endi | +0.405 |
ually | +0.381 |
Neg logit contributions | |
threat | -0.447 |
credit | -0.432 |
aligned | -0.431 |
strength | -0.426 |
bang | -0.414 |
Token | an |
Token ID | 281 |
Feature activation | +4.69e-03 |
Pos logit contributions | |
threat | +0.068 |
credit | +0.065 |
aligned | +0.065 |
strength | +0.064 |
bang | +0.062 |
Neg logit contributions | |
ilers | -0.068 |
VIDIA | -0.068 |
irtual | -0.067 |
endi | -0.065 |
LET | -0.061 |
Token | exchange |
Token ID | 5163 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ilers | +0.009 |
VIDIA | +0.009 |
irtual | +0.009 |
endi | +0.008 |
LET | +0.008 |
Neg logit contributions | |
threat | -0.009 |
aligned | -0.009 |
credit | -0.009 |
strength | -0.008 |
bang | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
ilers | +0.742 |
VIDIA | +0.733 |
irtual | +0.729 |
endi | +0.701 |
ually | +0.659 |
Neg logit contributions | |
threat | -0.750 |
credit | -0.723 |
aligned | -0.721 |
strength | -0.711 |
bang | -0.693 |
Token | shares |
Token ID | 7303 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
ilers | +0.068 |
VIDIA | +0.067 |
irtual | +0.067 |
endi | +0.064 |
LET | +0.060 |
Neg logit contributions | |
threat | -0.079 |
credit | -0.076 |
aligned | -0.076 |
strength | -0.075 |
bang | -0.073 |
Token | back |
Token ID | 736 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ilers | +0.304 |
VIDIA | +0.300 |
irtual | +0.299 |
endi | +0.289 |
ually | +0.274 |
Neg logit contributions | |
threat | -0.277 |
credit | -0.266 |
aligned | -0.265 |
strength | -0.262 |
bang | -0.254 |
Token | into |
Token ID | 656 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
ilers | +0.383 |
irtual | +0.378 |
VIDIA | +0.378 |
endi | +0.366 |
ually | +0.348 |
Neg logit contributions | |
threat | -0.333 |
credit | -0.320 |
aligned | -0.318 |
strength | -0.314 |
bang | -0.304 |
Token | D |
Token ID | 360 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
ilers | +0.030 |
VIDIA | +0.030 |
irtual | +0.029 |
endi | +0.028 |
eln | +0.026 |
Neg logit contributions | |
threat | -0.034 |
aligned | -0.033 |
credit | -0.033 |
strength | -0.032 |
bang | -0.031 |
Token | or |
Token ID | 393 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
ilers | +0.156 |
VIDIA | +0.154 |
irtual | +0.153 |
endi | +0.147 |
ually | +0.139 |
Neg logit contributions | |
threat | -0.155 |
credit | -0.149 |
aligned | -0.149 |
strength | -0.147 |
bang | -0.143 |
Token | S |
Token ID | 311 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
threat | +0.625 |
credit | +0.606 |
aligned | +0.606 |
strength | +0.596 |
bang | +0.581 |
Neg logit contributions | |
ilers | -0.641 |
VIDIA | -0.633 |
irtual | -0.626 |
endi | -0.609 |
eln | -0.568 |
Token | and |
Token ID | 290 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
ilers | +0.098 |
VIDIA | +0.096 |
irtual | +0.096 |
endi | +0.093 |
ually | +0.087 |
Neg logit contributions | |
threat | -0.095 |
credit | -0.092 |
aligned | -0.092 |
strength | -0.091 |
bang | -0.088 |
Token | keep |
Token ID | 1394 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ilers | +0.070 |
VIDIA | +0.070 |
irtual | +0.069 |
endi | +0.067 |
LET | +0.062 |
Neg logit contributions | |
threat | -0.079 |
credit | -0.077 |
aligned | -0.076 |
strength | -0.075 |
bang | -0.074 |
Token | your |
Token ID | 534 |
Feature activation | -2.16e-03 |
Pos logit contributions | |
ilers | +0.595 |
VIDIA | +0.590 |
irtual | +0.587 |
endi | +0.563 |
LET | +0.529 |
Neg logit contributions | |
threat | -0.652 |
credit | -0.632 |
aligned | -0.632 |
strength | -0.623 |
bang | -0.605 |
Token | foot |
Token ID | 2366 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
threat | +0.005 |
credit | +0.004 |
aligned | +0.004 |
strength | +0.004 |
bang | +0.004 |
Neg logit contributions | |
ilers | -0.004 |
VIDIA | -0.004 |
irtual | -0.004 |
endi | -0.003 |
LET | -0.003 |
Token | on |
Token ID | 319 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
threat | +0.407 |
credit | +0.391 |
aligned | +0.390 |
strength | +0.385 |
bang | +0.374 |
Neg logit contributions | |
ilers | -0.483 |
VIDIA | -0.477 |
irtual | -0.476 |
endi | -0.460 |
ually | -0.436 |
Token | the |
Token ID | 262 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
threat | +0.004 |
credit | +0.004 |
aligned | +0.004 |
strength | +0.004 |
bang | +0.003 |
Neg logit contributions | |
ilers | -0.004 |
VIDIA | -0.004 |
irtual | -0.003 |
endi | -0.003 |
LET | -0.003 |
Token | woman |
Token ID | 2415 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
threat | +0.002 |
credit | +0.002 |
aligned | +0.002 |
strength | +0.002 |
bang | +0.002 |
Neg logit contributions | |
ilers | -0.002 |
VIDIA | -0.002 |
irtual | -0.002 |
endi | -0.002 |
ually | -0.002 |
Token | who |
Token ID | 508 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ilers | +0.156 |
VIDIA | +0.154 |
irtual | +0.154 |
endi | +0.148 |
ually | +0.140 |
Neg logit contributions | |
threat | -0.155 |
credit | -0.149 |
aligned | -0.149 |
strength | -0.147 |
bang | -0.143 |
Token | had |
Token ID | 550 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
threat | +0.315 |
credit | +0.303 |
aligned | +0.302 |
strength | +0.298 |
bang | +0.291 |
Neg logit contributions | |
ilers | -0.348 |
VIDIA | -0.346 |
irtual | -0.344 |
endi | -0.330 |
LET | -0.312 |
Token | a |
Token ID | 257 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
threat | +0.088 |
credit | +0.085 |
aligned | +0.084 |
strength | +0.084 |
bang | +0.081 |
Neg logit contributions | |
ilers | -0.089 |
VIDIA | -0.088 |
irtual | -0.087 |
endi | -0.084 |
LET | -0.079 |
Token | stroke |
Token ID | 14000 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ilers | +0.314 |
VIDIA | +0.312 |
irtual | +0.310 |
endi | +0.298 |
LET | +0.279 |
Neg logit contributions | |
threat | -0.325 |
credit | -0.314 |
aligned | -0.312 |
strength | -0.309 |
bang | -0.301 |
Token | and |
Token ID | 290 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ilers | +0.378 |
VIDIA | +0.372 |
irtual | +0.371 |
endi | +0.358 |
ually | +0.337 |
Neg logit contributions | |
threat | -0.400 |
credit | -0.386 |
aligned | -0.385 |
strength | -0.381 |
bang | -0.371 |
Token | now |
Token ID | 783 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
ilers | +0.458 |
VIDIA | +0.454 |
irtual | +0.452 |
endi | +0.434 |
LET | +0.409 |
Neg logit contributions | |
threat | -0.442 |
credit | -0.426 |
aligned | -0.425 |
strength | -0.420 |
bang | -0.408 |
Token | sounds |
Token ID | 5238 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
ilers | +0.604 |
VIDIA | +0.597 |
irtual | +0.595 |
endi | +0.575 |
ually | +0.545 |
Neg logit contributions | |
threat | -0.527 |
credit | -0.507 |
aligned | -0.505 |
strength | -0.499 |
bang | -0.484 |
Token | French |
Token ID | 4141 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
threat | +0.725 |
credit | +0.695 |
aligned | +0.692 |
strength | +0.683 |
bang | +0.665 |
Neg logit contributions | |
ilers | -0.860 |
VIDIA | -0.853 |
irtual | -0.848 |
endi | -0.818 |
LET | -0.773 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ilers | +0.324 |
irtual | +0.318 |
VIDIA | +0.317 |
endi | +0.306 |
ually | +0.290 |
Neg logit contributions | |
threat | -0.378 |
credit | -0.366 |
aligned | -0.365 |
strength | -0.361 |
bang | -0.352 |
Token |
|
Token ID | 198 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
ilers | +0.362 |
irtual | +0.354 |
VIDIA | +0.354 |
endi | +0.342 |
ually | +0.324 |
Neg logit contributions | |
threat | -0.352 |
credit | -0.338 |
aligned | -0.338 |
strength | -0.334 |
bang | -0.325 |
Token | than |
Token ID | 621 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
ilers | +0.208 |
VIDIA | +0.206 |
irtual | +0.205 |
endi | +0.197 |
ually | +0.186 |
Neg logit contributions | |
threat | -0.197 |
credit | -0.189 |
aligned | -0.189 |
strength | -0.187 |
bang | -0.182 |
Token | Red |
Token ID | 2297 |
Feature activation | +6.86e-05 |
Pos logit contributions | |
threat | +0.141 |
credit | +0.136 |
aligned | +0.136 |
strength | +0.135 |
bang | +0.132 |
Neg logit contributions | |
ilers | -0.140 |
VIDIA | -0.139 |
irtual | -0.137 |
endi | -0.132 |
ually | -0.124 |
Token | th |
Token ID | 294 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
ilers | +0.000 |
VIDIA | +0.000 |
irtual | +0.000 |
endi | +0.000 |
ually | +0.000 |
Neg logit contributions | |
threat | -0.000 |
credit | -0.000 |
aligned | -0.000 |
strength | -0.000 |
bang | -0.000 |
Token | ai |
Token ID | 1872 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
ilers | +1.156 |
irtual | +1.139 |
VIDIA | +1.139 |
endi | +1.112 |
ually | +1.063 |
Neg logit contributions | |
threat | -0.657 |
credit | -0.624 |
aligned | -0.620 |
strength | -0.609 |
bang | -0.584 |
Token | curry |
Token ID | 34611 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
ilers | +0.776 |
VIDIA | +0.766 |
irtual | +0.765 |
endi | +0.740 |
ually | +0.703 |
Neg logit contributions | |
threat | -0.626 |
credit | -0.602 |
aligned | -0.600 |
strength | -0.591 |
bang | -0.572 |
Token | for |
Token ID | 329 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ilers | +0.767 |
VIDIA | +0.754 |
irtual | +0.753 |
endi | +0.727 |
ually | +0.688 |
Neg logit contributions | |
threat | -0.762 |
credit | -0.735 |
aligned | -0.733 |
strength | -0.723 |
bang | -0.703 |
Token | the |
Token ID | 262 |
Feature activation | +9.80e-02 |
Pos logit contributions | |
ilers | +0.289 |
VIDIA | +0.285 |
irtual | +0.283 |
endi | +0.272 |
ually | +0.255 |
Neg logit contributions | |
threat | -0.337 |
credit | -0.326 |
aligned | -0.325 |
strength | -0.322 |
bang | -0.314 |
Token | rest |
Token ID | 1334 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ilers | +0.209 |
VIDIA | +0.207 |
irtual | +0.206 |
endi | +0.199 |
ually | +0.189 |
Neg logit contributions | |
threat | -0.162 |
credit | -0.156 |
aligned | -0.155 |
strength | -0.153 |
bang | -0.149 |
Token | of |
Token ID | 286 |
Feature activation | -8.73e-03 |
Pos logit contributions | |
threat | +0.454 |
credit | +0.437 |
aligned | +0.435 |
strength | +0.432 |
bang | +0.421 |
Neg logit contributions | |
VIDIA | -0.493 |
ilers | -0.492 |
irtual | -0.488 |
endi | -0.466 |
ually | -0.439 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
threat | +0.018 |
credit | +0.018 |
aligned | +0.017 |
strength | +0.017 |
bang | +0.017 |
Neg logit contributions | |
ilers | -0.015 |
VIDIA | -0.015 |
irtual | -0.015 |
endi | -0.014 |
ually | -0.013 |
Token | week |
Token ID | 1285 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
threat | +0.017 |
credit | +0.016 |
aligned | +0.016 |
strength | +0.016 |
bang | +0.015 |
Neg logit contributions | |
ilers | -0.023 |
VIDIA | -0.022 |
irtual | -0.022 |
endi | -0.022 |
ually | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
threat | +0.073 |
credit | +0.071 |
aligned | +0.071 |
strength | +0.070 |
bang | +0.068 |
Neg logit contributions | |
ilers | -0.063 |
VIDIA | -0.063 |
irtual | -0.062 |
endi | -0.060 |
ually | -0.056 |
Token | V |
Token ID | 53 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
threat | +0.094 |
credit | +0.091 |
aligned | +0.090 |
strength | +0.089 |
bang | +0.087 |
Neg logit contributions | |
ilers | -0.099 |
VIDIA | -0.098 |
irtual | -0.097 |
endi | -0.094 |
ually | -0.088 |
Token | ou |
Token ID | 280 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
threat | +0.040 |
credit | +0.038 |
aligned | +0.038 |
strength | +0.037 |
bang | +0.036 |
Neg logit contributions | |
ilers | -0.081 |
VIDIA | -0.080 |
irtual | -0.079 |
endi | -0.077 |
ually | -0.074 |
Token | cher |
Token ID | 2044 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
threat | +0.196 |
credit | +0.189 |
aligned | +0.188 |
strength | +0.185 |
bang | +0.180 |
Neg logit contributions | |
VIDIA | -0.208 |
ilers | -0.207 |
irtual | -0.206 |
endi | -0.198 |
LET | -0.187 |
Token | proponents |
Token ID | 27642 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
ilers | +0.124 |
VIDIA | +0.123 |
irtual | +0.122 |
endi | +0.118 |
ually | +0.112 |
Neg logit contributions | |
threat | -0.119 |
credit | -0.115 |
aligned | -0.115 |
strength | -0.113 |
bang | -0.110 |
Token | are |
Token ID | 389 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
threat | +1.405 |
credit | +1.351 |
aligned | +1.349 |
strength | +1.321 |
bang | +1.299 |
Neg logit contributions | |
VIDIA | -1.303 |
ilers | -1.298 |
irtual | -1.291 |
endi | -1.235 |
LET | -1.165 |
Token | trying |
Token ID | 2111 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
ilers | +0.036 |
VIDIA | +0.036 |
irtual | +0.036 |
endi | +0.034 |
LET | +0.032 |
Neg logit contributions | |
threat | -0.038 |
credit | -0.036 |
aligned | -0.036 |
strength | -0.036 |
bang | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
threat | +0.109 |
credit | +0.105 |
aligned | +0.104 |
strength | +0.103 |
bang | +0.100 |
Neg logit contributions | |
ilers | -0.148 |
VIDIA | -0.146 |
irtual | -0.145 |
endi | -0.141 |
ually | -0.135 |
Token | chip |
Token ID | 11594 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ilers | +0.245 |
VIDIA | +0.242 |
irtual | +0.241 |
endi | +0.232 |
ually | +0.218 |
Neg logit contributions | |
threat | -0.272 |
credit | -0.263 |
aligned | -0.262 |
strength | -0.259 |
bang | -0.252 |
Token | away |
Token ID | 1497 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
threat | +0.233 |
credit | +0.225 |
aligned | +0.224 |
strength | +0.222 |
bang | +0.216 |
Neg logit contributions | |
ilers | -0.230 |
VIDIA | -0.227 |
irtual | -0.226 |
endi | -0.218 |
ually | -0.205 |
Token | at |
Token ID | 379 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ilers | +0.168 |
VIDIA | +0.166 |
irtual | +0.165 |
endi | +0.160 |
ually | +0.150 |
Neg logit contributions | |
threat | -0.192 |
credit | -0.185 |
aligned | -0.185 |
strength | -0.183 |
bang | -0.179 |
Token | capital |
Token ID | 3139 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
threat | +0.236 |
credit | +0.228 |
aligned | +0.228 |
strength | +0.224 |
bang | +0.220 |
Neg logit contributions | |
ilers | -0.226 |
VIDIA | -0.224 |
irtual | -0.223 |
endi | -0.213 |
LET | -0.200 |
Token | flight |
Token ID | 5474 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
ilers | +0.275 |
VIDIA | +0.272 |
irtual | +0.271 |
endi | +0.261 |
ually | +0.246 |
Neg logit contributions | |
threat | -0.260 |
credit | -0.250 |
aligned | -0.250 |
strength | -0.246 |
bang | -0.240 |
Token | and |
Token ID | 290 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
threat | +0.572 |
credit | +0.548 |
aligned | +0.548 |
strength | +0.539 |
bang | +0.528 |
Neg logit contributions | |
ilers | -0.563 |
VIDIA | -0.558 |
irtual | -0.555 |
endi | -0.532 |
LET | -0.501 |
Token | tax |
Token ID | 1687 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
threat | +0.196 |
credit | +0.188 |
aligned | +0.188 |
strength | +0.185 |
bang | +0.182 |
Neg logit contributions | |
ilers | -0.190 |
VIDIA | -0.189 |
irtual | -0.189 |
endi | -0.180 |
LET | -0.169 |
Token | evasion |
Token ID | 30877 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ilers | +0.401 |
VIDIA | +0.393 |
irtual | +0.390 |
endi | +0.372 |
ually | +0.343 |
Neg logit contributions | |
threat | -0.727 |
credit | -0.706 |
aligned | -0.705 |
strength | -0.699 |
bang | -0.684 |
Token | , |
Token ID | 11 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ilers | +0.260 |
VIDIA | +0.257 |
irtual | +0.256 |
endi | +0.246 |
ually | +0.232 |
Neg logit contributions | |
threat | -0.285 |
credit | -0.276 |
aligned | -0.275 |
strength | -0.272 |
bang | -0.265 |
Token | it |
Token ID | 340 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
threat | +0.248 |
credit | +0.239 |
aligned | +0.238 |
strength | +0.235 |
bang | +0.229 |
Neg logit contributions | |
ilers | -0.268 |
VIDIA | -0.265 |
irtual | -0.264 |
endi | -0.255 |
ually | -0.241 |
Token | is |
Token ID | 318 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ilers | +0.059 |
VIDIA | +0.059 |
irtual | +0.058 |
endi | +0.056 |
ually | +0.053 |
Neg logit contributions | |
threat | -0.057 |
credit | -0.055 |
aligned | -0.055 |
strength | -0.054 |
bang | -0.053 |
Token | hard |
Token ID | 1327 |
Feature activation | -7.88e-02 |
Pos logit contributions | |
ilers | +0.297 |
VIDIA | +0.295 |
irtual | +0.294 |
endi | +0.282 |
LET | +0.265 |
Neg logit contributions | |
threat | -0.302 |
credit | -0.291 |
aligned | -0.290 |
strength | -0.286 |
bang | -0.279 |
Token | to |
Token ID | 284 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
threat | +0.130 |
credit | +0.124 |
aligned | +0.123 |
strength | +0.122 |
bang | +0.118 |
Neg logit contributions | |
ilers | -0.169 |
VIDIA | -0.167 |
irtual | -0.166 |
endi | -0.161 |
ually | -0.154 |
Token | convince |
Token ID | 11508 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
ilers | +0.043 |
VIDIA | +0.043 |
irtual | +0.043 |
endi | +0.041 |
LET | +0.039 |
Neg logit contributions | |
threat | -0.039 |
credit | -0.037 |
aligned | -0.037 |
strength | -0.037 |
bang | -0.036 |
Token | were |
Token ID | 547 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
threat | +0.751 |
aligned | +0.722 |
credit | +0.720 |
strength | +0.710 |
bang | +0.691 |
Neg logit contributions | |
ilers | -0.690 |
VIDIA | -0.685 |
irtual | -0.684 |
endi | -0.654 |
LET | -0.616 |
Token | done |
Token ID | 1760 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
threat | +0.308 |
credit | +0.296 |
aligned | +0.295 |
strength | +0.291 |
bang | +0.283 |
Neg logit contributions | |
ilers | -0.345 |
VIDIA | -0.342 |
irtual | -0.340 |
endi | -0.329 |
ually | -0.311 |
Token | in |
Token ID | 287 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
threat | +0.579 |
credit | +0.557 |
aligned | +0.556 |
strength | +0.548 |
bang | +0.535 |
Neg logit contributions | |
ilers | -0.557 |
VIDIA | -0.552 |
irtual | -0.549 |
endi | -0.528 |
ually | -0.497 |
Token | Roh |
Token ID | 32694 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
threat | +0.212 |
credit | +0.204 |
aligned | +0.203 |
strength | +0.201 |
bang | +0.197 |
Neg logit contributions | |
ilers | -0.204 |
VIDIA | -0.203 |
irtual | -0.201 |
endi | -0.195 |
ually | -0.182 |
Token | t |
Token ID | 83 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
threat | +1.111 |
credit | +1.073 |
aligned | +1.070 |
strength | +1.059 |
bang | +1.037 |
Neg logit contributions | |
VIDIA | -0.895 |
ilers | -0.889 |
irtual | -0.879 |
endi | -0.835 |
ually | -0.787 |
Token | ak |
Token ID | 461 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
threat | +0.811 |
credit | +0.777 |
aligned | +0.773 |
strength | +0.760 |
bang | +0.736 |
Neg logit contributions | |
VIDIA | -1.352 |
ilers | -1.344 |
irtual | -1.336 |
endi | -1.288 |
LET | -1.236 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
threat | +0.131 |
credit | +0.127 |
aligned | +0.126 |
strength | +0.124 |
bang | +0.121 |
Neg logit contributions | |
ilers | -0.130 |
VIDIA | -0.129 |
irtual | -0.128 |
endi | -0.123 |
ually | -0.116 |
Token | Public |
Token ID | 5094 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ilers | +0.034 |
VIDIA | +0.034 |
irtual | +0.034 |
endi | +0.033 |
ually | +0.031 |
Neg logit contributions | |
threat | -0.034 |
credit | -0.033 |
aligned | -0.033 |
strength | -0.032 |
bang | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
threat | +0.588 |
credit | +0.571 |
aligned | +0.566 |
strength | +0.560 |
bang | +0.545 |
Neg logit contributions | |
ilers | -0.486 |
VIDIA | -0.479 |
irtual | -0.477 |
endi | -0.458 |
LET | -0.430 |
Token | private |
Token ID | 2839 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
ilers | +0.308 |
VIDIA | +0.304 |
irtual | +0.303 |
endi | +0.292 |
ually | +0.276 |
Neg logit contributions | |
threat | -0.313 |
credit | -0.302 |
aligned | -0.301 |
strength | -0.297 |
bang | -0.290 |
Token | properties |
Token ID | 6608 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
threat | +0.981 |
credit | +0.955 |
aligned | +0.949 |
strength | +0.935 |
bang | +0.912 |
Neg logit contributions | |
ilers | -0.769 |
irtual | -0.762 |
VIDIA | -0.761 |
endi | -0.726 |
eln | -0.677 |
Token | grounds |
Token ID | 9384 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
threat | +0.707 |
credit | +0.688 |
aligned | +0.685 |
strength | +0.680 |
bang | +0.660 |
Neg logit contributions | |
ilers | -0.454 |
VIDIA | -0.446 |
irtual | -0.445 |
endi | -0.423 |
LET | -0.394 |
Token | the |
Token ID | 262 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ilers | +0.210 |
VIDIA | +0.207 |
irtual | +0.207 |
endi | +0.199 |
LET | +0.187 |
Neg logit contributions | |
threat | -0.224 |
credit | -0.216 |
aligned | -0.216 |
strength | -0.214 |
bang | -0.208 |
Token | justice |
Token ID | 5316 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
threat | +0.256 |
credit | +0.247 |
aligned | +0.247 |
strength | +0.244 |
bang | +0.237 |
Neg logit contributions | |
ilers | -0.247 |
VIDIA | -0.244 |
irtual | -0.243 |
endi | -0.234 |
ually | -0.220 |
Token | of |
Token ID | 286 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
threat | +1.085 |
aligned | +1.042 |
credit | +1.039 |
strength | +1.024 |
bang | +0.997 |
Neg logit contributions | |
ilers | -1.130 |
VIDIA | -1.116 |
irtual | -1.108 |
endi | -1.061 |
LET | -1.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
threat | +0.249 |
credit | +0.241 |
aligned | +0.240 |
strength | +0.238 |
bang | +0.231 |
Neg logit contributions | |
ilers | -0.236 |
VIDIA | -0.234 |
irtual | -0.233 |
endi | -0.223 |
LET | -0.211 |
Token | cause |
Token ID | 2728 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
threat | +0.367 |
credit | +0.354 |
aligned | +0.353 |
strength | +0.349 |
bang | +0.339 |
Neg logit contributions | |
ilers | -0.345 |
VIDIA | -0.341 |
irtual | -0.340 |
endi | -0.327 |
LET | -0.308 |
Token | of |
Token ID | 286 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
threat | +0.723 |
credit | +0.695 |
aligned | +0.694 |
strength | +0.685 |
bang | +0.669 |
Neg logit contributions | |
ilers | -0.714 |
VIDIA | -0.705 |
irtual | -0.704 |
endi | -0.673 |
LET | -0.637 |
Token | women |
Token ID | 1466 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
threat | +0.307 |
credit | +0.296 |
aligned | +0.294 |
strength | +0.292 |
bang | +0.284 |
Neg logit contributions | |
ilers | -0.293 |
VIDIA | -0.291 |
irtual | -0.290 |
endi | -0.278 |
LET | -0.262 |
Token | 's |
Token ID | 338 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
ilers | +0.298 |
VIDIA | +0.295 |
irtual | +0.294 |
endi | +0.282 |
ually | +0.265 |
Neg logit contributions | |
threat | -0.319 |
credit | -0.308 |
aligned | -0.307 |
strength | -0.304 |
bang | -0.296 |
Token | equality |
Token ID | 10537 |
Feature activation | -9.46e-03 |
Pos logit contributions | |
threat | +0.093 |
credit | +0.090 |
aligned | +0.089 |
strength | +0.089 |
bang | +0.086 |
Neg logit contributions | |
ilers | -0.082 |
VIDIA | -0.081 |
irtual | -0.081 |
endi | -0.078 |
LET | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
threat | +0.019 |
credit | +0.019 |
aligned | +0.019 |
strength | +0.018 |
bang | +0.018 |
Neg logit contributions | |
ilers | -0.017 |
VIDIA | -0.016 |
irtual | -0.016 |
endi | -0.016 |
ually | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
threat | +0.086 |
credit | +0.083 |
aligned | +0.083 |
strength | +0.082 |
bang | +0.079 |
Neg logit contributions | |
ilers | -0.090 |
VIDIA | -0.088 |
irtual | -0.088 |
endi | -0.085 |
ually | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
threat | +0.059 |
credit | +0.057 |
aligned | +0.057 |
strength | +0.056 |
bang | +0.054 |
Neg logit contributions | |
ilers | -0.061 |
irtual | -0.060 |
VIDIA | -0.060 |
endi | -0.058 |
ually | -0.055 |
Token | It |
Token ID | 1026 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
threat | +0.044 |
credit | +0.042 |
aligned | +0.042 |
strength | +0.042 |
bang | +0.040 |
Neg logit contributions | |
ilers | -0.052 |
VIDIA | -0.051 |
irtual | -0.051 |
endi | -0.049 |
ually | -0.047 |
Token | 's |
Token ID | 338 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
threat | +0.080 |
credit | +0.077 |
aligned | +0.077 |
strength | +0.076 |
bang | +0.074 |
Neg logit contributions | |
ilers | -0.079 |
VIDIA | -0.078 |
irtual | -0.077 |
endi | -0.074 |
ually | -0.070 |
Token | been |
Token ID | 587 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
ilers | +0.360 |
VIDIA | +0.358 |
irtual | +0.357 |
endi | +0.340 |
ually | +0.320 |
Neg logit contributions | |
threat | -0.362 |
credit | -0.349 |
aligned | -0.347 |
strength | -0.344 |
bang | -0.335 |
Token | a |
Token ID | 257 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
ilers | +0.032 |
VIDIA | +0.032 |
irtual | +0.032 |
endi | +0.030 |
ually | +0.029 |
Neg logit contributions | |
threat | -0.029 |
credit | -0.028 |
aligned | -0.028 |
strength | -0.028 |
bang | -0.027 |
Token | terrible |
Token ID | 7818 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
threat | +0.092 |
credit | +0.089 |
aligned | +0.088 |
strength | +0.088 |
bang | +0.085 |
Neg logit contributions | |
ilers | -0.084 |
VIDIA | -0.084 |
irtual | -0.084 |
endi | -0.080 |
ually | -0.075 |
Token | year |
Token ID | 614 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
ilers | +0.865 |
VIDIA | +0.854 |
irtual | +0.851 |
endi | +0.822 |
ually | +0.779 |
Neg logit contributions | |
threat | -0.770 |
credit | -0.741 |
aligned | -0.739 |
strength | -0.729 |
bang | -0.709 |
Token | for |
Token ID | 329 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
threat | +0.747 |
credit | +0.711 |
aligned | +0.708 |
strength | +0.698 |
bang | +0.674 |
Neg logit contributions | |
ilers | -1.232 |
VIDIA | -1.229 |
irtual | -1.222 |
endi | -1.179 |
LET | -1.126 |
Token | Tan |
Token ID | 11818 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
threat | +0.104 |
credit | +0.100 |
aligned | +0.099 |
strength | +0.098 |
bang | +0.095 |
Neg logit contributions | |
ilers | -0.138 |
VIDIA | -0.138 |
irtual | -0.138 |
endi | -0.132 |
eln | -0.126 |
Token | ne |
Token ID | 710 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
threat | +0.025 |
credit | +0.022 |
aligned | +0.021 |
strength | +0.020 |
bang | +0.018 |
Neg logit contributions | |
ilers | -0.152 |
VIDIA | -0.151 |
irtual | -0.151 |
endi | -0.147 |
ually | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
threat | +0.176 |
credit | +0.171 |
aligned | +0.170 |
strength | +0.168 |
bang | +0.165 |
Neg logit contributions | |
ilers | -0.132 |
VIDIA | -0.132 |
irtual | -0.131 |
endi | -0.124 |
ually | -0.116 |
Token | Invalid |
Token ID | 17665 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
threat | +0.200 |
credit | +0.194 |
aligned | +0.193 |
strength | +0.190 |
bang | +0.185 |
Neg logit contributions | |
ilers | -0.207 |
VIDIA | -0.205 |
irtual | -0.204 |
endi | -0.196 |
ually | -0.185 |
Token | email |
Token ID | 3053 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
threat | +1.436 |
aligned | +1.414 |
credit | +1.410 |
strength | +1.388 |
� | +1.354 |
Neg logit contributions | |
VIDIA | -0.775 |
irtual | -0.748 |
ilers | -0.736 |
endi | -0.681 |
LET | -0.621 |
Token | address |
Token ID | 2209 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
threat | +0.644 |
credit | +0.631 |
aligned | +0.630 |
strength | +0.620 |
bang | +0.610 |
Neg logit contributions | |
VIDIA | -0.250 |
irtual | -0.244 |
ilers | -0.242 |
endi | -0.219 |
eln | -0.196 |
Token | . |
Token ID | 13 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
threat | +0.430 |
credit | +0.417 |
aligned | +0.416 |
strength | +0.411 |
bang | +0.402 |
Neg logit contributions | |
VIDIA | -0.325 |
ilers | -0.325 |
irtual | -0.322 |
endi | -0.305 |
ually | -0.285 |
Token | Please |
Token ID | 4222 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
threat | +0.264 |
credit | +0.258 |
aligned | +0.257 |
strength | +0.255 |
bang | +0.250 |
Neg logit contributions | |
ilers | -0.107 |
VIDIA | -0.105 |
irtual | -0.104 |
endi | -0.097 |
ually | -0.087 |
Token | re |
Token ID | 302 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
threat | +1.052 |
credit | +1.018 |
aligned | +1.014 |
strength | +1.000 |
bang | +0.976 |
Neg logit contributions | |
VIDIA | -0.995 |
irtual | -0.988 |
ilers | -0.977 |
endi | -0.930 |
eln | -0.870 |
Token | - |
Token ID | 12 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
threat | +0.788 |
credit | +0.761 |
aligned | +0.758 |
strength | +0.746 |
bang | +0.724 |
Neg logit contributions | |
VIDIA | -0.895 |
ilers | -0.895 |
irtual | -0.888 |
endi | -0.850 |
ually | -0.802 |
Token | enter |
Token ID | 9255 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
ilers | +0.267 |
VIDIA | +0.266 |
irtual | +0.265 |
endi | +0.257 |
ually | +0.246 |
Neg logit contributions | |
threat | -0.114 |
credit | -0.108 |
aligned | -0.107 |
strength | -0.104 |
bang | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
threat | +0.647 |
credit | +0.630 |
aligned | +0.627 |
strength | +0.619 |
bang | +0.606 |
Neg logit contributions | |
VIDIA | -0.522 |
irtual | -0.513 |
ilers | -0.511 |
endi | -0.483 |
LET | -0.448 |
Token | You |
Token ID | 921 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
threat | +0.131 |
credit | +0.127 |
aligned | +0.126 |
strength | +0.125 |
bang | +0.122 |
Neg logit contributions | |
ilers | -0.114 |
VIDIA | -0.113 |
irtual | -0.112 |
endi | -0.108 |
ually | -0.101 |
Token | our |
Token ID | 674 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
threat | +0.049 |
credit | +0.047 |
aligned | +0.047 |
strength | +0.046 |
bang | +0.045 |
Neg logit contributions | |
ilers | -0.046 |
VIDIA | -0.045 |
irtual | -0.044 |
endi | -0.043 |
LET | -0.040 |
Token | daily |
Token ID | 4445 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
threat | +0.891 |
credit | +0.858 |
aligned | +0.853 |
strength | +0.846 |
bang | +0.818 |
Neg logit contributions | |
ilers | -0.968 |
VIDIA | -0.963 |
irtual | -0.953 |
endi | -0.915 |
ually | -0.867 |
Token | newsletter |
Token ID | 13129 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
threat | +0.853 |
credit | +0.822 |
aligned | +0.810 |
strength | +0.806 |
bang | +0.783 |
Neg logit contributions | |
VIDIA | -0.808 |
irtual | -0.793 |
ilers | -0.790 |
endi | -0.746 |
ually | -0.716 |
Token | Upgrade |
Token ID | 24236 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
threat | +2.164 |
credit | +2.112 |
aligned | +2.083 |
strength | +2.073 |
bang | +2.018 |
Neg logit contributions | |
VIDIA | -2.384 |
ilers | -2.332 |
irtual | -2.308 |
endi | -2.234 |
ually | -2.077 |
Token | your |
Token ID | 534 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ilers | +0.066 |
irtual | +0.064 |
VIDIA | +0.064 |
endi | +0.061 |
ually | +0.057 |
Neg logit contributions | |
threat | -0.100 |
aligned | -0.097 |
credit | -0.097 |
strength | -0.096 |
bang | -0.094 |
Token | inbox |
Token ID | 13734 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
threat | +0.353 |
credit | +0.340 |
strength | +0.339 |
aligned | +0.337 |
bang | +0.329 |
Neg logit contributions | |
VIDIA | -0.264 |
ilers | -0.261 |
irtual | -0.256 |
endi | -0.242 |
LET | -0.227 |
Token | and |
Token ID | 290 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
threat | +2.089 |
aligned | +2.010 |
credit | +2.001 |
strength | +1.974 |
bang | +1.909 |
Neg logit contributions | |
VIDIA | -2.605 |
ilers | -2.530 |
irtual | -2.514 |
endi | -2.423 |
LET | -2.286 |
Token | get |
Token ID | 651 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ilers | +0.146 |
irtual | +0.142 |
VIDIA | +0.142 |
endi | +0.136 |
ually | +0.127 |
Neg logit contributions | |
threat | -0.210 |
credit | -0.204 |
aligned | -0.203 |
strength | -0.201 |
bang | -0.196 |
Token | our |
Token ID | 674 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
threat | +0.268 |
credit | +0.259 |
aligned | +0.259 |
strength | +0.256 |
bang | +0.249 |
Neg logit contributions | |
ilers | -0.236 |
VIDIA | -0.233 |
irtual | -0.232 |
endi | -0.223 |
ually | -0.209 |
Token | Daily |
Token ID | 6714 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
threat | +0.794 |
credit | +0.771 |
aligned | +0.765 |
strength | +0.759 |
bang | +0.740 |
Neg logit contributions | |
VIDIA | -0.626 |
ilers | -0.619 |
irtual | -0.611 |
endi | -0.576 |
ually | -0.540 |
Token | Dispatch |
Token ID | 35934 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
threat | +0.325 |
credit | +0.312 |
aligned | +0.310 |
strength | +0.307 |
bang | +0.299 |
Neg logit contributions | |
ilers | -0.359 |
VIDIA | -0.358 |
irtual | -0.354 |
endi | -0.340 |
ually | -0.323 |
Token | me |
Token ID | 502 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
threat | +0.279 |
credit | +0.267 |
aligned | +0.267 |
strength | +0.263 |
bang | +0.256 |
Neg logit contributions | |
ilers | -0.330 |
VIDIA | -0.327 |
irtual | -0.326 |
endi | -0.313 |
ually | -0.297 |
Token | K |
Token ID | 509 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
threat | +0.371 |
credit | +0.355 |
aligned | +0.354 |
strength | +0.350 |
bang | +0.341 |
Neg logit contributions | |
ilers | -0.483 |
VIDIA | -0.478 |
irtual | -0.477 |
endi | -0.458 |
ually | -0.436 |
Token | ā |
Token ID | 10235 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
ilers | +0.372 |
VIDIA | +0.368 |
irtual | +0.366 |
endi | +0.352 |
ually | +0.331 |
Neg logit contributions | |
threat | -0.382 |
credit | -0.367 |
aligned | -0.366 |
strength | -0.362 |
bang | -0.354 |
Token | n |
Token ID | 77 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
threat | +0.634 |
credit | +0.609 |
aligned | +0.606 |
strength | +0.599 |
bang | +0.586 |
Neg logit contributions | |
ilers | -0.726 |
VIDIA | -0.719 |
irtual | -0.716 |
endi | -0.688 |
ually | -0.653 |
Token | ep |
Token ID | 538 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
threat | +0.943 |
credit | +0.908 |
aligned | +0.904 |
strength | +0.892 |
bang | +0.875 |
Neg logit contributions | |
ilers | -1.063 |
VIDIA | -1.055 |
irtual | -1.052 |
endi | -1.005 |
LET | -0.957 |
Token | ō |
Token ID | 13090 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
threat | +1.259 |
credit | +1.212 |
aligned | +1.206 |
strength | +1.195 |
bang | +1.168 |
Neg logit contributions | |
VIDIA | -1.330 |
ilers | -1.325 |
irtual | -1.311 |
endi | -1.248 |
LET | -1.196 |
Token | iki |
Token ID | 5580 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
threat | +1.486 |
credit | +1.422 |
aligned | +1.413 |
strength | +1.398 |
bang | +1.380 |
Neg logit contributions | |
ilers | -1.816 |
VIDIA | -1.805 |
irtual | -1.797 |
endi | -1.712 |
ually | -1.633 |
Token | , |
Token ID | 11 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
threat | +0.417 |
credit | +0.400 |
aligned | +0.399 |
strength | +0.394 |
bang | +0.384 |
Neg logit contributions | |
ilers | -0.483 |
VIDIA | -0.477 |
irtual | -0.476 |
endi | -0.457 |
ually | -0.434 |
Token | ka |
Token ID | 38387 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
threat | +0.162 |
credit | +0.155 |
aligned | +0.155 |
strength | +0.153 |
bang | +0.149 |
Neg logit contributions | |
ilers | -0.183 |
VIDIA | -0.181 |
irtual | -0.180 |
endi | -0.174 |
ually | -0.165 |
Token | m |
Token ID | 285 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
threat | +0.723 |
credit | +0.693 |
aligned | +0.692 |
strength | +0.682 |
bang | +0.667 |
Neg logit contributions | |
ilers | -0.861 |
VIDIA | -0.852 |
irtual | -0.849 |
endi | -0.816 |
LET | -0.773 |
Token | ak |
Token ID | 461 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
threat | +0.595 |
credit | +0.570 |
aligned | +0.568 |
strength | +0.560 |
bang | +0.551 |
Neg logit contributions | |
ilers | -0.706 |
VIDIA | -0.703 |
irtual | -0.700 |
endi | -0.666 |
LET | -0.639 |
Token |
|
Token ID | 198 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
threat | +0.671 |
credit | +0.648 |
aligned | +0.646 |
strength | +0.637 |
bang | +0.621 |
Neg logit contributions | |
ilers | -0.621 |
VIDIA | -0.618 |
irtual | -0.613 |
endi | -0.591 |
ually | -0.551 |
Token |
|
Token ID | 198 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
ilers | +0.147 |
irtual | +0.143 |
VIDIA | +0.143 |
endi | +0.139 |
ually | +0.132 |
Neg logit contributions | |
threat | -0.142 |
credit | -0.137 |
aligned | -0.137 |
strength | -0.135 |
bang | -0.131 |
Token | More |
Token ID | 5167 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
ilers | +0.094 |
VIDIA | +0.093 |
irtual | +0.092 |
endi | +0.089 |
ually | +0.085 |
Neg logit contributions | |
threat | -0.078 |
credit | -0.075 |
aligned | -0.075 |
strength | -0.074 |
bang | -0.072 |
Token | : |
Token ID | 25 |
Feature activation | +3.42e-03 |
Pos logit contributions | |
threat | +0.056 |
aligned | +0.053 |
credit | +0.053 |
strength | +0.052 |
bang | +0.050 |
Neg logit contributions | |
ilers | -0.086 |
VIDIA | -0.085 |
irtual | -0.085 |
endi | -0.082 |
ually | -0.079 |
Token | Law |
Token ID | 3854 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ilers | +0.007 |
VIDIA | +0.007 |
irtual | +0.007 |
endi | +0.007 |
ually | +0.006 |
Neg logit contributions | |
threat | -0.006 |
credit | -0.006 |
aligned | -0.006 |
strength | -0.006 |
bang | -0.005 |
Token | suit |
Token ID | 6063 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ilers | +0.555 |
VIDIA | +0.548 |
irtual | +0.547 |
endi | +0.529 |
ually | +0.505 |
Neg logit contributions | |
threat | -0.454 |
credit | -0.435 |
aligned | -0.435 |
strength | -0.431 |
bang | -0.416 |
Token | : |
Token ID | 25 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
threat | +2.300 |
credit | +2.200 |
aligned | +2.191 |
strength | +2.130 |
rattled | +2.088 |
Neg logit contributions | |
ilers | -2.616 |
VIDIA | -2.607 |
irtual | -2.585 |
endi | -2.476 |
LET | -2.329 |
Token | UC |
Token ID | 14417 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
ilers | +0.099 |
VIDIA | +0.098 |
irtual | +0.098 |
endi | +0.095 |
ually | +0.089 |
Neg logit contributions | |
threat | -0.086 |
credit | -0.083 |
aligned | -0.082 |
strength | -0.081 |
bang | -0.079 |
Token | has |
Token ID | 468 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ilers | +0.177 |
VIDIA | +0.175 |
irtual | +0.174 |
endi | +0.168 |
ually | +0.158 |
Neg logit contributions | |
threat | -0.182 |
credit | -0.176 |
aligned | -0.175 |
strength | -0.173 |
bang | -0.168 |
Token | ' |
Token ID | 705 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
threat | +0.278 |
credit | +0.267 |
aligned | +0.265 |
strength | +0.262 |
bang | +0.255 |
Neg logit contributions | |
ilers | -0.285 |
irtual | -0.283 |
VIDIA | -0.282 |
endi | -0.270 |
LET | -0.254 |
Token | anti |
Token ID | 17096 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
threat | +0.441 |
credit | +0.420 |
aligned | +0.418 |
strength | +0.412 |
bang | +0.398 |
Neg logit contributions | |
ilers | -0.672 |
VIDIA | -0.667 |
irtual | -0.663 |
endi | -0.642 |
ually | -0.612 |
Token | with |
Token ID | 351 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
threat | +0.845 |
credit | +0.807 |
aligned | +0.805 |
strength | +0.797 |
bang | +0.772 |
Neg logit contributions | |
ilers | -0.906 |
VIDIA | -0.893 |
irtual | -0.891 |
endi | -0.856 |
eln | -0.804 |
Token | racism |
Token ID | 10713 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
threat | +0.641 |
credit | +0.615 |
aligned | +0.612 |
strength | +0.606 |
bang | +0.587 |
Neg logit contributions | |
ilers | -0.649 |
VIDIA | -0.643 |
irtual | -0.639 |
endi | -0.615 |
LET | -0.577 |
Token | Fiber |
Token ID | 29933 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
threat | +0.452 |
credit | +0.431 |
aligned | +0.431 |
strength | +0.424 |
bang | +0.413 |
Neg logit contributions | |
ilers | -0.458 |
VIDIA | -0.451 |
irtual | -0.449 |
endi | -0.431 |
eln | -0.406 |
Token | artists |
Token ID | 7912 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
ilers | +0.757 |
VIDIA | +0.748 |
irtual | +0.745 |
endi | +0.721 |
ually | +0.685 |
Neg logit contributions | |
threat | -0.621 |
credit | -0.597 |
aligned | -0.595 |
strength | -0.587 |
bang | -0.569 |
Token | of |
Token ID | 286 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
threat | +0.742 |
credit | +0.715 |
aligned | +0.711 |
strength | +0.702 |
bang | +0.685 |
Neg logit contributions | |
ilers | -0.724 |
VIDIA | -0.721 |
irtual | -0.715 |
endi | -0.687 |
LET | -0.648 |
Token | color |
Token ID | 3124 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
threat | +0.169 |
credit | +0.163 |
aligned | +0.163 |
strength | +0.161 |
bang | +0.157 |
Neg logit contributions | |
ilers | -0.163 |
VIDIA | -0.162 |
irtual | -0.161 |
endi | -0.154 |
LET | -0.145 |
Token | are |
Token ID | 389 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
threat | +1.739 |
credit | +1.672 |
aligned | +1.667 |
strength | +1.640 |
bang | +1.598 |
Neg logit contributions | |
ilers | -1.663 |
VIDIA | -1.662 |
irtual | -1.653 |
endi | -1.588 |
eln | -1.491 |
Token | taking |
Token ID | 2263 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
threat | +0.073 |
credit | +0.070 |
aligned | +0.070 |
strength | +0.069 |
bang | +0.067 |
Neg logit contributions | |
ilers | -0.068 |
VIDIA | -0.068 |
irtual | -0.067 |
endi | -0.064 |
LET | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
threat | +0.408 |
credit | +0.392 |
aligned | +0.389 |
strength | +0.385 |
bang | +0.373 |
Neg logit contributions | |
ilers | -0.488 |
VIDIA | -0.483 |
irtual | -0.481 |
endi | -0.464 |
ually | -0.439 |
Token | Instagram |
Token ID | 10767 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
threat | +0.296 |
credit | +0.286 |
aligned | +0.284 |
strength | +0.280 |
bang | +0.272 |
Neg logit contributions | |
ilers | -0.277 |
VIDIA | -0.276 |
irtual | -0.272 |
endi | -0.263 |
LET | -0.246 |
Token | stories |
Token ID | 3923 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
ilers | +0.099 |
VIDIA | +0.098 |
irtual | +0.098 |
endi | +0.094 |
ually | +0.090 |
Neg logit contributions | |
threat | -0.081 |
credit | -0.077 |
aligned | -0.077 |
strength | -0.076 |
bang | -0.074 |
Token | rational |
Token ID | 9377 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
ilers | +0.043 |
VIDIA | +0.042 |
irtual | +0.042 |
endi | +0.041 |
ually | +0.038 |
Neg logit contributions | |
threat | -0.039 |
credit | -0.037 |
aligned | -0.037 |
strength | -0.037 |
bang | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
threat | +0.077 |
credit | +0.075 |
aligned | +0.074 |
strength | +0.074 |
bang | +0.072 |
Neg logit contributions | |
ilers | -0.077 |
VIDIA | -0.076 |
irtual | -0.076 |
endi | -0.073 |
ually | -0.069 |
Token | It |
Token ID | 632 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
threat | +0.294 |
credit | +0.283 |
aligned | +0.282 |
strength | +0.279 |
bang | +0.271 |
Neg logit contributions | |
ilers | -0.294 |
VIDIA | -0.291 |
irtual | -0.289 |
endi | -0.279 |
ually | -0.263 |
Token | is |
Token ID | 318 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
threat | +0.518 |
credit | +0.496 |
aligned | +0.495 |
strength | +0.488 |
bang | +0.477 |
Neg logit contributions | |
ilers | -0.533 |
VIDIA | -0.530 |
irtual | -0.526 |
endi | -0.505 |
LET | -0.478 |
Token | not |
Token ID | 407 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
ilers | +0.032 |
VIDIA | +0.031 |
irtual | +0.031 |
endi | +0.030 |
LET | +0.028 |
Neg logit contributions | |
threat | -0.034 |
credit | -0.033 |
aligned | -0.033 |
strength | -0.033 |
bang | -0.032 |
Token | asking |
Token ID | 4737 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
threat | +0.064 |
credit | +0.061 |
aligned | +0.061 |
strength | +0.060 |
bang | +0.059 |
Neg logit contributions | |
ilers | -0.064 |
VIDIA | -0.063 |
irtual | -0.063 |
endi | -0.061 |
ually | -0.057 |
Token | people |
Token ID | 661 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
threat | +2.086 |
aligned | +2.002 |
strength | +1.998 |
credit | +1.995 |
bang | +1.922 |
Neg logit contributions | |
VIDIA | -2.177 |
irtual | -2.175 |
ilers | -2.170 |
endi | -2.060 |
eln | -1.936 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ilers | +0.134 |
VIDIA | +0.132 |
irtual | +0.132 |
endi | +0.128 |
ually | +0.122 |
Neg logit contributions | |
threat | -0.106 |
credit | -0.102 |
aligned | -0.102 |
strength | -0.100 |
bang | -0.097 |
Token | think |
Token ID | 892 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
threat | +0.253 |
credit | +0.243 |
aligned | +0.242 |
strength | +0.240 |
bang | +0.235 |
Neg logit contributions | |
VIDIA | -0.248 |
ilers | -0.247 |
irtual | -0.246 |
endi | -0.237 |
LET | -0.223 |
Token | , |
Token ID | 11 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
ilers | +0.175 |
VIDIA | +0.173 |
irtual | +0.173 |
endi | +0.167 |
ually | +0.158 |
Neg logit contributions | |
threat | -0.166 |
credit | -0.160 |
aligned | -0.160 |
strength | -0.158 |
bang | -0.153 |
Token | question |
Token ID | 1808 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
threat | +0.141 |
credit | +0.136 |
aligned | +0.136 |
strength | +0.134 |
bang | +0.131 |
Neg logit contributions | |
ilers | -0.133 |
VIDIA | -0.132 |
irtual | -0.131 |
endi | -0.126 |
ually | -0.119 |