Token | holes |
Token ID | 28439 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
abase | +0.136 |
rador | +0.101 |
MB | +0.099 |
CAD | +0.091 |
ielding | +0.089 |
Neg logit contributions | |
moons | -0.187 |
horm | -0.182 |
nerv | -0.177 |
mosqu | -0.172 |
behavi | -0.169 |
Token | in |
Token ID | 287 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
moons | +0.175 |
horm | +0.168 |
nerv | +0.163 |
mosqu | +0.156 |
behavi | +0.153 |
Neg logit contributions | |
abase | -0.206 |
rador | -0.165 |
MB | -0.162 |
CAD | -0.153 |
ielding | -0.151 |
Token | American |
Token ID | 1605 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
moons | +0.110 |
horm | +0.106 |
nerv | +0.102 |
mosqu | +0.097 |
behavi | +0.096 |
Neg logit contributions | |
abase | -0.140 |
rador | -0.112 |
MB | -0.109 |
CAD | -0.104 |
ielding | -0.104 |
Token | politics |
Token ID | 4819 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
abase | +0.171 |
MB | +0.141 |
rador | +0.141 |
CAD | +0.133 |
ielding | +0.133 |
Neg logit contributions | |
moons | -0.099 |
horm | -0.098 |
nerv | -0.091 |
mosqu | -0.090 |
behavi | -0.087 |
Token | ' |
Token ID | 6 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
abase | +0.346 |
rador | +0.275 |
MB | +0.272 |
CAD | +0.256 |
ielding | +0.253 |
Neg logit contributions | |
moons | -0.301 |
horm | -0.292 |
nerv | -0.281 |
mosqu | -0.272 |
behavi | -0.266 |
Token | MORE |
Token ID | 12011 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
moons | +0.627 |
horm | +0.608 |
nerv | +0.594 |
mosqu | +0.565 |
seiz | +0.552 |
Neg logit contributions | |
abase | -0.568 |
rador | -0.438 |
MB | -0.403 |
xes | -0.376 |
CAD | -0.375 |
Token | as |
Token ID | 355 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
abase | +3.877 |
MB | +3.215 |
rador | +3.145 |
CAD | +3.004 |
ielding | +2.992 |
Neg logit contributions | |
moons | -2.873 |
horm | -2.873 |
mosqu | -2.670 |
nerv | -2.657 |
behavi | -2.584 |
Token | a |
Token ID | 257 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
abase | +0.629 |
rador | +0.506 |
MB | +0.504 |
CAD | +0.474 |
ielding | +0.470 |
Neg logit contributions | |
moons | -0.493 |
horm | -0.479 |
nerv | -0.459 |
mosqu | -0.447 |
behavi | -0.434 |
Token | 68 |
Token ID | 8257 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
abase | +1.117 |
rador | +0.911 |
MB | +0.911 |
CAD | +0.861 |
ielding | +0.851 |
Neg logit contributions | |
moons | -0.768 |
horm | -0.747 |
nerv | -0.711 |
mosqu | -0.696 |
behavi | -0.676 |
Token | - |
Token ID | 12 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
abase | +0.457 |
rador | +0.349 |
MB | +0.345 |
CAD | +0.319 |
ielding | +0.316 |
Neg logit contributions | |
moons | -0.533 |
horm | -0.519 |
nerv | -0.502 |
mosqu | -0.489 |
behavi | -0.478 |
Token | year |
Token ID | 1941 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
abase | +0.378 |
rador | +0.294 |
MB | +0.291 |
CAD | +0.271 |
ielding | +0.268 |
Neg logit contributions | |
moons | -0.391 |
horm | -0.381 |
nerv | -0.368 |
mosqu | -0.359 |
behavi | -0.351 |
Token | ice |
Token ID | 501 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
moons | +0.790 |
horm | +0.783 |
mosqu | +0.752 |
nerv | +0.748 |
behavi | +0.729 |
Neg logit contributions | |
abase | -0.604 |
MB | -0.456 |
rador | -0.451 |
ielding | -0.413 |
CAD | -0.410 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
moons | +0.125 |
horm | +0.120 |
nerv | +0.115 |
mosqu | +0.111 |
behavi | +0.108 |
Neg logit contributions | |
abase | -0.180 |
rador | -0.147 |
MB | -0.146 |
CAD | -0.138 |
ielding | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
abase | +0.184 |
rador | +0.147 |
MB | +0.146 |
CAD | +0.137 |
ielding | +0.135 |
Neg logit contributions | |
moons | -0.154 |
horm | -0.149 |
nerv | -0.143 |
mosqu | -0.139 |
behavi | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
moons | +0.251 |
horm | +0.242 |
nerv | +0.234 |
mosqu | +0.224 |
behavi | +0.219 |
Neg logit contributions | |
abase | -0.303 |
rador | -0.242 |
MB | -0.239 |
CAD | -0.225 |
ielding | -0.223 |
Token | V |
Token ID | 53 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
moons | +0.252 |
horm | +0.243 |
nerv | +0.234 |
mosqu | +0.225 |
behavi | +0.219 |
Neg logit contributions | |
abase | -0.308 |
rador | -0.248 |
MB | -0.244 |
CAD | -0.230 |
ielding | -0.228 |
Token | ox |
Token ID | 1140 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
abase | +0.095 |
rador | +0.075 |
MB | +0.074 |
CAD | +0.070 |
ielding | +0.069 |
Neg logit contributions | |
moons | -0.088 |
horm | -0.085 |
nerv | -0.082 |
mosqu | -0.080 |
behavi | -0.078 |
Token | can |
Token ID | 460 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
abase | +3.728 |
MB | +2.986 |
rador | +2.974 |
CAD | +2.798 |
ielding | +2.752 |
Neg logit contributions | |
moons | -2.960 |
horm | -2.922 |
nerv | -2.752 |
mosqu | -2.719 |
behavi | -2.657 |
Token | beat |
Token ID | 4405 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
abase | +0.223 |
rador | +0.181 |
MB | +0.179 |
CAD | +0.169 |
ielding | +0.167 |
Neg logit contributions | |
moons | -0.167 |
horm | -0.162 |
nerv | -0.155 |
mosqu | -0.150 |
behavi | -0.146 |
Token | Flip |
Token ID | 29583 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
abase | +0.780 |
rador | +0.625 |
MB | +0.624 |
CAD | +0.587 |
ielding | +0.579 |
Neg logit contributions | |
moons | -0.621 |
horm | -0.603 |
nerv | -0.578 |
mosqu | -0.561 |
behavi | -0.547 |
Token | S |
Token ID | 50 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
moons | +0.526 |
horm | +0.504 |
nerv | +0.491 |
mosqu | +0.469 |
behavi | +0.457 |
Neg logit contributions | |
abase | -0.620 |
rador | -0.496 |
MB | -0.485 |
ielding | -0.456 |
CAD | -0.455 |
Token | id |
Token ID | 312 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
moons | +0.416 |
horm | +0.397 |
nerv | +0.390 |
mosqu | +0.371 |
behavi | +0.364 |
Neg logit contributions | |
abase | -0.357 |
rador | -0.277 |
MB | -0.271 |
CAD | -0.251 |
ielding | -0.249 |
Token | than |
Token ID | 621 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
moons | +1.859 |
horm | +1.778 |
nerv | +1.738 |
mosqu | +1.669 |
behavi | +1.642 |
Neg logit contributions | |
abase | -1.789 |
rador | -1.375 |
MB | -1.321 |
CAD | -1.241 |
ielding | -1.236 |
Token | 10 |
Token ID | 838 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
moons | +0.363 |
horm | +0.353 |
nerv | +0.342 |
mosqu | +0.332 |
behavi | +0.324 |
Neg logit contributions | |
abase | -0.370 |
rador | -0.291 |
MB | -0.290 |
CAD | -0.270 |
ielding | -0.267 |
Token | years |
Token ID | 812 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
moons | +0.758 |
horm | +0.718 |
nerv | +0.700 |
mosqu | +0.672 |
behavi | +0.662 |
Neg logit contributions | |
abase | -0.793 |
rador | -0.637 |
MB | -0.563 |
CAD | -0.553 |
ielding | -0.538 |
Token | in |
Token ID | 287 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
moons | +0.533 |
horm | +0.516 |
nerv | +0.495 |
mosqu | +0.479 |
behavi | +0.464 |
Neg logit contributions | |
abase | -0.716 |
rador | -0.580 |
MB | -0.577 |
CAD | -0.543 |
ielding | -0.538 |
Token | prison |
Token ID | 3770 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
moons | +0.354 |
horm | +0.349 |
nerv | +0.335 |
mosqu | +0.325 |
behavi | +0.318 |
Neg logit contributions | |
abase | -0.368 |
MB | -0.297 |
rador | -0.292 |
CAD | -0.270 |
ielding | -0.264 |
Token | MORE |
Token ID | 12011 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
abase | +0.533 |
MB | +0.422 |
rador | +0.418 |
CAD | +0.392 |
ielding | +0.387 |
Neg logit contributions | |
moons | -0.506 |
horm | -0.494 |
nerv | -0.474 |
mosqu | -0.465 |
behavi | -0.455 |
Token | and |
Token ID | 290 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
abase | +3.483 |
MB | +2.909 |
rador | +2.841 |
ielding | +2.704 |
CAD | +2.687 |
Neg logit contributions | |
horm | -2.695 |
moons | -2.668 |
mosqu | -2.516 |
nerv | -2.497 |
behavi | -2.438 |
Token | tick |
Token ID | 4378 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
abase | +0.436 |
rador | +0.353 |
MB | +0.352 |
CAD | +0.331 |
ielding | +0.329 |
Neg logit contributions | |
moons | -0.323 |
horm | -0.314 |
nerv | -0.300 |
mosqu | -0.291 |
behavi | -0.284 |
Token | ed |
Token ID | 276 |
Feature activation | -9.98e-02 |
Pos logit contributions | |
abase | +1.130 |
rador | +0.800 |
MB | +0.793 |
CAD | +0.709 |
ielding | +0.699 |
Neg logit contributions | |
moons | -1.917 |
horm | -1.876 |
nerv | -1.826 |
mosqu | -1.788 |
behavi | -1.753 |
Token | through |
Token ID | 832 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
moons | +0.059 |
horm | +0.056 |
nerv | +0.054 |
mosqu | +0.051 |
behavi | +0.049 |
Neg logit contributions | |
abase | -0.106 |
rador | -0.088 |
MB | -0.087 |
CAD | -0.083 |
ielding | -0.082 |
Token | her |
Token ID | 607 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
abase | +0.623 |
rador | +0.501 |
MB | +0.501 |
CAD | +0.469 |
ielding | +0.465 |
Neg logit contributions | |
moons | -0.501 |
horm | -0.487 |
nerv | -0.467 |
mosqu | -0.456 |
behavi | -0.444 |
Token | holes |
Token ID | 28439 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
abase | +0.119 |
rador | +0.088 |
MB | +0.086 |
CAD | +0.079 |
ielding | +0.078 |
Neg logit contributions | |
moons | -0.169 |
horm | -0.164 |
nerv | -0.160 |
mosqu | -0.156 |
behavi | -0.153 |
Token | in |
Token ID | 287 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
moons | +0.208 |
horm | +0.201 |
nerv | +0.194 |
mosqu | +0.187 |
behavi | +0.182 |
Neg logit contributions | |
abase | -0.241 |
rador | -0.192 |
MB | -0.190 |
CAD | -0.178 |
ielding | -0.177 |
Token | American |
Token ID | 1605 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
moons | +0.106 |
horm | +0.102 |
nerv | +0.099 |
mosqu | +0.094 |
behavi | +0.093 |
Neg logit contributions | |
abase | -0.134 |
rador | -0.107 |
MB | -0.104 |
CAD | -0.099 |
ielding | -0.099 |
Token | politics |
Token ID | 4819 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
abase | +0.705 |
MB | +0.584 |
rador | +0.582 |
CAD | +0.550 |
ielding | +0.547 |
Neg logit contributions | |
moons | -0.399 |
horm | -0.394 |
nerv | -0.367 |
mosqu | -0.364 |
behavi | -0.349 |
Token | ' |
Token ID | 6 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
abase | +0.368 |
rador | +0.293 |
MB | +0.290 |
CAD | +0.272 |
ielding | +0.269 |
Neg logit contributions | |
moons | -0.320 |
horm | -0.310 |
nerv | -0.299 |
mosqu | -0.289 |
behavi | -0.282 |
Token | MORE |
Token ID | 12011 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
moons | +0.514 |
horm | +0.499 |
nerv | +0.486 |
mosqu | +0.464 |
seiz | +0.452 |
Neg logit contributions | |
abase | -0.462 |
rador | -0.354 |
MB | -0.324 |
xes | -0.304 |
CAD | -0.303 |
Token | completed |
Token ID | 5668 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
abase | +3.383 |
MB | +2.749 |
rador | +2.673 |
CAD | +2.533 |
ielding | +2.503 |
Neg logit contributions | |
moons | -2.842 |
horm | -2.830 |
mosqu | -2.689 |
nerv | -2.655 |
behavi | -2.617 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
abase | +0.228 |
rador | +0.183 |
MB | +0.181 |
CAD | +0.170 |
ielding | +0.169 |
Neg logit contributions | |
moons | -0.187 |
horm | -0.181 |
nerv | -0.174 |
mosqu | -0.168 |
behavi | -0.164 |
Token | swing |
Token ID | 9628 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
abase | +1.034 |
rador | +0.835 |
MB | +0.833 |
CAD | +0.784 |
ielding | +0.773 |
Neg logit contributions | |
moons | -0.792 |
horm | -0.772 |
nerv | -0.736 |
mosqu | -0.720 |
behavi | -0.699 |
Token | through |
Token ID | 832 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
abase | +0.781 |
rador | +0.631 |
MB | +0.626 |
CAD | +0.590 |
ielding | +0.585 |
Neg logit contributions | |
moons | -0.587 |
horm | -0.567 |
nerv | -0.544 |
mosqu | -0.526 |
behavi | -0.511 |
Token | North |
Token ID | 2258 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
abase | +0.451 |
rador | +0.362 |
MB | +0.359 |
CAD | +0.338 |
ielding | +0.335 |
Neg logit contributions | |
moons | -0.364 |
horm | -0.352 |
nerv | -0.339 |
mosqu | -0.328 |
behavi | -0.319 |
Token | t |
Token ID | 83 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
abase | +0.032 |
rador | +0.025 |
MB | +0.025 |
CAD | +0.023 |
ielding | +0.023 |
Neg logit contributions | |
moons | -0.029 |
horm | -0.028 |
nerv | -0.027 |
mosqu | -0.026 |
behavi | -0.026 |
Token | weet |
Token ID | 7277 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
moons | +0.163 |
horm | +0.158 |
nerv | +0.152 |
mosqu | +0.148 |
behavi | +0.144 |
Neg logit contributions | |
abase | -0.186 |
rador | -0.148 |
MB | -0.146 |
CAD | -0.137 |
ielding | -0.136 |
Token | / |
Token ID | 14 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
abase | +0.716 |
rador | +0.554 |
MB | +0.548 |
CAD | +0.509 |
ielding | +0.504 |
Neg logit contributions | |
moons | -0.769 |
horm | -0.748 |
nerv | -0.724 |
mosqu | -0.703 |
behavi | -0.687 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
moons | +0.664 |
horm | +0.641 |
nerv | +0.618 |
mosqu | +0.596 |
behavi | +0.581 |
Neg logit contributions | |
abase | -0.853 |
rador | -0.686 |
MB | -0.678 |
CAD | -0.639 |
ielding | -0.634 |
Token | Story |
Token ID | 11605 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
moons | +0.147 |
horm | +0.142 |
nerv | +0.137 |
mosqu | +0.132 |
behavi | +0.128 |
Neg logit contributions | |
abase | -0.178 |
rador | -0.142 |
MB | -0.141 |
CAD | -0.132 |
ielding | -0.131 |
Token | highlights |
Token ID | 11330 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
abase | +0.380 |
rador | +0.306 |
MB | +0.302 |
CAD | +0.285 |
ielding | +0.283 |
Neg logit contributions | |
moons | -0.297 |
horm | -0.287 |
nerv | -0.276 |
mosqu | -0.266 |
behavi | -0.259 |
Token | Secretary |
Token ID | 4986 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
abase | +3.264 |
MB | +2.678 |
rador | +2.584 |
CAD | +2.491 |
ielding | +2.404 |
Neg logit contributions | |
moons | -2.891 |
horm | -2.840 |
nerv | -2.708 |
mosqu | -2.697 |
behavi | -2.640 |
Token | of |
Token ID | 286 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
abase | +0.081 |
rador | +0.065 |
MB | +0.064 |
CAD | +0.060 |
ielding | +0.059 |
Neg logit contributions | |
moons | -0.072 |
horm | -0.070 |
nerv | -0.067 |
mosqu | -0.065 |
behavi | -0.063 |
Token | Defense |
Token ID | 5947 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
abase | +0.282 |
rador | +0.229 |
MB | +0.227 |
CAD | +0.214 |
ielding | +0.212 |
Neg logit contributions | |
moons | -0.206 |
horm | -0.199 |
nerv | -0.191 |
mosqu | -0.184 |
behavi | -0.179 |
Token | Chuck |
Token ID | 14663 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
moons | +0.021 |
horm | +0.021 |
nerv | +0.020 |
mosqu | +0.020 |
behavi | +0.019 |
Neg logit contributions | |
abase | -0.019 |
MB | -0.015 |
rador | -0.015 |
CAD | -0.014 |
ielding | -0.014 |
Token | Hag |
Token ID | 21375 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
abase | +0.027 |
MB | +0.018 |
rador | +0.018 |
CAD | +0.016 |
ielding | +0.016 |
Neg logit contributions | |
moons | -0.053 |
horm | -0.052 |
nerv | -0.050 |
mosqu | -0.050 |
behavi | -0.049 |
Token | vote |
Token ID | 3015 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
moons | +0.172 |
horm | +0.166 |
nerv | +0.159 |
mosqu | +0.155 |
behavi | +0.150 |
Neg logit contributions | |
abase | -0.251 |
rador | -0.205 |
MB | -0.205 |
CAD | -0.194 |
ielding | -0.191 |
Token | accordingly |
Token ID | 16062 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
abase | +0.515 |
MB | +0.410 |
rador | +0.410 |
CAD | +0.384 |
ielding | +0.379 |
Neg logit contributions | |
moons | -0.438 |
horm | -0.425 |
nerv | -0.409 |
mosqu | -0.398 |
behavi | -0.387 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
abase | +0.163 |
MB | +0.133 |
rador | +0.132 |
CAD | +0.125 |
ielding | +0.124 |
Neg logit contributions | |
moons | -0.111 |
horm | -0.107 |
nerv | -0.102 |
mosqu | -0.100 |
behavi | -0.096 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
abase | +0.031 |
rador | +0.025 |
MB | +0.025 |
CAD | +0.024 |
ielding | +0.023 |
Neg logit contributions | |
moons | -0.024 |
horm | -0.024 |
nerv | -0.023 |
mosqu | -0.022 |
behavi | -0.021 |
Token | Story |
Token ID | 11605 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
moons | +0.133 |
horm | +0.129 |
nerv | +0.124 |
mosqu | +0.119 |
behavi | +0.116 |
Neg logit contributions | |
abase | -0.161 |
rador | -0.129 |
MB | -0.128 |
CAD | -0.120 |
ielding | -0.119 |
Token | highlights |
Token ID | 11330 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
abase | +0.482 |
rador | +0.388 |
MB | +0.383 |
CAD | +0.361 |
ielding | +0.358 |
Neg logit contributions | |
moons | -0.379 |
horm | -0.366 |
nerv | -0.352 |
mosqu | -0.340 |
behavi | -0.331 |
Token | Police |
Token ID | 4287 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
abase | +3.207 |
MB | +2.626 |
rador | +2.541 |
CAD | +2.445 |
ielding | +2.360 |
Neg logit contributions | |
moons | -2.843 |
horm | -2.792 |
nerv | -2.664 |
mosqu | -2.651 |
behavi | -2.594 |
Token | chief |
Token ID | 4039 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
abase | +0.319 |
rador | +0.257 |
MB | +0.256 |
CAD | +0.241 |
ielding | +0.239 |
Neg logit contributions | |
moons | -0.248 |
horm | -0.241 |
nerv | -0.231 |
mosqu | -0.224 |
behavi | -0.218 |
Token | vows |
Token ID | 36605 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
moons | +0.367 |
horm | +0.353 |
nerv | +0.338 |
mosqu | +0.324 |
behavi | +0.314 |
Neg logit contributions | |
abase | -0.575 |
rador | -0.472 |
MB | -0.467 |
CAD | -0.443 |
ielding | -0.440 |
Token | wanted |
Token ID | 2227 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
moons | +1.049 |
horm | +0.999 |
nerv | +0.964 |
mosqu | +0.922 |
behavi | +0.897 |
Neg logit contributions | |
abase | -1.416 |
rador | -1.154 |
MB | -1.120 |
ielding | -1.065 |
CAD | -1.060 |
Token | suspect |
Token ID | 4099 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
abase | +0.344 |
rador | +0.276 |
MB | +0.274 |
CAD | +0.258 |
ielding | +0.255 |
Neg logit contributions | |
moons | -0.280 |
horm | -0.272 |
nerv | -0.261 |
mosqu | -0.254 |
behavi | -0.246 |
Token | holes |
Token ID | 28439 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
abase | +0.067 |
rador | +0.050 |
MB | +0.049 |
CAD | +0.045 |
ielding | +0.044 |
Neg logit contributions | |
moons | -0.092 |
horm | -0.090 |
nerv | -0.087 |
mosqu | -0.085 |
behavi | -0.083 |
Token | in |
Token ID | 287 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
moons | +0.221 |
horm | +0.213 |
nerv | +0.206 |
mosqu | +0.198 |
behavi | +0.193 |
Neg logit contributions | |
abase | -0.260 |
rador | -0.208 |
MB | -0.205 |
CAD | -0.193 |
ielding | -0.191 |
Token | American |
Token ID | 1605 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
moons | +0.151 |
horm | +0.145 |
nerv | +0.140 |
mosqu | +0.134 |
behavi | +0.131 |
Neg logit contributions | |
abase | -0.189 |
rador | -0.151 |
MB | -0.147 |
CAD | -0.140 |
ielding | -0.140 |
Token | politics |
Token ID | 4819 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
abase | +0.427 |
MB | +0.352 |
rador | +0.351 |
CAD | +0.331 |
ielding | +0.329 |
Neg logit contributions | |
moons | -0.257 |
horm | -0.255 |
nerv | -0.237 |
mosqu | -0.236 |
behavi | -0.227 |
Token | ' |
Token ID | 6 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
abase | +0.333 |
rador | +0.265 |
MB | +0.262 |
CAD | +0.246 |
ielding | +0.244 |
Neg logit contributions | |
moons | -0.287 |
horm | -0.278 |
nerv | -0.268 |
mosqu | -0.259 |
behavi | -0.252 |
Token | MORE |
Token ID | 12011 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
moons | +0.590 |
horm | +0.575 |
nerv | +0.560 |
mosqu | +0.529 |
seiz | +0.518 |
Neg logit contributions | |
abase | -0.555 |
rador | -0.429 |
MB | -0.390 |
xes | -0.369 |
CAD | -0.363 |
Token | , |
Token ID | 11 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
abase | +3.085 |
MB | +2.498 |
rador | +2.471 |
CAD | +2.307 |
ielding | +2.287 |
Neg logit contributions | |
moons | -2.819 |
horm | -2.807 |
nerv | -2.666 |
mosqu | -2.623 |
behavi | -2.556 |
Token | told |
Token ID | 1297 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
abase | +0.445 |
MB | +0.357 |
rador | +0.356 |
CAD | +0.334 |
ielding | +0.331 |
Neg logit contributions | |
moons | -0.357 |
horm | -0.349 |
nerv | -0.333 |
mosqu | -0.325 |
behavi | -0.316 |
Token | 77 |
Token ID | 8541 |
Feature activation | -9.95e-02 |
Pos logit contributions | |
abase | +0.818 |
MB | +0.650 |
rador | +0.649 |
CAD | +0.606 |
ielding | +0.600 |
Neg logit contributions | |
moons | -0.730 |
horm | -0.711 |
nerv | -0.684 |
mosqu | -0.664 |
behavi | -0.651 |
Token | WA |
Token ID | 15543 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
moons | +0.076 |
horm | +0.073 |
nerv | +0.071 |
mosqu | +0.068 |
behavi | +0.067 |
Neg logit contributions | |
abase | -0.088 |
rador | -0.070 |
MB | -0.069 |
CAD | -0.065 |
ielding | -0.065 |
Token | BC |
Token ID | 2749 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
abase | +0.595 |
rador | +0.477 |
MB | +0.476 |
CAD | +0.446 |
ielding | +0.441 |
Neg logit contributions | |
moons | -0.494 |
horm | -0.481 |
nerv | -0.462 |
mosqu | -0.446 |
behavi | -0.437 |
Token | great |
Token ID | 1049 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
abase | +0.155 |
rador | +0.123 |
MB | +0.122 |
CAD | +0.115 |
ielding | +0.114 |
Neg logit contributions | |
moons | -0.134 |
horm | -0.130 |
nerv | -0.125 |
mosqu | -0.122 |
behavi | -0.119 |
Token | mechanical |
Token ID | 12370 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
moons | +0.393 |
horm | +0.379 |
nerv | +0.366 |
mosqu | +0.350 |
behavi | +0.343 |
Neg logit contributions | |
abase | -0.486 |
rador | -0.390 |
MB | -0.383 |
CAD | -0.360 |
ielding | -0.359 |
Token | stress |
Token ID | 5503 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
abase | +0.001 |
rador | +0.001 |
MB | +0.001 |
CAD | +0.001 |
ielding | +0.001 |
Neg logit contributions | |
moons | -0.001 |
horm | -0.001 |
nerv | -0.001 |
mosqu | -0.001 |
behavi | -0.001 |
Token | ( |
Token ID | 357 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
abase | +0.821 |
rador | +0.669 |
MB | +0.668 |
CAD | +0.631 |
ielding | +0.625 |
Neg logit contributions | |
moons | -0.590 |
horm | -0.571 |
nerv | -0.545 |
mosqu | -0.535 |
behavi | -0.516 |
Token | bending |
Token ID | 49667 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
moons | +0.357 |
horm | +0.346 |
nerv | +0.333 |
mosqu | +0.323 |
behavi | +0.315 |
Neg logit contributions | |
abase | -0.394 |
rador | -0.312 |
MB | -0.309 |
CAD | -0.289 |
ielding | -0.287 |
Token | open |
Token ID | 1280 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
moons | +0.495 |
horm | +0.477 |
nerv | +0.462 |
mosqu | +0.441 |
behavi | +0.430 |
Neg logit contributions | |
abase | -0.601 |
rador | -0.482 |
MB | -0.475 |
CAD | -0.446 |
ielding | -0.444 |
Token | and |
Token ID | 290 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
abase | +3.084 |
MB | +2.459 |
rador | +2.453 |
CAD | +2.307 |
ielding | +2.261 |
Neg logit contributions | |
moons | -2.697 |
horm | -2.641 |
nerv | -2.515 |
mosqu | -2.474 |
behavi | -2.422 |
Token | slamming |
Token ID | 39603 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
abase | +0.167 |
rador | +0.134 |
MB | +0.132 |
CAD | +0.124 |
ielding | +0.123 |
Neg logit contributions | |
moons | -0.139 |
horm | -0.135 |
nerv | -0.130 |
mosqu | -0.125 |
behavi | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
moons | +0.156 |
horm | +0.150 |
nerv | +0.145 |
mosqu | +0.139 |
behavi | +0.135 |
Neg logit contributions | |
abase | -0.196 |
rador | -0.158 |
MB | -0.156 |
CAD | -0.146 |
ielding | -0.146 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
abase | +0.136 |
rador | +0.109 |
MB | +0.107 |
CAD | +0.101 |
ielding | +0.101 |
Neg logit contributions | |
moons | -0.109 |
horm | -0.105 |
nerv | -0.101 |
mosqu | -0.095 |
behavi | -0.093 |
Token | shut |
Token ID | 49625 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
abase | +0.278 |
rador | +0.220 |
MB | +0.219 |
CAD | +0.204 |
ielding | +0.203 |
Neg logit contributions | |
moons | -0.251 |
horm | -0.243 |
nerv | -0.234 |
mosqu | -0.225 |
behavi | -0.219 |
Token | forehead |
Token ID | 22645 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
abase | +0.227 |
rador | +0.183 |
MB | +0.181 |
CAD | +0.171 |
ielding | +0.169 |
Neg logit contributions | |
moons | -0.174 |
horm | -0.168 |
nerv | -0.161 |
mosqu | -0.156 |
behavi | -0.152 |
Token | a |
Token ID | 257 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
moons | +0.271 |
horm | +0.263 |
nerv | +0.253 |
mosqu | +0.245 |
behavi | +0.239 |
Neg logit contributions | |
abase | -0.323 |
rador | -0.258 |
MB | -0.256 |
CAD | -0.240 |
ielding | -0.238 |
Token | butt |
Token ID | 8530 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
abase | +0.887 |
rador | +0.719 |
MB | +0.717 |
CAD | +0.676 |
ielding | +0.665 |
Neg logit contributions | |
moons | -0.654 |
horm | -0.635 |
nerv | -0.607 |
mosqu | -0.593 |
behavi | -0.576 |
Token | - |
Token ID | 12 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
moons | +0.550 |
horm | +0.533 |
nerv | +0.509 |
mosqu | +0.495 |
behavi | +0.481 |
Neg logit contributions | |
abase | -0.765 |
rador | -0.621 |
MB | -0.616 |
CAD | -0.581 |
ielding | -0.575 |
Token | cr |
Token ID | 6098 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
moons | +0.108 |
horm | +0.105 |
nerv | +0.101 |
mosqu | +0.098 |
behavi | +0.096 |
Neg logit contributions | |
abase | -0.125 |
rador | -0.100 |
MB | -0.099 |
CAD | -0.093 |
ielding | -0.092 |
Token | ack |
Token ID | 441 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
abase | +1.012 |
rador | +0.744 |
MB | +0.734 |
CAD | +0.669 |
ielding | +0.662 |
Neg logit contributions | |
moons | -1.438 |
horm | -1.405 |
nerv | -1.364 |
mosqu | -1.332 |
behavi | -1.308 |
Token | with |
Token ID | 351 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
abase | +3.282 |
MB | +2.693 |
rador | +2.667 |
CAD | +2.505 |
ielding | +2.444 |
Neg logit contributions | |
moons | -2.430 |
horm | -2.420 |
mosqu | -2.266 |
nerv | -2.248 |
behavi | -2.160 |
Token | an |
Token ID | 281 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
abase | +0.491 |
rador | +0.393 |
MB | +0.390 |
CAD | +0.366 |
ielding | +0.362 |
Neg logit contributions | |
moons | -0.410 |
horm | -0.397 |
nerv | -0.382 |
mosqu | -0.370 |
behavi | -0.361 |
Token | ax |
Token ID | 7877 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
abase | +1.016 |
MB | +0.812 |
rador | +0.809 |
CAD | +0.758 |
ielding | +0.749 |
Neg logit contributions | |
moons | -0.845 |
horm | -0.820 |
nerv | -0.786 |
mosqu | -0.765 |
behavi | -0.745 |
Token | : |
Token ID | 25 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
abase | +0.298 |
rador | +0.242 |
MB | +0.240 |
CAD | +0.226 |
ielding | +0.225 |
Neg logit contributions | |
moons | -0.217 |
horm | -0.210 |
nerv | -0.200 |
mosqu | -0.195 |
behavi | -0.189 |
Token | a |
Token ID | 257 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
moons | +0.379 |
horm | +0.366 |
nerv | +0.353 |
mosqu | +0.341 |
behavi | +0.332 |
Neg logit contributions | |
abase | -0.465 |
rador | -0.373 |
MB | -0.368 |
CAD | -0.347 |
ielding | -0.344 |
Token | this |
Token ID | 428 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
abase | +0.186 |
rador | +0.148 |
MB | +0.147 |
CAD | +0.138 |
ielding | +0.136 |
Neg logit contributions | |
moons | -0.163 |
horm | -0.158 |
nerv | -0.152 |
mosqu | -0.148 |
behavi | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
abase | +0.058 |
rador | +0.047 |
MB | +0.047 |
CAD | +0.044 |
ielding | +0.044 |
Neg logit contributions | |
moons | -0.042 |
horm | -0.041 |
nerv | -0.039 |
mosqu | -0.038 |
behavi | -0.036 |
Token | This |
Token ID | 770 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
moons | +0.390 |
horm | +0.378 |
nerv | +0.365 |
mosqu | +0.352 |
behavi | +0.345 |
Neg logit contributions | |
abase | -0.408 |
rador | -0.321 |
MB | -0.316 |
CAD | -0.296 |
ielding | -0.295 |
Token | [ |
Token ID | 685 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
abase | +0.056 |
rador | +0.045 |
MB | +0.044 |
CAD | +0.042 |
ielding | +0.041 |
Neg logit contributions | |
moons | -0.047 |
horm | -0.046 |
nerv | -0.044 |
mosqu | -0.042 |
behavi | -0.041 |
Token | ep |
Token ID | 538 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
moons | +0.742 |
horm | +0.718 |
nerv | +0.692 |
mosqu | +0.670 |
behavi | +0.652 |
Neg logit contributions | |
abase | -0.812 |
rador | -0.644 |
MB | -0.635 |
CAD | -0.596 |
ielding | -0.595 |
Token | id |
Token ID | 312 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
moons | +0.295 |
horm | +0.288 |
nerv | +0.280 |
mosqu | +0.271 |
behavi | +0.264 |
Neg logit contributions | |
abase | -0.245 |
rador | -0.185 |
MB | -0.182 |
CAD | -0.169 |
ielding | -0.167 |
Token | emic |
Token ID | 5314 |
Feature activation | +8.96e-03 |
Pos logit contributions | |
abase | +2.176 |
MB | +1.550 |
rador | +1.541 |
CAD | +1.386 |
ielding | +1.364 |
Neg logit contributions | |
moons | -3.607 |
horm | -3.541 |
nerv | -3.421 |
mosqu | -3.342 |
behavi | -3.316 |
Token | ] |
Token ID | 60 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
abase | +0.007 |
rador | +0.005 |
MB | +0.005 |
CAD | +0.005 |
ielding | +0.005 |
Neg logit contributions | |
moons | -0.008 |
horm | -0.008 |
nerv | -0.008 |
mosqu | -0.007 |
behavi | -0.007 |
Token | is |
Token ID | 318 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
abase | +0.258 |
rador | +0.205 |
MB | +0.203 |
CAD | +0.191 |
ielding | +0.189 |
Neg logit contributions | |
moons | -0.220 |
horm | -0.213 |
nerv | -0.205 |
mosqu | -0.199 |
behavi | -0.194 |
Token | happening |
Token ID | 5836 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
abase | +0.398 |
rador | +0.316 |
MB | +0.312 |
CAD | +0.293 |
ielding | +0.291 |
Neg logit contributions | |
moons | -0.356 |
horm | -0.345 |
nerv | -0.333 |
mosqu | -0.322 |
behavi | -0.314 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
abase | +0.230 |
rador | +0.186 |
MB | +0.184 |
CAD | +0.174 |
ielding | +0.173 |
Neg logit contributions | |
moons | -0.175 |
horm | -0.169 |
nerv | -0.162 |
mosqu | -0.156 |
behavi | -0.152 |
Token | candidate |
Token ID | 4540 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
abase | +1.308 |
MB | +1.066 |
rador | +1.066 |
CAD | +1.001 |
ielding | +0.991 |
Neg logit contributions | |
moons | -0.917 |
horm | -0.897 |
nerv | -0.854 |
mosqu | -0.832 |
behavi | -0.814 |
Token | . |
Token ID | 13 |
Feature activation | +8.31e-03 |
Pos logit contributions | |
abase | +0.738 |
MB | +0.600 |
rador | +0.599 |
CAD | +0.566 |
ielding | +0.559 |
Neg logit contributions | |
moons | -0.508 |
horm | -0.497 |
nerv | -0.471 |
mosqu | -0.460 |
behavi | -0.446 |
Token |
|
Token ID | 198 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
abase | +0.007 |
rador | +0.006 |
MB | +0.006 |
CAD | +0.005 |
ielding | +0.005 |
Neg logit contributions | |
moons | -0.006 |
horm | -0.006 |
nerv | -0.006 |
mosqu | -0.006 |
behavi | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
abase | +0.049 |
rador | +0.040 |
MB | +0.039 |
ielding | +0.036 |
CAD | +0.036 |
Neg logit contributions | |
moons | -0.039 |
horm | -0.037 |
nerv | -0.036 |
mosqu | -0.033 |
behavi | -0.032 |
Token | N |
Token ID | 45 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
abase | +0.125 |
rador | +0.101 |
MB | +0.099 |
CAD | +0.094 |
ielding | +0.093 |
Neg logit contributions | |
moons | -0.102 |
horm | -0.098 |
nerv | -0.094 |
mosqu | -0.090 |
behavi | -0.088 |
Token | ancy |
Token ID | 3883 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
abase | +0.110 |
rador | +0.085 |
MB | +0.085 |
CAD | +0.079 |
ielding | +0.078 |
Neg logit contributions | |
moons | -0.111 |
horm | -0.108 |
nerv | -0.105 |
mosqu | -0.102 |
behavi | -0.099 |
Token | Pelosi |
Token ID | 29611 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
abase | +2.110 |
MB | +1.540 |
rador | +1.472 |
CAD | +1.368 |
ielding | +1.328 |
Neg logit contributions | |
moons | -3.541 |
horm | -3.470 |
nerv | -3.369 |
mosqu | -3.349 |
behavi | -3.298 |
Token |
|
Token ID | 198 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
abase | +0.322 |
rador | +0.258 |
MB | +0.255 |
CAD | +0.240 |
ielding | +0.238 |
Neg logit contributions | |
moons | -0.270 |
horm | -0.261 |
nerv | -0.251 |
mosqu | -0.243 |
behavi | -0.237 |
Token |
|
Token ID | 198 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
moons | +0.510 |
horm | +0.481 |
nerv | +0.469 |
mosqu | +0.420 |
behavi | +0.413 |
Neg logit contributions | |
abase | -0.685 |
rador | -0.554 |
MB | -0.533 |
ielding | -0.508 |
CAD | -0.504 |
Token | In |
Token ID | 818 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
moons | +0.405 |
horm | +0.389 |
nerv | +0.373 |
mosqu | +0.356 |
behavi | +0.346 |
Neg logit contributions | |
abase | -0.555 |
rador | -0.451 |
MB | -0.444 |
CAD | -0.420 |
ielding | -0.417 |
Token | October |
Token ID | 3267 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
moons | +0.041 |
horm | +0.040 |
nerv | +0.039 |
mosqu | +0.037 |
behavi | +0.036 |
Neg logit contributions | |
abase | -0.048 |
rador | -0.039 |
MB | -0.038 |
CAD | -0.036 |
ielding | -0.036 |
Token | ernel |
Token ID | 7948 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
abase | +0.594 |
rador | +0.494 |
MB | +0.490 |
CAD | +0.466 |
ielding | +0.463 |
Neg logit contributions | |
moons | -0.322 |
horm | -0.309 |
nerv | -0.294 |
mosqu | -0.283 |
behavi | -0.273 |
Token | ) |
Token ID | 1267 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
abase | +0.635 |
rador | +0.518 |
MB | +0.511 |
CAD | +0.483 |
ielding | +0.481 |
Neg logit contributions | |
moons | -0.431 |
horm | -0.413 |
nerv | -0.398 |
mosqu | -0.376 |
behavi | -0.366 |
Token |
|
Token ID | 198 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
abase | +0.378 |
rador | +0.283 |
MB | +0.281 |
CAD | +0.258 |
ielding | +0.253 |
Neg logit contributions | |
moons | -0.502 |
horm | -0.490 |
nerv | -0.475 |
mosqu | -0.465 |
behavi | -0.455 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
abase | +0.282 |
rador | +0.226 |
MB | +0.222 |
CAD | +0.209 |
ielding | +0.208 |
Neg logit contributions | |
moons | -0.229 |
horm | -0.220 |
nerv | -0.212 |
mosqu | -0.201 |
behavi | -0.197 |
Token | L |
Token ID | 43 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
abase | +0.352 |
rador | +0.283 |
MB | +0.280 |
CAD | +0.264 |
ielding | +0.261 |
Neg logit contributions | |
moons | -0.283 |
horm | -0.274 |
nerv | -0.263 |
mosqu | -0.254 |
behavi | -0.247 |
Token | ines |
Token ID | 1127 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
abase | +0.058 |
rador | +0.044 |
MB | +0.044 |
CAD | +0.040 |
ielding | +0.040 |
Neg logit contributions | |
moons | -0.070 |
horm | -0.068 |
nerv | -0.066 |
mosqu | -0.064 |
behavi | -0.063 |
Token | 20 |
Token ID | 1160 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
abase | +2.176 |
MB | +1.593 |
rador | +1.543 |
CAD | +1.443 |
ielding | +1.383 |
Neg logit contributions | |
moons | -3.450 |
horm | -3.392 |
nerv | -3.278 |
mosqu | -3.234 |
behavi | -3.192 |
Token | and |
Token ID | 290 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
moons | +0.112 |
horm | +0.108 |
nerv | +0.103 |
mosqu | +0.100 |
behavi | +0.097 |
Neg logit contributions | |
abase | -0.174 |
rador | -0.143 |
MB | -0.142 |
CAD | -0.135 |
ielding | -0.134 |
Token | 21 |
Token ID | 2310 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
moons | +0.271 |
horm | +0.264 |
nerv | +0.255 |
mosqu | +0.248 |
behavi | +0.243 |
Neg logit contributions | |
abase | -0.236 |
rador | -0.181 |
MB | -0.179 |
CAD | -0.165 |
ielding | -0.164 |
Token | loads |
Token ID | 15989 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
abase | +1.045 |
rador | +0.849 |
MB | +0.848 |
CAD | +0.800 |
ielding | +0.789 |
Neg logit contributions | |
moons | -0.753 |
horm | -0.732 |
nerv | -0.698 |
mosqu | -0.682 |
behavi | -0.665 |
Token | our |
Token ID | 674 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
moons | +0.267 |
horm | +0.258 |
nerv | +0.249 |
mosqu | +0.241 |
behavi | +0.234 |
Neg logit contributions | |
abase | -0.334 |
rador | -0.268 |
MB | -0.264 |
CAD | -0.249 |
ielding | -0.248 |
Token |
|
Token ID | 198 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
abase | +1.502 |
MB | +1.196 |
rador | +1.189 |
CAD | +1.120 |
ielding | +1.101 |
Neg logit contributions | |
moons | -1.330 |
horm | -1.294 |
nerv | -1.238 |
mosqu | -1.220 |
behavi | -1.179 |
Token |
|
Token ID | 198 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
abase | +0.634 |
rador | +0.507 |
MB | +0.501 |
CAD | +0.471 |
ielding | +0.467 |
Neg logit contributions | |
moons | -0.532 |
horm | -0.515 |
nerv | -0.496 |
mosqu | -0.478 |
behavi | -0.466 |
Token | How |
Token ID | 2437 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
abase | +0.549 |
rador | +0.442 |
MB | +0.442 |
CAD | +0.414 |
ielding | +0.411 |
Neg logit contributions | |
moons | -0.437 |
horm | -0.425 |
nerv | -0.409 |
mosqu | -0.401 |
behavi | -0.389 |
Token | a |
Token ID | 257 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
moons | +0.194 |
horm | +0.188 |
nerv | +0.180 |
mosqu | +0.174 |
behavi | +0.169 |
Neg logit contributions | |
abase | -0.260 |
rador | -0.210 |
MB | -0.209 |
CAD | -0.197 |
ielding | -0.195 |
Token | pro |
Token ID | 1676 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
moons | +0.380 |
horm | +0.368 |
nerv | +0.353 |
mosqu | +0.342 |
behavi | +0.332 |
Neg logit contributions | |
abase | -0.501 |
rador | -0.405 |
MB | -0.402 |
CAD | -0.379 |
ielding | -0.375 |
Token | pos |
Token ID | 1930 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
moons | +0.495 |
horm | +0.479 |
nerv | +0.470 |
mosqu | +0.450 |
behavi | +0.439 |
Neg logit contributions | |
abase | -0.404 |
rador | -0.305 |
MB | -0.300 |
CAD | -0.278 |
ielding | -0.275 |
Token | that |
Token ID | 326 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
abase | +2.948 |
MB | +2.376 |
rador | +2.342 |
CAD | +2.199 |
ielding | +2.162 |
Neg logit contributions | |
moons | -2.603 |
horm | -2.568 |
nerv | -2.451 |
mosqu | -2.412 |
behavi | -2.338 |
Token | this |
Token ID | 428 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
abase | +0.058 |
rador | +0.046 |
MB | +0.046 |
CAD | +0.043 |
ielding | +0.043 |
Neg logit contributions | |
moons | -0.047 |
horm | -0.045 |
nerv | -0.043 |
mosqu | -0.042 |
behavi | -0.041 |
Token | famous |
Token ID | 5863 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
abase | +0.479 |
rador | +0.386 |
MB | +0.385 |
CAD | +0.361 |
ielding | +0.355 |
Neg logit contributions | |
moons | -0.389 |
horm | -0.377 |
nerv | -0.362 |
mosqu | -0.353 |
behavi | -0.343 |
Token | and |
Token ID | 290 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
moons | +0.288 |
horm | +0.278 |
nerv | +0.267 |
mosqu | +0.257 |
behavi | +0.250 |
Neg logit contributions | |
abase | -0.405 |
rador | -0.330 |
MB | -0.327 |
CAD | -0.309 |
ielding | -0.306 |
Token | very |
Token ID | 845 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
abase | +0.460 |
rador | +0.365 |
MB | +0.362 |
CAD | +0.339 |
ielding | +0.335 |
Neg logit contributions | |
moons | -0.415 |
horm | -0.403 |
nerv | -0.388 |
mosqu | -0.377 |
behavi | -0.367 |
Token | necessary |
Token ID | 3306 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
abase | +0.280 |
rador | +0.231 |
MB | +0.230 |
CAD | +0.217 |
ielding | +0.216 |
Neg logit contributions | |
moons | -0.173 |
horm | -0.167 |
nerv | -0.159 |
mosqu | -0.154 |
behavi | -0.148 |
Token | skills |
Token ID | 4678 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
moons | +0.231 |
horm | +0.222 |
nerv | +0.211 |
mosqu | +0.202 |
behavi | +0.196 |
Neg logit contributions | |
abase | -0.415 |
rador | -0.344 |
MB | -0.341 |
CAD | -0.324 |
ielding | -0.322 |
Token | to |
Token ID | 284 |
Feature activation | +7.40e-03 |
Pos logit contributions | |
abase | +0.194 |
rador | +0.157 |
MB | +0.156 |
CAD | +0.147 |
ielding | +0.146 |
Neg logit contributions | |
moons | -0.141 |
horm | -0.137 |
nerv | -0.131 |
mosqu | -0.127 |
behavi | -0.123 |
Token | analyze |
Token ID | 16602 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
abase | +0.007 |
MB | +0.006 |
rador | +0.006 |
CAD | +0.006 |
ielding | +0.006 |
Neg logit contributions | |
moons | -0.005 |
horm | -0.005 |
nerv | -0.004 |
mosqu | -0.004 |
behavi | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
abase | +0.343 |
rador | +0.277 |
MB | +0.276 |
CAD | +0.260 |
ielding | +0.257 |
Neg logit contributions | |
moons | -0.261 |
horm | -0.253 |
nerv | -0.243 |
mosqu | -0.236 |
behavi | -0.228 |
Token | synthes |
Token ID | 24983 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
abase | +0.490 |
rador | +0.402 |
MB | +0.402 |
CAD | +0.381 |
ielding | +0.376 |
Neg logit contributions | |
moons | -0.324 |
horm | -0.314 |
nerv | -0.299 |
mosqu | -0.295 |
behavi | -0.283 |
Token | ize |
Token ID | 1096 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
abase | +1.955 |
MB | +1.339 |
rador | +1.330 |
CAD | +1.191 |
ielding | +1.163 |
Neg logit contributions | |
moons | -3.644 |
horm | -3.615 |
mosqu | -3.490 |
nerv | -3.474 |
behavi | -3.411 |
Token | information |
Token ID | 1321 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
abase | +0.183 |
rador | +0.147 |
MB | +0.146 |
CAD | +0.137 |
ielding | +0.136 |
Neg logit contributions | |
moons | -0.145 |
horm | -0.140 |
nerv | -0.135 |
mosqu | -0.131 |
behavi | -0.127 |
Token | and |
Token ID | 290 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
abase | +0.924 |
rador | +0.744 |
MB | +0.742 |
CAD | +0.698 |
ielding | +0.690 |
Neg logit contributions | |
moons | -0.719 |
horm | -0.698 |
nerv | -0.668 |
mosqu | -0.652 |
behavi | -0.630 |
Token | to |
Token ID | 284 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
abase | +0.040 |
rador | +0.033 |
MB | +0.033 |
CAD | +0.031 |
ielding | +0.031 |
Neg logit contributions | |
moons | -0.028 |
horm | -0.027 |
nerv | -0.026 |
mosqu | -0.025 |
behavi | -0.024 |
Token | generate |
Token ID | 7716 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
abase | +0.062 |
rador | +0.051 |
MB | +0.051 |
CAD | +0.048 |
ielding | +0.048 |
Neg logit contributions | |
moons | -0.040 |
horm | -0.038 |
nerv | -0.036 |
mosqu | -0.035 |
behavi | -0.034 |
Token | than |
Token ID | 621 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
moons | +1.921 |
horm | +1.843 |
nerv | +1.799 |
mosqu | +1.728 |
behavi | +1.704 |
Neg logit contributions | |
abase | -1.822 |
rador | -1.397 |
MB | -1.344 |
CAD | -1.262 |
ielding | -1.260 |
Token | 10 |
Token ID | 838 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
moons | +0.328 |
horm | +0.320 |
nerv | +0.310 |
mosqu | +0.302 |
behavi | +0.293 |
Neg logit contributions | |
abase | -0.346 |
MB | -0.275 |
rador | -0.274 |
CAD | -0.256 |
ielding | -0.253 |
Token | years |
Token ID | 812 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
moons | +0.678 |
horm | +0.646 |
nerv | +0.631 |
mosqu | +0.604 |
behavi | +0.596 |
Neg logit contributions | |
abase | -0.687 |
rador | -0.545 |
MB | -0.483 |
CAD | -0.474 |
ielding | -0.463 |
Token | in |
Token ID | 287 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
moons | +0.612 |
horm | +0.593 |
nerv | +0.570 |
mosqu | +0.552 |
behavi | +0.537 |
Neg logit contributions | |
abase | -0.764 |
rador | -0.614 |
MB | -0.609 |
CAD | -0.573 |
ielding | -0.568 |
Token | prison |
Token ID | 3770 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
moons | +0.361 |
horm | +0.354 |
nerv | +0.340 |
mosqu | +0.331 |
behavi | +0.323 |
Neg logit contributions | |
abase | -0.372 |
MB | -0.301 |
rador | -0.295 |
CAD | -0.274 |
ielding | -0.268 |
Token | MORE |
Token ID | 12011 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
abase | +0.429 |
MB | +0.331 |
rador | +0.324 |
CAD | +0.303 |
ielding | +0.298 |
Neg logit contributions | |
moons | -0.513 |
horm | -0.502 |
nerv | -0.483 |
mosqu | -0.477 |
behavi | -0.468 |
Token | and |
Token ID | 290 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
abase | +3.320 |
MB | +2.760 |
rador | +2.731 |
ielding | +2.609 |
CAD | +2.597 |
Neg logit contributions | |
moons | -2.158 |
horm | -2.157 |
nerv | -1.987 |
mosqu | -1.978 |
behavi | -1.909 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
abase | +0.526 |
rador | +0.424 |
MB | +0.422 |
CAD | +0.397 |
ielding | +0.393 |
Neg logit contributions | |
moons | -0.409 |
horm | -0.396 |
nerv | -0.380 |
mosqu | -0.368 |
behavi | -0.359 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
abase | +1.028 |
rador | +0.834 |
MB | +0.830 |
CAD | +0.782 |
ielding | +0.775 |
Neg logit contributions | |
moons | -0.751 |
horm | -0.727 |
nerv | -0.696 |
mosqu | -0.677 |
behavi | -0.657 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
abase | +0.373 |
MB | +0.299 |
rador | +0.299 |
CAD | +0.280 |
ielding | +0.277 |
Neg logit contributions | |
moons | -0.299 |
horm | -0.291 |
nerv | -0.279 |
mosqu | -0.271 |
behavi | -0.265 |
Token | Diane |
Token ID | 26542 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
abase | +0.884 |
rador | +0.646 |
MB | +0.646 |
CAD | +0.583 |
ielding | +0.579 |
Neg logit contributions | |
moons | -1.330 |
horm | -1.302 |
nerv | -1.260 |
mosqu | -1.241 |
behavi | -1.219 |
Token | during |
Token ID | 1141 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
abase | +1.017 |
rador | +0.829 |
MB | +0.829 |
CAD | +0.777 |
ielding | +0.771 |
Neg logit contributions | |
moons | -0.724 |
horm | -0.707 |
nerv | -0.666 |
mosqu | -0.657 |
behavi | -0.636 |
Token | this |
Token ID | 428 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
moons | +0.959 |
horm | +0.928 |
nerv | +0.892 |
mosqu | +0.856 |
behavi | +0.833 |
Neg logit contributions | |
abase | -1.260 |
rador | -1.014 |
MB | -1.000 |
ielding | -0.945 |
CAD | -0.943 |
Token | time |
Token ID | 640 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
abase | +0.302 |
rador | +0.245 |
MB | +0.243 |
CAD | +0.229 |
ielding | +0.226 |
Neg logit contributions | |
moons | -0.223 |
horm | -0.216 |
nerv | -0.207 |
mosqu | -0.201 |
behavi | -0.195 |
Token | period |
Token ID | 2278 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
moons | +0.525 |
horm | +0.506 |
nerv | +0.483 |
mosqu | +0.467 |
behavi | +0.452 |
Neg logit contributions | |
abase | -0.797 |
rador | -0.653 |
MB | -0.649 |
CAD | -0.614 |
ielding | -0.609 |
Token | but |
Token ID | 475 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
moons | +0.446 |
horm | +0.430 |
nerv | +0.410 |
mosqu | +0.397 |
behavi | +0.385 |
Neg logit contributions | |
abase | -0.670 |
rador | -0.548 |
MB | -0.545 |
CAD | -0.515 |
ielding | -0.511 |
Token | rather |
Token ID | 2138 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
abase | +0.486 |
rador | +0.389 |
MB | +0.388 |
CAD | +0.363 |
ielding | +0.359 |
Neg logit contributions | |
moons | -0.403 |
horm | -0.391 |
nerv | -0.376 |
mosqu | -0.365 |
behavi | -0.356 |
Token | " |
Token ID | 366 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
abase | +2.894 |
MB | +2.357 |
rador | +2.317 |
CAD | +2.199 |
ielding | +2.133 |
Neg logit contributions | |
moons | -2.494 |
horm | -2.436 |
nerv | -2.318 |
mosqu | -2.289 |
behavi | -2.250 |
Token | on |
Token ID | 261 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
moons | +0.385 |
horm | +0.374 |
nerv | +0.360 |
mosqu | +0.349 |
behavi | +0.340 |
Neg logit contributions | |
abase | -0.398 |
rador | -0.313 |
MB | -0.310 |
CAD | -0.290 |
ielding | -0.286 |
Token | the |
Token ID | 262 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
moons | +0.128 |
horm | +0.123 |
nerv | +0.119 |
mosqu | +0.114 |
behavi | +0.111 |
Neg logit contributions | |
abase | -0.165 |
rador | -0.132 |
MB | -0.131 |
CAD | -0.123 |
ielding | -0.123 |
Token | other |
Token ID | 584 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
moons | +0.158 |
horm | +0.153 |
nerv | +0.147 |
mosqu | +0.142 |
behavi | +0.138 |
Neg logit contributions | |
abase | -0.199 |
rador | -0.160 |
MB | -0.158 |
CAD | -0.149 |
ielding | -0.148 |
Token | side |
Token ID | 1735 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
abase | +1.122 |
rador | +0.934 |
MB | +0.930 |
CAD | +0.883 |
ielding | +0.876 |
Neg logit contributions | |
moons | -0.603 |
horm | -0.578 |
nerv | -0.549 |
mosqu | -0.528 |
behavi | -0.508 |
Token | Silver |
Token ID | 26766 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
abase | +0.439 |
rador | +0.346 |
MB | +0.344 |
CAD | +0.321 |
ielding | +0.318 |
Neg logit contributions | |
moons | -0.410 |
horm | -0.398 |
nerv | -0.384 |
mosqu | -0.372 |
behavi | -0.363 |
Token | Bullet |
Token ID | 18003 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
abase | +0.452 |
rador | +0.341 |
MB | +0.336 |
CAD | +0.310 |
ielding | +0.306 |
Neg logit contributions | |
moons | -0.570 |
horm | -0.556 |
nerv | -0.539 |
mosqu | -0.525 |
behavi | -0.514 |
Token | � |
Token ID | 447 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
abase | +1.444 |
MB | +1.155 |
rador | +1.145 |
CAD | +1.080 |
ielding | +1.066 |
Neg logit contributions | |
moons | -1.205 |
horm | -1.169 |
nerv | -1.120 |
mosqu | -1.095 |
behavi | -1.053 |
Token | � |
Token ID | 251 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
abase | +0.135 |
rador | +0.104 |
MB | +0.103 |
CAD | +0.096 |
ielding | +0.095 |
Neg logit contributions | |
moons | -0.145 |
horm | -0.141 |
nerv | -0.136 |
mosqu | -0.132 |
behavi | -0.129 |
Token | but |
Token ID | 475 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
abase | +0.232 |
rador | +0.188 |
MB | +0.187 |
CAD | +0.176 |
ielding | +0.175 |
Neg logit contributions | |
moons | -0.173 |
horm | -0.167 |
nerv | -0.160 |
mosqu | -0.156 |
behavi | -0.151 |
Token | rather |
Token ID | 2138 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
abase | +0.252 |
rador | +0.192 |
MB | +0.190 |
CAD | +0.176 |
ielding | +0.174 |
Neg logit contributions | |
moons | -0.296 |
horm | -0.288 |
nerv | -0.279 |
mosqu | -0.272 |
behavi | -0.266 |
Token | a |
Token ID | 257 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
abase | +2.819 |
MB | +2.304 |
rador | +2.262 |
CAD | +2.145 |
ielding | +2.085 |
Neg logit contributions | |
moons | -2.536 |
horm | -2.461 |
nerv | -2.383 |
mosqu | -2.327 |
behavi | -2.253 |
Token | combination |
Token ID | 6087 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
moons | +0.216 |
horm | +0.209 |
nerv | +0.202 |
mosqu | +0.195 |
behavi | +0.190 |
Neg logit contributions | |
abase | -0.250 |
rador | -0.199 |
MB | -0.197 |
CAD | -0.184 |
ielding | -0.183 |
Token | of |
Token ID | 286 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
abase | +1.885 |
MB | +1.489 |
rador | +1.480 |
CAD | +1.385 |
ielding | +1.359 |
Neg logit contributions | |
moons | -1.851 |
horm | -1.798 |
nerv | -1.738 |
mosqu | -1.696 |
behavi | -1.639 |
Token | D |
Token ID | 360 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
abase | +0.054 |
rador | +0.044 |
MB | +0.043 |
CAD | +0.041 |
ielding | +0.040 |
Neg logit contributions | |
moons | -0.046 |
horm | -0.045 |
nerv | -0.043 |
mosqu | -0.042 |
behavi | -0.040 |
Token | DoS |
Token ID | 46498 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
abase | +0.516 |
rador | +0.428 |
MB | +0.427 |
CAD | +0.404 |
ielding | +0.402 |
Neg logit contributions | |
moons | -0.288 |
horm | -0.276 |
nerv | -0.264 |
mosqu | -0.254 |
behavi | -0.244 |
Token | approach |
Token ID | 3164 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
moons | +0.087 |
horm | +0.084 |
nerv | +0.081 |
mosqu | +0.078 |
behavi | +0.076 |
Neg logit contributions | |
abase | -0.115 |
rador | -0.093 |
MB | -0.092 |
CAD | -0.086 |
ielding | -0.086 |
Token | to |
Token ID | 284 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
moons | +0.365 |
horm | +0.351 |
nerv | +0.339 |
mosqu | +0.324 |
behavi | +0.315 |
Neg logit contributions | |
abase | -0.479 |
rador | -0.387 |
MB | -0.383 |
CAD | -0.361 |
ielding | -0.358 |
Token | designing |
Token ID | 18492 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
moons | +0.126 |
horm | +0.122 |
nerv | +0.118 |
mosqu | +0.114 |
behavi | +0.110 |
Neg logit contributions | |
abase | -0.177 |
rador | -0.143 |
MB | -0.143 |
CAD | -0.135 |
ielding | -0.134 |
Token | X |
Token ID | 1395 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
abase | +0.241 |
MB | +0.195 |
rador | +0.195 |
CAD | +0.184 |
ielding | +0.181 |
Neg logit contributions | |
moons | -0.179 |
horm | -0.174 |
nerv | -0.167 |
mosqu | -0.162 |
behavi | -0.158 |
Token | e |
Token ID | 68 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
abase | +1.033 |
rador | +0.809 |
MB | +0.806 |
CAD | +0.752 |
ielding | +0.744 |
Neg logit contributions | |
moons | -1.011 |
horm | -0.987 |
nerv | -0.950 |
mosqu | -0.926 |
behavi | -0.913 |
Token | od |
Token ID | 375 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
abase | +0.646 |
MB | +0.500 |
rador | +0.495 |
CAD | +0.463 |
ielding | +0.455 |
Neg logit contributions | |
moons | -0.709 |
horm | -0.693 |
nerv | -0.668 |
mosqu | -0.655 |
behavi | -0.644 |
Token | r |
Token ID | 81 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
abase | +2.770 |
rador | +2.170 |
MB | +2.154 |
ielding | +2.025 |
CAD | +2.004 |
Neg logit contributions | |
moons | -2.676 |
horm | -2.620 |
nerv | -2.511 |
mosqu | -2.483 |
behavi | -2.463 |
Token | ifter |
Token ID | 18171 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
abase | +0.727 |
rador | +0.572 |
MB | +0.569 |
CAD | +0.532 |
ielding | +0.527 |
Neg logit contributions | |
moons | -0.660 |
horm | -0.641 |
nerv | -0.617 |
mosqu | -0.602 |
behavi | -0.586 |
Token | was |
Token ID | 373 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
abase | +0.702 |
rador | +0.564 |
MB | +0.560 |
CAD | +0.526 |
ielding | +0.522 |
Neg logit contributions | |
moons | -0.561 |
horm | -0.543 |
nerv | -0.522 |
mosqu | -0.506 |
behavi | -0.493 |
Token | a |
Token ID | 257 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
abase | +0.170 |
rador | +0.134 |
MB | +0.133 |
CAD | +0.124 |
ielding | +0.123 |
Neg logit contributions | |
moons | -0.154 |
horm | -0.149 |
nerv | -0.144 |
mosqu | -0.139 |
behavi | -0.135 |
Token | case |
Token ID | 1339 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
abase | +0.784 |
rador | +0.628 |
MB | +0.625 |
CAD | +0.588 |
ielding | +0.581 |
Neg logit contributions | |
moons | -0.645 |
horm | -0.627 |
nerv | -0.602 |
mosqu | -0.588 |
behavi | -0.572 |
Token | T |
Token ID | 51 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
moons | +0.146 |
horm | +0.141 |
nerv | +0.136 |
mosqu | +0.131 |
behavi | +0.128 |
Neg logit contributions | |
abase | -0.180 |
rador | -0.145 |
MB | -0.143 |
CAD | -0.135 |
ielding | -0.134 |
Token | ear |
Token ID | 451 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
moons | +0.185 |
horm | +0.179 |
nerv | +0.173 |
mosqu | +0.167 |
behavi | +0.163 |
Neg logit contributions | |
abase | -0.231 |
rador | -0.185 |
MB | -0.184 |
CAD | -0.173 |
ielding | -0.171 |
Token |
|
Token ID | 198 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
abase | +0.797 |
rador | +0.635 |
MB | +0.633 |
CAD | +0.590 |
ielding | +0.587 |
Neg logit contributions | |
moons | -0.663 |
horm | -0.650 |
nerv | -0.622 |
mosqu | -0.605 |
behavi | -0.589 |
Token |
|
Token ID | 198 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
moons | +0.216 |
horm | +0.206 |
nerv | +0.200 |
mosqu | +0.186 |
behavi | +0.182 |
Neg logit contributions | |
abase | -0.272 |
rador | -0.219 |
MB | -0.213 |
ielding | -0.201 |
CAD | -0.201 |
Token | V |
Token ID | 53 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
moons | +0.138 |
horm | +0.133 |
nerv | +0.128 |
mosqu | +0.124 |
behavi | +0.121 |
Neg logit contributions | |
abase | -0.171 |
rador | -0.137 |
MB | -0.136 |
CAD | -0.128 |
ielding | -0.127 |
Token | oid |
Token ID | 1868 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
abase | +0.083 |
rador | +0.065 |
MB | +0.065 |
CAD | +0.060 |
ielding | +0.060 |
Neg logit contributions | |
moons | -0.077 |
horm | -0.074 |
nerv | -0.072 |
mosqu | -0.069 |
behavi | -0.068 |
Token | Ray |
Token ID | 19591 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
abase | +2.947 |
MB | +2.351 |
rador | +2.349 |
CAD | +2.202 |
ielding | +2.178 |
Neg logit contributions | |
moons | -2.432 |
horm | -2.376 |
nerv | -2.289 |
mosqu | -2.250 |
behavi | -2.181 |
Token |
|
Token ID | 198 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
abase | +1.318 |
rador | +1.054 |
MB | +1.051 |
CAD | +0.986 |
ielding | +0.972 |
Neg logit contributions | |
moons | -1.106 |
horm | -1.076 |
nerv | -1.032 |
mosqu | -1.008 |
behavi | -0.979 |
Token |
|
Token ID | 198 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
moons | +0.063 |
horm | +0.060 |
nerv | +0.058 |
mosqu | +0.055 |
behavi | +0.053 |
Neg logit contributions | |
abase | -0.079 |
rador | -0.063 |
MB | -0.062 |
CAD | -0.058 |
ielding | -0.058 |
Token | J |
Token ID | 41 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
moons | +0.070 |
horm | +0.067 |
nerv | +0.065 |
mosqu | +0.063 |
behavi | +0.061 |
Neg logit contributions | |
abase | -0.086 |
rador | -0.069 |
MB | -0.068 |
CAD | -0.064 |
ielding | -0.064 |
Token | KS |
Token ID | 27015 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
moons | +0.338 |
horm | +0.328 |
nerv | +0.317 |
mosqu | +0.307 |
behavi | +0.300 |
Neg logit contributions | |
abase | -0.360 |
rador | -0.283 |
MB | -0.281 |
CAD | -0.262 |
ielding | -0.260 |
Token | s |
Token ID | 82 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
abase | +0.271 |
rador | +0.220 |
MB | +0.217 |
CAD | +0.203 |
ielding | +0.202 |
Neg logit contributions | |
moons | -0.219 |
horm | -0.213 |
nerv | -0.205 |
mosqu | -0.198 |
behavi | -0.194 |
Token | — |
Token ID | 851 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
abase | +0.320 |
rador | +0.256 |
MB | +0.256 |
CAD | +0.239 |
ielding | +0.236 |
Neg logit contributions | |
moons | -0.265 |
horm | -0.258 |
nerv | -0.248 |
mosqu | -0.240 |
behavi | -0.234 |
Token | Cody |
Token ID | 27035 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
abase | +0.801 |
rador | +0.628 |
MB | +0.627 |
CAD | +0.585 |
ielding | +0.575 |
Neg logit contributions | |
moons | -0.774 |
horm | -0.753 |
nerv | -0.726 |
mosqu | -0.706 |
behavi | -0.690 |
Token | Wester |
Token ID | 32104 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
abase | +0.419 |
MB | +0.333 |
rador | +0.332 |
CAD | +0.311 |
ielding | +0.307 |
Neg logit contributions | |
moons | -0.367 |
horm | -0.357 |
nerv | -0.344 |
mosqu | -0.335 |
behavi | -0.327 |
Token | lund |
Token ID | 37525 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
abase | +0.410 |
rador | +0.331 |
MB | +0.329 |
CAD | +0.308 |
ielding | +0.305 |
Neg logit contributions | |
moons | -0.327 |
horm | -0.316 |
nerv | -0.305 |
mosqu | -0.296 |
behavi | -0.288 |
Token | (@ |
Token ID | 4275 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
abase | +0.420 |
rador | +0.347 |
MB | +0.345 |
CAD | +0.327 |
ielding | +0.323 |
Neg logit contributions | |
moons | -0.262 |
horm | -0.253 |
nerv | -0.241 |
mosqu | -0.233 |
behavi | -0.225 |
Token | C |
Token ID | 34 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
abase | +2.528 |
rador | +1.964 |
MB | +1.917 |
CAD | +1.796 |
ielding | +1.788 |
Neg logit contributions | |
moons | -2.824 |
horm | -2.764 |
nerv | -2.670 |
mosqu | -2.600 |
behavi | -2.563 |
Token | ody |
Token ID | 1118 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
abase | +0.124 |
rador | +0.093 |
MB | +0.091 |
CAD | +0.084 |
ielding | +0.083 |
Neg logit contributions | |
moons | -0.165 |
horm | -0.161 |
nerv | -0.156 |
mosqu | -0.153 |
behavi | -0.150 |
Token | W |
Token ID | 54 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
abase | +1.345 |
rador | +1.067 |
MB | +1.060 |
CAD | +0.989 |
ielding | +0.989 |
Neg logit contributions | |
moons | -1.218 |
horm | -1.186 |
nerv | -1.150 |
mosqu | -1.117 |
behavi | -1.092 |
Token | ester |
Token ID | 7834 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
moons | +0.407 |
horm | +0.395 |
nerv | +0.380 |
mosqu | +0.370 |
behavi | +0.361 |
Neg logit contributions | |
abase | -0.454 |
rador | -0.361 |
MB | -0.357 |
CAD | -0.334 |
ielding | -0.333 |
Token | lund |
Token ID | 37525 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
abase | +0.473 |
rador | +0.343 |
MB | +0.338 |
CAD | +0.308 |
ielding | +0.304 |
Neg logit contributions | |
moons | -0.706 |
horm | -0.688 |
nerv | -0.669 |
mosqu | -0.650 |
behavi | -0.638 |
Token | 411 |
Token ID | 43184 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
moons | +0.704 |
horm | +0.683 |
nerv | +0.664 |
mosqu | +0.641 |
behavi | +0.626 |
Neg logit contributions | |
abase | -0.593 |
rador | -0.455 |
MB | -0.442 |
ielding | -0.409 |
CAD | -0.408 |
Token | horsepower |
Token ID | 36696 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
moons | +0.838 |
horm | +0.814 |
nerv | +0.783 |
mosqu | +0.760 |
behavi | +0.741 |
Neg logit contributions | |
abase | -0.973 |
rador | -0.776 |
MB | -0.771 |
CAD | -0.722 |
ielding | -0.715 |
Token | and |
Token ID | 290 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
moons | +0.519 |
horm | +0.497 |
nerv | +0.475 |
mosqu | +0.454 |
behavi | +0.439 |
Neg logit contributions | |
abase | -0.899 |
rador | -0.745 |
MB | -0.737 |
CAD | -0.700 |
ielding | -0.696 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
moons | +0.045 |
horm | +0.044 |
nerv | +0.043 |
mosqu | +0.042 |
behavi | +0.041 |
Neg logit contributions | |
abase | -0.035 |
rador | -0.027 |
MB | -0.026 |
CAD | -0.024 |
ielding | -0.024 |
Token | 34 |
Token ID | 2682 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
moons | +0.080 |
horm | +0.078 |
nerv | +0.075 |
mosqu | +0.073 |
behavi | +0.071 |
Neg logit contributions | |
abase | -0.093 |
rador | -0.074 |
MB | -0.073 |
CAD | -0.069 |
ielding | -0.068 |
Token | lb |
Token ID | 18360 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
abase | +0.034 |
rador | +0.027 |
MB | +0.027 |
CAD | +0.025 |
ielding | +0.025 |
Neg logit contributions | |
moons | -0.033 |
horm | -0.032 |
nerv | -0.031 |
mosqu | -0.030 |
behavi | -0.029 |
Token | .- |
Token ID | 7874 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
moons | +2.108 |
horm | +1.935 |
nerv | +1.864 |
mosqu | +1.654 |
behavi | +1.574 |
Neg logit contributions | |
abase | -4.890 |
rador | -4.144 |
MB | -3.993 |
CAD | -3.840 |
ielding | -3.824 |
Token | ft |
Token ID | 701 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
moons | +0.401 |
horm | +0.386 |
nerv | +0.377 |
mosqu | +0.355 |
seiz | +0.349 |
Neg logit contributions | |
abase | -0.338 |
rador | -0.258 |
MB | -0.252 |
CAD | -0.232 |
ielding | -0.227 |
Token | . |
Token ID | 13 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
moons | +0.777 |
horm | +0.744 |
nerv | +0.712 |
mosqu | +0.682 |
behavi | +0.659 |
Neg logit contributions | |
abase | -1.327 |
rador | -1.097 |
MB | -1.084 |
CAD | -1.031 |
ielding | -1.022 |
Token | of |
Token ID | 286 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
abase | +0.035 |
rador | +0.027 |
MB | +0.027 |
CAD | +0.025 |
ielding | +0.025 |
Neg logit contributions | |
moons | -0.036 |
horm | -0.035 |
nerv | -0.034 |
mosqu | -0.033 |
behavi | -0.032 |
Token | torque |
Token ID | 26415 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
moons | +0.109 |
horm | +0.105 |
nerv | +0.099 |
mosqu | +0.095 |
behavi | +0.092 |
Neg logit contributions | |
abase | -0.216 |
rador | -0.180 |
MB | -0.179 |
CAD | -0.171 |
ielding | -0.169 |
Token | all |
Token ID | 477 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
moons | +0.796 |
horm | +0.769 |
nerv | +0.740 |
mosqu | +0.715 |
behavi | +0.696 |
Neg logit contributions | |
abase | -0.906 |
rador | -0.720 |
MB | -0.709 |
CAD | -0.666 |
ielding | -0.661 |
Token | minions |
Token ID | 22811 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
moons | +0.046 |
horm | +0.044 |
nerv | +0.042 |
mosqu | +0.041 |
behavi | +0.040 |
Neg logit contributions | |
abase | -0.057 |
rador | -0.046 |
MB | -0.045 |
CAD | -0.043 |
ielding | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
moons | +0.247 |
horm | +0.239 |
nerv | +0.228 |
mosqu | +0.220 |
behavi | +0.213 |
Neg logit contributions | |
abase | -0.373 |
rador | -0.305 |
MB | -0.303 |
CAD | -0.287 |
ielding | -0.285 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
moons | +0.158 |
horm | +0.153 |
nerv | +0.148 |
mosqu | +0.143 |
behavi | +0.139 |
Neg logit contributions | |
abase | -0.182 |
rador | -0.145 |
MB | -0.144 |
CAD | -0.135 |
ielding | -0.134 |
Token |
|
Token ID | 198 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
moons | +0.150 |
horm | +0.143 |
nerv | +0.139 |
mosqu | +0.127 |
behavi | +0.125 |
Neg logit contributions | |
abase | -0.194 |
rador | -0.157 |
MB | -0.152 |
ielding | -0.144 |
CAD | -0.144 |
Token | IGN |
Token ID | 16284 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
moons | +0.168 |
horm | +0.161 |
nerv | +0.154 |
mosqu | +0.148 |
behavi | +0.143 |
Neg logit contributions | |
abase | -0.267 |
rador | -0.219 |
MB | -0.218 |
CAD | -0.206 |
ielding | -0.205 |
Token | : |
Token ID | 25 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
moons | +2.489 |
horm | +2.247 |
nerv | +2.230 |
Sparrow | +1.940 |
Quake | +1.918 |
Neg logit contributions | |
abase | -4.103 |
rador | -3.360 |
MB | -3.202 |
ielding | -3.121 |
olesc | -3.066 |
Token | Sure |
Token ID | 10889 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
moons | +1.008 |
horm | +0.972 |
nerv | +0.937 |
mosqu | +0.900 |
behavi | +0.876 |
Neg logit contributions | |
abase | -1.240 |
rador | -0.996 |
MB | -0.980 |
CAD | -0.922 |
ielding | -0.920 |
Token | . |
Token ID | 13 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
moons | +1.579 |
horm | +1.516 |
nerv | +1.460 |
mosqu | +1.397 |
behavi | +1.366 |
Neg logit contributions | |
abase | -2.159 |
rador | -1.759 |
MB | -1.734 |
CAD | -1.642 |
ielding | -1.630 |
Token | Before |
Token ID | 7413 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
moons | +0.029 |
horm | +0.028 |
nerv | +0.027 |
mosqu | +0.027 |
behavi | +0.026 |
Neg logit contributions | |
abase | -0.034 |
MB | -0.027 |
rador | -0.027 |
CAD | -0.025 |
ielding | -0.025 |
Token | we |
Token ID | 356 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
moons | +0.347 |
horm | +0.337 |
nerv | +0.325 |
mosqu | +0.315 |
behavi | +0.307 |
Neg logit contributions | |
abase | -0.382 |
rador | -0.302 |
MB | -0.300 |
CAD | -0.281 |
ielding | -0.278 |
Token | Al |
Token ID | 2348 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
moons | +0.334 |
horm | +0.324 |
nerv | +0.313 |
mosqu | +0.302 |
behavi | +0.298 |
Neg logit contributions | |
abase | -0.324 |
rador | -0.252 |
MB | -0.249 |
CAD | -0.232 |
ielding | -0.230 |
Token | ignment |
Token ID | 16747 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
moons | +0.393 |
horm | +0.383 |
nerv | +0.375 |
mosqu | +0.362 |
behavi | +0.357 |
Neg logit contributions | |
abase | -0.202 |
rador | -0.136 |
MB | -0.136 |
CAD | -0.119 |
ielding | -0.115 |
Token | ] |
Token ID | 60 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
moons | +0.944 |
horm | +0.913 |
nerv | +0.888 |
mosqu | +0.864 |
behavi | +0.846 |
Neg logit contributions | |
abase | -0.764 |
rador | -0.577 |
MB | -0.566 |
CAD | -0.522 |
ielding | -0.517 |
Token | :: |
Token ID | 3712 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
abase | +0.381 |
rador | +0.289 |
MB | +0.283 |
CAD | +0.261 |
ielding | +0.259 |
Neg logit contributions | |
moons | -0.460 |
horm | -0.445 |
nerv | -0.433 |
mosqu | -0.416 |
behavi | -0.409 |
Token | Center |
Token ID | 23656 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
abase | +0.141 |
rador | +0.109 |
MB | +0.107 |
CAD | +0.099 |
ielding | +0.098 |
Neg logit contributions | |
moons | -0.157 |
horm | -0.152 |
nerv | -0.147 |
mosqu | -0.143 |
behavi | -0.140 |
Token | break |
Token ID | 2270 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
moons | +0.506 |
horm | +0.490 |
nerv | +0.477 |
mosqu | +0.464 |
behavi | +0.456 |
Neg logit contributions | |
abase | -0.365 |
rador | -0.269 |
MB | -0.262 |
CAD | -0.240 |
ielding | -0.239 |
Token | } |
Token ID | 1782 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
moons | +2.490 |
horm | +2.383 |
nerv | +2.304 |
mosqu | +2.179 |
behavi | +2.128 |
Neg logit contributions | |
abase | -3.669 |
rador | -2.974 |
MB | -2.926 |
ielding | -2.793 |
CAD | -2.761 |
Token | Left |
Token ID | 9578 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
moons | +0.047 |
horm | +0.046 |
nerv | +0.044 |
mosqu | +0.042 |
behavi | +0.041 |
Neg logit contributions | |
abase | -0.058 |
rador | -0.047 |
MB | -0.046 |
CAD | -0.043 |
ielding | -0.043 |
Token | { |
Token ID | 1391 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
abase | +1.272 |
rador | +1.007 |
MB | +0.998 |
CAD | +0.937 |
ielding | +0.925 |
Neg logit contributions | |
moons | -1.171 |
horm | -1.139 |
nerv | -1.095 |
mosqu | -1.067 |
behavi | -1.038 |
Token | $ |
Token ID | 720 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
abase | +1.587 |
MB | +1.144 |
rador | +1.135 |
CAD | +1.032 |
ielding | +0.997 |
Neg logit contributions | |
moons | -2.555 |
horm | -2.512 |
nerv | -2.432 |
mosqu | -2.384 |
behavi | -2.333 |
Token | s |
Token ID | 82 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
moons | +1.439 |
horm | +1.380 |
nerv | +1.324 |
mosqu | +1.273 |
behavi | +1.240 |
Neg logit contributions | |
abase | -2.013 |
rador | -1.643 |
MB | -1.624 |
CAD | -1.536 |
ielding | -1.521 |
Token | - |
Token ID | 12 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
moons | +0.057 |
horm | +0.055 |
nerv | +0.054 |
mosqu | +0.052 |
behavi | +0.051 |
Neg logit contributions | |
abase | -0.049 |
rador | -0.037 |
MB | -0.037 |
CAD | -0.034 |
ielding | -0.034 |
Token | im |
Token ID | 320 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
abase | +0.109 |
rador | +0.087 |
MB | +0.087 |
CAD | +0.081 |
ielding | +0.080 |
Neg logit contributions | |
moons | -0.091 |
horm | -0.088 |
nerv | -0.085 |
mosqu | -0.082 |
behavi | -0.080 |
Token | perial |
Token ID | 7629 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
moons | +0.235 |
horm | +0.229 |
nerv | +0.222 |
mosqu | +0.216 |
behavi | +0.211 |
Neg logit contributions | |
abase | -0.187 |
rador | -0.141 |
MB | -0.139 |
CAD | -0.129 |
ielding | -0.127 |
Token | ist |
Token ID | 396 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
moons | +0.282 |
horm | +0.272 |
nerv | +0.266 |
mosqu | +0.257 |
behavi | +0.250 |
Neg logit contributions | |
abase | -0.262 |
rador | -0.200 |
MB | -0.197 |
CAD | -0.184 |
ielding | -0.183 |
Token | sc |
Token ID | 629 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
abase | +0.384 |
rador | +0.305 |
MB | +0.302 |
CAD | +0.283 |
ielding | +0.280 |
Neg logit contributions | |
moons | -0.341 |
horm | -0.331 |
nerv | -0.319 |
mosqu | -0.309 |
behavi | -0.302 |
Token | ound |
Token ID | 633 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
moons | +0.391 |
horm | +0.370 |
nerv | +0.348 |
mosqu | +0.329 |
behavi | +0.313 |
Neg logit contributions | |
abase | -0.963 |
rador | -0.813 |
MB | -0.809 |
CAD | -0.775 |
ielding | -0.768 |
Token | rel |
Token ID | 2411 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
moons | +2.303 |
horm | +2.197 |
nerv | +2.063 |
mosqu | +1.951 |
behavi | +1.880 |
Neg logit contributions | |
abase | -3.832 |
MB | -3.083 |
rador | -3.058 |
CAD | -2.930 |
ielding | -2.873 |
Token | Vac |
Token ID | 25709 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
moons | +1.416 |
horm | +1.363 |
nerv | +1.318 |
mosqu | +1.266 |
behavi | +1.225 |
Neg logit contributions | |
abase | -1.642 |
rador | -1.313 |
MB | -1.280 |
CAD | -1.214 |
ielding | -1.212 |
Token | lav |
Token ID | 18809 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
abase | +1.343 |
rador | +1.103 |
MB | +1.097 |
CAD | +1.035 |
ielding | +1.028 |
Neg logit contributions | |
moons | -0.873 |
horm | -0.849 |
nerv | -0.808 |
mosqu | -0.787 |
behavi | -0.763 |
Token | Ha |
Token ID | 9398 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
moons | +0.873 |
horm | +0.845 |
nerv | +0.818 |
mosqu | +0.781 |
behavi | +0.766 |
Neg logit contributions | |
abase | -0.676 |
rador | -0.496 |
MB | -0.470 |
ielding | -0.447 |
CAD | -0.446 |
Token | vel |
Token ID | 626 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
abase | +0.341 |
rador | +0.255 |
MB | +0.252 |
CAD | +0.232 |
ielding | +0.229 |
Neg logit contributions | |
moons | -0.442 |
horm | -0.431 |
nerv | -0.418 |
mosqu | -0.407 |
behavi | -0.399 |
Token | : |
Token ID | 25 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
moons | +0.331 |
horm | +0.320 |
nerv | +0.308 |
mosqu | +0.298 |
behavi | +0.289 |
Neg logit contributions | |
abase | -0.431 |
rador | -0.348 |
MB | -0.345 |
CAD | -0.325 |
ielding | -0.322 |
Token | 50 |
Token ID | 1120 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
moons | +0.412 |
horm | +0.395 |
nerv | +0.381 |
mosqu | +0.359 |
behavi | +0.350 |
Neg logit contributions | |
abase | -0.548 |
rador | -0.443 |
MB | -0.434 |
CAD | -0.410 |
ielding | -0.410 |
Token | pur |
Token ID | 1308 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
abase | +0.264 |
rador | +0.216 |
MB | +0.215 |
CAD | +0.202 |
ielding | +0.200 |
Neg logit contributions | |
moons | -0.189 |
horm | -0.182 |
nerv | -0.174 |
mosqu | -0.169 |
behavi | -0.165 |
Token | ak |
Token ID | 461 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
moons | +0.682 |
horm | +0.652 |
nerv | +0.637 |
mosqu | +0.593 |
seiz | +0.578 |
Neg logit contributions | |
abase | -0.849 |
rador | -0.685 |
MB | -0.674 |
CAD | -0.637 |
ielding | -0.629 |
Token | ushi |
Token ID | 17731 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
moons | +0.716 |
horm | +0.696 |
nerv | +0.674 |
mosqu | +0.658 |
behavi | +0.645 |
Neg logit contributions | |
abase | -0.623 |
rador | -0.477 |
MB | -0.470 |
CAD | -0.435 |
ielding | -0.432 |
Token | wrote |
Token ID | 2630 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
abase | +0.033 |
rador | +0.026 |
MB | +0.026 |
CAD | +0.024 |
ielding | +0.024 |
Neg logit contributions | |
moons | -0.033 |
horm | -0.032 |
nerv | -0.031 |
mosqu | -0.030 |
behavi | -0.030 |
Token | : |
Token ID | 25 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
moons | +2.272 |
horm | +2.084 |
nerv | +2.076 |
Quake | +1.763 |
Sparrow | +1.749 |
Neg logit contributions | |
abase | -3.686 |
rador | -3.048 |
MB | -2.887 |
ielding | -2.816 |
CAD | -2.761 |
Token |
|
Token ID | 198 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
moons | +1.300 |
horm | +1.249 |
nerv | +1.207 |
mosqu | +1.144 |
behavi | +1.119 |
Neg logit contributions | |
abase | -1.600 |
rador | -1.284 |
MB | -1.260 |
CAD | -1.187 |
ielding | -1.183 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
moons | +1.263 |
horm | +1.192 |
nerv | +1.161 |
mosqu | +1.046 |
behavi | +1.034 |
Neg logit contributions | |
abase | -1.688 |
rador | -1.366 |
MB | -1.314 |
ielding | -1.252 |
CAD | -1.245 |
Token | Happy |
Token ID | 25082 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
moons | +1.150 |
horm | +1.106 |
nerv | +1.057 |
mosqu | +1.012 |
behavi | +0.979 |
Neg logit contributions | |
abase | -1.731 |
rador | -1.421 |
MB | -1.404 |
CAD | -1.331 |
ielding | -1.315 |
Token | it |
Token ID | 340 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
moons | +0.353 |
horm | +0.343 |
nerv | +0.331 |
mosqu | +0.321 |
behavi | +0.314 |
Neg logit contributions | |
abase | -0.354 |
rador | -0.277 |
MB | -0.274 |
CAD | -0.256 |
ielding | -0.253 |
Token | this |
Token ID | 428 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
moons | +0.136 |
horm | +0.131 |
nerv | +0.127 |
mosqu | +0.122 |
behavi | +0.119 |
Neg logit contributions | |
abase | -0.165 |
rador | -0.132 |
MB | -0.131 |
CAD | -0.123 |
ielding | -0.122 |
Token | article |
Token ID | 2708 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
moons | +0.141 |
horm | +0.137 |
nerv | +0.131 |
mosqu | +0.127 |
behavi | +0.124 |
Neg logit contributions | |
abase | -0.174 |
rador | -0.139 |
MB | -0.138 |
CAD | -0.130 |
ielding | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
abase | +0.313 |
rador | +0.253 |
MB | +0.251 |
CAD | +0.236 |
ielding | +0.234 |
Neg logit contributions | |
moons | -0.240 |
horm | -0.232 |
nerv | -0.223 |
mosqu | -0.216 |
behavi | -0.210 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
abase | +0.148 |
rador | +0.118 |
MB | +0.117 |
CAD | +0.109 |
ielding | +0.109 |
Neg logit contributions | |
moons | -0.126 |
horm | -0.122 |
nerv | -0.118 |
mosqu | -0.114 |
behavi | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
moons | +0.008 |
horm | +0.007 |
nerv | +0.007 |
mosqu | +0.007 |
behavi | +0.006 |
Neg logit contributions | |
abase | -0.010 |
rador | -0.008 |
MB | -0.008 |
CAD | -0.007 |
ielding | -0.007 |
Token | NOTE |
Token ID | 16580 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
moons | +0.039 |
horm | +0.037 |
nerv | +0.036 |
mosqu | +0.034 |
behavi | +0.034 |
Neg logit contributions | |
abase | -0.050 |
rador | -0.040 |
MB | -0.040 |
CAD | -0.037 |
ielding | -0.037 |
Token | : |
Token ID | 25 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
moons | +2.431 |
horm | +2.338 |
nerv | +2.268 |
mosqu | +2.136 |
behavi | +2.074 |
Neg logit contributions | |
abase | -3.514 |
rador | -2.850 |
MB | -2.743 |
ielding | -2.647 |
CAD | -2.602 |
Token | Also |
Token ID | 4418 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
moons | +0.286 |
horm | +0.277 |
nerv | +0.267 |
mosqu | +0.258 |
behavi | +0.251 |
Neg logit contributions | |
abase | -0.331 |
rador | -0.264 |
MB | -0.260 |
CAD | -0.245 |
ielding | -0.243 |
Token | , |
Token ID | 11 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
moons | +0.623 |
horm | +0.602 |
nerv | +0.581 |
mosqu | +0.559 |
behavi | +0.544 |
Neg logit contributions | |
abase | -0.739 |
rador | -0.590 |
MB | -0.580 |
CAD | -0.547 |
ielding | -0.545 |
Token | it |
Token ID | 340 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
moons | +0.330 |
horm | +0.319 |
nerv | +0.306 |
mosqu | +0.296 |
behavi | +0.287 |
Neg logit contributions | |
abase | -0.434 |
rador | -0.351 |
MB | -0.347 |
CAD | -0.327 |
ielding | -0.325 |
Token | should |
Token ID | 815 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
moons | +0.176 |
horm | +0.171 |
nerv | +0.164 |
mosqu | +0.159 |
behavi | +0.155 |
Neg logit contributions | |
abase | -0.217 |
rador | -0.174 |
MB | -0.173 |
CAD | -0.163 |
ielding | -0.161 |
Token | [ |
Token ID | 685 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
moons | +0.192 |
horm | +0.187 |
nerv | +0.181 |
mosqu | +0.176 |
behavi | +0.172 |
Neg logit contributions | |
abase | -0.182 |
rador | -0.141 |
MB | -0.140 |
CAD | -0.130 |
ielding | -0.128 |
Token | 10 |
Token ID | 940 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
abase | +0.083 |
rador | +0.067 |
MB | +0.067 |
CAD | +0.063 |
ielding | +0.062 |
Neg logit contributions | |
moons | -0.063 |
horm | -0.061 |
nerv | -0.058 |
mosqu | -0.056 |
behavi | -0.055 |
Token | : |
Token ID | 25 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
moons | +0.711 |
horm | +0.665 |
nerv | +0.649 |
mosqu | +0.574 |
seiz | +0.561 |
Neg logit contributions | |
abase | -1.052 |
rador | -0.861 |
MB | -0.828 |
ielding | -0.795 |
CAD | -0.789 |
Token | 47 |
Token ID | 2857 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
moons | +1.066 |
horm | +1.022 |
nerv | +0.987 |
mosqu | +0.952 |
behavi | +0.916 |
Neg logit contributions | |
abase | -1.478 |
rador | -1.200 |
MB | -1.168 |
CAD | -1.115 |
ielding | -1.110 |
Token | ] |
Token ID | 60 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
moons | +1.800 |
horm | +1.681 |
nerv | +1.667 |
Sparrow | +1.496 |
Quake | +1.495 |
Neg logit contributions | |
abase | -1.685 |
rador | -1.304 |
MB | -1.210 |
ielding | -1.164 |
olesc | -1.137 |
Token | <@ |
Token ID | 32406 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
moons | +1.630 |
horm | +1.588 |
nerv | +1.542 |
mosqu | +1.507 |
behavi | +1.473 |
Neg logit contributions | |
abase | -1.176 |
rador | -0.869 |
MB | -0.850 |
CAD | -0.778 |
ielding | -0.774 |
Token | t |
Token ID | 83 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
moons | +2.749 |
horm | +2.654 |
nerv | +2.528 |
mosqu | +2.438 |
seiz | +2.352 |
Neg logit contributions | |
abase | -3.131 |
rador | -2.512 |
MB | -2.476 |
CAD | -2.344 |
ielding | -2.287 |
Token | ay |
Token ID | 323 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
moons | +0.677 |
horm | +0.656 |
nerv | +0.634 |
mosqu | +0.622 |
behavi | +0.610 |
Neg logit contributions | |
abase | -0.685 |
rador | -0.535 |
MB | -0.529 |
CAD | -0.493 |
ielding | -0.492 |
Token | l |
Token ID | 75 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
moons | +0.052 |
horm | +0.051 |
nerv | +0.049 |
mosqu | +0.047 |
behavi | +0.046 |
Neg logit contributions | |
abase | -0.054 |
rador | -0.043 |
MB | -0.042 |
CAD | -0.040 |
ielding | -0.039 |
Token | ort |
Token ID | 419 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
moons | +0.805 |
horm | +0.775 |
nerv | +0.741 |
mosqu | +0.713 |
behavi | +0.690 |
Neg logit contributions | |
abase | -1.267 |
rador | -1.040 |
MB | -1.032 |
CAD | -0.978 |
ielding | -0.970 |
Token | ot |
Token ID | 313 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
abase | +0.182 |
rador | +0.143 |
MB | +0.141 |
CAD | +0.132 |
ielding | +0.131 |
Neg logit contributions | |
moons | -0.175 |
horm | -0.170 |
nerv | -0.164 |
mosqu | -0.160 |
behavi | -0.156 |
Token | MI |
Token ID | 8895 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
moons | +0.288 |
horm | +0.276 |
nerv | +0.263 |
mosqu | +0.251 |
behavi | +0.244 |
Neg logit contributions | |
abase | -0.502 |
rador | -0.415 |
MB | -0.411 |
CAD | -0.390 |
ielding | -0.388 |
Token | ≤ |
Token ID | 41305 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
abase | +0.540 |
rador | +0.414 |
MB | +0.404 |
CAD | +0.373 |
ielding | +0.370 |
Neg logit contributions | |
moons | -0.629 |
horm | -0.610 |
nerv | -0.595 |
mosqu | -0.572 |
behavi | -0.561 |
Token | 24 |
Token ID | 1731 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
abase | +0.185 |
rador | +0.140 |
MB | +0.136 |
CAD | +0.126 |
ielding | +0.125 |
Neg logit contributions | |
moons | -0.230 |
horm | -0.223 |
nerv | -0.218 |
mosqu | -0.210 |
behavi | -0.206 |
Token | . |
Token ID | 13 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
abase | +0.360 |
rador | +0.286 |
MB | +0.282 |
CAD | +0.264 |
ielding | +0.262 |
Neg logit contributions | |
moons | -0.324 |
horm | -0.313 |
nerv | -0.303 |
mosqu | -0.292 |
behavi | -0.285 |
Token | 99 |
Token ID | 2079 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
moons | +0.447 |
horm | +0.430 |
nerv | +0.415 |
mosqu | +0.396 |
behavi | +0.385 |
Neg logit contributions | |
abase | -0.629 |
rador | -0.511 |
MB | -0.504 |
CAD | -0.476 |
ielding | -0.475 |
Token | kg |
Token ID | 14211 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
moons | +1.337 |
horm | +1.289 |
nerv | +1.267 |
mosqu | +1.212 |
behavi | +1.191 |
Neg logit contributions | |
abase | -1.027 |
rador | -0.771 |
MB | -0.737 |
ielding | -0.679 |
CAD | -0.674 |
Token | / |
Token ID | 14 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
moons | +2.888 |
horm | +2.717 |
nerv | +2.708 |
mosqu | +2.531 |
seiz | +2.482 |
Neg logit contributions | |
abase | -2.927 |
rador | -2.318 |
MB | -2.201 |
xes | -2.059 |
ielding | -2.046 |
Token | m |
Token ID | 76 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
moons | +0.177 |
horm | +0.172 |
nerv | +0.165 |
mosqu | +0.160 |
behavi | +0.156 |
Neg logit contributions | |
abase | -0.195 |
rador | -0.155 |
MB | -0.152 |
CAD | -0.143 |
ielding | -0.142 |
Token | ² |
Token ID | 31185 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
moons | +0.477 |
horm | +0.458 |
nerv | +0.442 |
mosqu | +0.421 |
behavi | +0.408 |
Neg logit contributions | |
abase | -0.575 |
rador | -0.465 |
MB | -0.454 |
CAD | -0.426 |
ielding | -0.422 |
Token | ), |
Token ID | 828 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
abase | +0.049 |
rador | +0.037 |
MB | +0.036 |
CAD | +0.032 |
ielding | +0.032 |
Neg logit contributions | |
moons | -0.068 |
horm | -0.066 |
nerv | -0.064 |
mosqu | -0.062 |
behavi | -0.061 |
Token | overweight |
Token ID | 22652 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
moons | +0.204 |
horm | +0.198 |
nerv | +0.192 |
mosqu | +0.185 |
behavi | +0.181 |
Neg logit contributions | |
abase | -0.222 |
rador | -0.175 |
MB | -0.173 |
CAD | -0.162 |
ielding | -0.161 |
Token | amazing |
Token ID | 4998 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
moons | +0.131 |
horm | +0.126 |
nerv | +0.122 |
mosqu | +0.117 |
behavi | +0.114 |
Neg logit contributions | |
abase | -0.161 |
rador | -0.130 |
MB | -0.128 |
CAD | -0.120 |
ielding | -0.120 |
Token | I |
Token ID | 314 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
abase | +0.198 |
rador | +0.159 |
MB | +0.158 |
CAD | +0.148 |
ielding | +0.147 |
Neg logit contributions | |
moons | -0.162 |
horm | -0.157 |
nerv | -0.151 |
mosqu | -0.146 |
behavi | -0.142 |
Token | 've |
Token ID | 1053 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
moons | +0.153 |
horm | +0.147 |
nerv | +0.142 |
mosqu | +0.136 |
behavi | +0.132 |
Neg logit contributions | |
abase | -0.189 |
rador | -0.151 |
MB | -0.149 |
CAD | -0.140 |
ielding | -0.140 |
Token | been |
Token ID | 587 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
moons | +0.052 |
horm | +0.050 |
nerv | +0.049 |
mosqu | +0.046 |
seiz | +0.045 |
Neg logit contributions | |
abase | -0.059 |
rador | -0.047 |
MB | -0.045 |
ielding | -0.043 |
CAD | -0.043 |
Token | ch |
Token ID | 442 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
moons | +0.131 |
horm | +0.127 |
nerv | +0.122 |
mosqu | +0.117 |
behavi | +0.114 |
Neg logit contributions | |
abase | -0.161 |
rador | -0.129 |
MB | -0.128 |
CAD | -0.120 |
ielding | -0.119 |
Token | omp |
Token ID | 3361 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
abase | +0.435 |
rador | +0.345 |
MB | +0.343 |
CAD | +0.320 |
ielding | +0.316 |
Neg logit contributions | |
moons | -0.383 |
horm | -0.370 |
nerv | -0.358 |
mosqu | -0.343 |
behavi | -0.333 |
Token | ing |
Token ID | 278 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
moons | +2.697 |
horm | +2.526 |
nerv | +2.470 |
mosqu | +2.281 |
behavi | +2.270 |
Neg logit contributions | |
abase | -3.086 |
rador | -2.454 |
MB | -2.386 |
CAD | -2.221 |
ielding | -2.196 |
Token | at |
Token ID | 379 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
moons | +0.456 |
horm | +0.439 |
nerv | +0.428 |
mosqu | +0.411 |
behavi | +0.405 |
Neg logit contributions | |
abase | -0.367 |
rador | -0.279 |
MB | -0.273 |
ielding | -0.253 |
CAD | -0.251 |
Token | the |
Token ID | 262 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
abase | +0.298 |
rador | +0.240 |
MB | +0.237 |
CAD | +0.223 |
ielding | +0.222 |
Neg logit contributions | |
moons | -0.239 |
horm | -0.230 |
nerv | -0.222 |
mosqu | -0.214 |
behavi | -0.208 |
Token | bit |
Token ID | 1643 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
moons | +0.077 |
horm | +0.075 |
nerv | +0.073 |
mosqu | +0.071 |
behavi | +0.070 |
Neg logit contributions | |
abase | -0.051 |
rador | -0.037 |
MB | -0.036 |
CAD | -0.033 |
ielding | -0.032 |
Token | for |
Token ID | 329 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
abase | +0.310 |
rador | +0.251 |
MB | +0.248 |
CAD | +0.234 |
ielding | +0.232 |
Neg logit contributions | |
moons | -0.230 |
horm | -0.222 |
nerv | -0.214 |
mosqu | -0.205 |
behavi | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
moons | +0.598 |
horm | +0.576 |
nerv | +0.552 |
mosqu | +0.531 |
behavi | +0.516 |
Neg logit contributions | |
abase | -0.875 |
rador | -0.714 |
MB | -0.708 |
CAD | -0.669 |
ielding | -0.664 |
Token | I |
Token ID | 314 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
abase | +0.100 |
rador | +0.080 |
MB | +0.080 |
CAD | +0.075 |
ielding | +0.074 |
Neg logit contributions | |
moons | -0.084 |
horm | -0.082 |
nerv | -0.079 |
mosqu | -0.076 |
behavi | -0.074 |
Token | had |
Token ID | 550 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
moons | +0.198 |
horm | +0.191 |
nerv | +0.184 |
mosqu | +0.177 |
behavi | +0.172 |
Neg logit contributions | |
abase | -0.261 |
rador | -0.211 |
MB | -0.209 |
CAD | -0.197 |
ielding | -0.196 |
Token | the |
Token ID | 262 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
abase | +0.313 |
rador | +0.249 |
MB | +0.245 |
CAD | +0.230 |
ielding | +0.230 |
Neg logit contributions | |
moons | -0.271 |
horm | -0.262 |
nerv | -0.253 |
mosqu | -0.244 |
behavi | -0.237 |
Token | 10 |
Token ID | 838 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
moons | +0.706 |
horm | +0.681 |
nerv | +0.657 |
mosqu | +0.634 |
behavi | +0.616 |
Neg logit contributions | |
abase | -0.820 |
rador | -0.654 |
MB | -0.642 |
ielding | -0.606 |
CAD | -0.605 |
Token | " |
Token ID | 1 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
moons | +0.770 |
horm | +0.747 |
nerv | +0.721 |
mosqu | +0.699 |
behavi | +0.681 |
Neg logit contributions | |
abase | -0.852 |
rador | -0.675 |
MB | -0.669 |
CAD | -0.626 |
ielding | -0.620 |
Token | 150 |
Token ID | 6640 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
moons | +2.594 |
horm | +2.478 |
nerv | +2.393 |
mosqu | +2.289 |
seiz | +2.235 |
Neg logit contributions | |
abase | -3.077 |
rador | -2.457 |
MB | -2.370 |
ielding | -2.290 |
CAD | -2.256 |
Token | watt |
Token ID | 40114 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
moons | +0.017 |
horm | +0.017 |
nerv | +0.016 |
mosqu | +0.015 |
behavi | +0.015 |
Neg logit contributions | |
abase | -0.024 |
rador | -0.019 |
MB | -0.019 |
CAD | -0.018 |
ielding | -0.018 |
Token | J |
Token ID | 449 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
moons | +0.488 |
horm | +0.471 |
nerv | +0.454 |
mosqu | +0.438 |
behavi | +0.426 |
Neg logit contributions | |
abase | -0.577 |
rador | -0.461 |
MB | -0.453 |
CAD | -0.427 |
ielding | -0.426 |
Token | BL |
Token ID | 9148 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
moons | +0.012 |
horm | +0.012 |
nerv | +0.011 |
mosqu | +0.011 |
behavi | +0.010 |
Neg logit contributions | |
abase | -0.014 |
rador | -0.011 |
MB | -0.011 |
CAD | -0.011 |
ielding | -0.011 |
Token | before |
Token ID | 878 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
moons | +0.135 |
horm | +0.131 |
nerv | +0.127 |
mosqu | +0.123 |
behavi | +0.119 |
Neg logit contributions | |
abase | -0.155 |
rador | -0.124 |
MB | -0.122 |
CAD | -0.115 |
ielding | -0.114 |
Token | this |
Token ID | 428 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
moons | +0.363 |
horm | +0.351 |
nerv | +0.338 |
mosqu | +0.326 |
behavi | +0.318 |
Neg logit contributions | |
abase | -0.427 |
rador | -0.341 |
MB | -0.336 |
CAD | -0.316 |
ielding | -0.314 |
Token | thing |
Token ID | 1517 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
moons | +0.522 |
horm | +0.506 |
nerv | +0.486 |
mosqu | +0.469 |
behavi | +0.458 |
Neg logit contributions | |
abase | -0.626 |
rador | -0.501 |
MB | -0.495 |
CAD | -0.464 |
ielding | -0.462 |
Token | . |
Token ID | 13 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
moons | +0.468 |
horm | +0.452 |
nerv | +0.434 |
mosqu | +0.419 |
behavi | +0.407 |
Neg logit contributions | |
abase | -0.629 |
rador | -0.510 |
MB | -0.505 |
CAD | -0.476 |
ielding | -0.472 |
Token |
|
Token ID | 198 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
moons | +0.331 |
horm | +0.320 |
nerv | +0.309 |
mosqu | +0.298 |
behavi | +0.291 |
Neg logit contributions | |
abase | -0.364 |
rador | -0.288 |
MB | -0.283 |
CAD | -0.265 |
ielding | -0.264 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
moons | +0.116 |
horm | +0.110 |
nerv | +0.107 |
mosqu | +0.098 |
behavi | +0.096 |
Neg logit contributions | |
abase | -0.150 |
rador | -0.121 |
MB | -0.117 |
ielding | -0.111 |
CAD | -0.111 |
Token | IGN |
Token ID | 16284 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
moons | +0.082 |
horm | +0.080 |
nerv | +0.076 |
mosqu | +0.074 |
behavi | +0.072 |
Neg logit contributions | |
abase | -0.112 |
rador | -0.091 |
MB | -0.090 |
CAD | -0.085 |
ielding | -0.085 |
Token | : |
Token ID | 25 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
moons | +2.135 |
horm | +1.949 |
nerv | +1.926 |
Sparrow | +1.669 |
Quake | +1.649 |
Neg logit contributions | |
abase | -3.446 |
rador | -2.821 |
MB | -2.697 |
ielding | -2.619 |
CAD | -2.572 |
Token | The |
Token ID | 383 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
moons | +0.949 |
horm | +0.914 |
nerv | +0.881 |
mosqu | +0.844 |
behavi | +0.821 |
Neg logit contributions | |
abase | -1.178 |
rador | -0.949 |
MB | -0.930 |
ielding | -0.876 |
CAD | -0.876 |
Token | armour |
Token ID | 18588 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
moons | +0.506 |
horm | +0.488 |
nerv | +0.468 |
mosqu | +0.451 |
behavi | +0.439 |
Neg logit contributions | |
abase | -0.696 |
rador | -0.565 |
MB | -0.559 |
CAD | -0.528 |
ielding | -0.524 |
Token | option |
Token ID | 3038 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
moons | +0.330 |
horm | +0.320 |
nerv | +0.307 |
mosqu | +0.296 |
behavi | +0.289 |
Neg logit contributions | |
abase | -0.406 |
rador | -0.326 |
MB | -0.322 |
CAD | -0.303 |
ielding | -0.301 |
Token | � |
Token ID | 447 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
abase | +0.976 |
rador | +0.777 |
MB | +0.774 |
CAD | +0.725 |
ielding | +0.716 |
Neg logit contributions | |
moons | -0.828 |
horm | -0.804 |
nerv | -0.773 |
mosqu | -0.754 |
behavi | -0.734 |
Token | ieving |
Token ID | 30749 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
moons | +0.558 |
horm | +0.537 |
nerv | +0.521 |
mosqu | +0.501 |
seiz | +0.489 |
Neg logit contributions | |
abase | -0.593 |
rador | -0.468 |
MB | -0.467 |
CAD | -0.434 |
ielding | -0.426 |
Token | Hollywood |
Token ID | 8502 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
moons | +0.593 |
horm | +0.572 |
nerv | +0.555 |
mosqu | +0.533 |
behavi | +0.519 |
Neg logit contributions | |
abase | -0.680 |
rador | -0.541 |
MB | -0.531 |
CAD | -0.499 |
ielding | -0.498 |
Token | agent |
Token ID | 5797 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
moons | +0.131 |
horm | +0.127 |
nerv | +0.123 |
mosqu | +0.118 |
behavi | +0.115 |
Neg logit contributions | |
abase | -0.157 |
rador | -0.126 |
MB | -0.124 |
CAD | -0.117 |
ielding | -0.116 |
Token | and |
Token ID | 290 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
moons | +1.266 |
horm | +1.217 |
nerv | +1.184 |
mosqu | +1.138 |
behavi | +1.106 |
Neg logit contributions | |
abase | -1.417 |
rador | -1.126 |
MB | -1.103 |
CAD | -1.037 |
ielding | -1.033 |
Token | anthrop |
Token ID | 17911 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
moons | +0.496 |
horm | +0.477 |
nerv | +0.464 |
mosqu | +0.444 |
behavi | +0.433 |
Neg logit contributions | |
abase | -0.610 |
rador | -0.489 |
MB | -0.481 |
CAD | -0.453 |
ielding | -0.451 |
Token | omorphic |
Token ID | 46374 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
moons | +0.298 |
horm | +0.290 |
nerv | +0.284 |
mosqu | +0.276 |
behavi | +0.269 |
Neg logit contributions | |
abase | -0.193 |
rador | -0.139 |
MB | -0.137 |
CAD | -0.125 |
ielding | -0.123 |
Token | cat |
Token ID | 3797 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
moons | +2.489 |
horm | +2.376 |
nerv | +2.325 |
mosqu | +2.183 |
behavi | +2.114 |
Neg logit contributions | |
abase | -3.113 |
rador | -2.468 |
MB | -2.392 |
ielding | -2.295 |
CAD | -2.260 |
Token | Princess |
Token ID | 8449 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
moons | +0.653 |
horm | +0.630 |
nerv | +0.607 |
mosqu | +0.586 |
behavi | +0.570 |
Neg logit contributions | |
abase | -0.812 |
rador | -0.651 |
MB | -0.645 |
CAD | -0.608 |
ielding | -0.603 |
Token | Carolyn |
Token ID | 43450 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
abase | +0.465 |
rador | +0.367 |
MB | +0.363 |
CAD | +0.340 |
ielding | +0.337 |
Neg logit contributions | |
moons | -0.432 |
horm | -0.419 |
nerv | -0.405 |
mosqu | -0.393 |
behavi | -0.383 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
abase | +0.267 |
rador | +0.217 |
MB | +0.217 |
CAD | +0.204 |
ielding | +0.202 |
Neg logit contributions | |
moons | -0.190 |
horm | -0.185 |
nerv | -0.176 |
mosqu | -0.171 |
behavi | -0.166 |
Token | She |
Token ID | 1375 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
abase | +0.100 |
rador | +0.079 |
MB | +0.078 |
CAD | +0.074 |
ielding | +0.073 |
Neg logit contributions | |
moons | -0.086 |
horm | -0.084 |
nerv | -0.081 |
mosqu | -0.078 |
behavi | -0.076 |
Token | that |
Token ID | 326 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
moons | +0.246 |
horm | +0.238 |
nerv | +0.229 |
mosqu | +0.221 |
behavi | +0.215 |
Neg logit contributions | |
abase | -0.293 |
rador | -0.235 |
MB | -0.231 |
CAD | -0.217 |
ielding | -0.217 |
Token | is |
Token ID | 318 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
abase | +0.018 |
rador | +0.014 |
MB | +0.014 |
CAD | +0.013 |
ielding | +0.013 |
Neg logit contributions | |
moons | -0.016 |
horm | -0.015 |
nerv | -0.015 |
mosqu | -0.014 |
behavi | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
moons | +0.103 |
horm | +0.100 |
nerv | +0.096 |
mosqu | +0.094 |
behavi | +0.091 |
Neg logit contributions | |
abase | -0.106 |
rador | -0.083 |
MB | -0.082 |
CAD | -0.077 |
ielding | -0.076 |
Token | for |
Token ID | 329 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
abase | +0.464 |
rador | +0.372 |
MB | +0.369 |
CAD | +0.347 |
ielding | +0.343 |
Neg logit contributions | |
moons | -0.379 |
horm | -0.367 |
nerv | -0.353 |
mosqu | -0.342 |
behavi | -0.333 |
Token | Michael |
Token ID | 3899 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
abase | +0.398 |
rador | +0.318 |
MB | +0.315 |
CAD | +0.295 |
ielding | +0.293 |
Neg logit contributions | |
moons | -0.336 |
horm | -0.325 |
nerv | -0.313 |
mosqu | -0.303 |
behavi | -0.295 |
Token | Ign |
Token ID | 16583 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
moons | +0.445 |
horm | +0.431 |
nerv | +0.415 |
mosqu | +0.401 |
behavi | +0.390 |
Neg logit contributions | |
abase | -0.485 |
rador | -0.385 |
MB | -0.376 |
CAD | -0.354 |
ielding | -0.352 |
Token | at |
Token ID | 265 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
moons | +2.706 |
horm | +2.560 |
nerv | +2.544 |
seiz | +2.342 |
mosqu | +2.241 |
Neg logit contributions | |
abase | -2.756 |
rador | -2.119 |
MB | -2.030 |
CAD | -1.954 |
ielding | -1.853 |
Token | ie |
Token ID | 494 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
abase | +0.194 |
rador | +0.158 |
MB | +0.156 |
CAD | +0.149 |
ielding | +0.147 |
Neg logit contributions | |
moons | -0.133 |
horm | -0.128 |
nerv | -0.123 |
mosqu | -0.117 |
behavi | -0.114 |
Token | ff |
Token ID | 487 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
moons | +0.356 |
horm | +0.345 |
nerv | +0.335 |
mosqu | +0.324 |
behavi | +0.318 |
Neg logit contributions | |
abase | -0.313 |
rador | -0.242 |
MB | -0.233 |
CAD | -0.217 |
ielding | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
moons | +0.851 |
horm | +0.820 |
nerv | +0.791 |
mosqu | +0.761 |
behavi | +0.741 |
Neg logit contributions | |
abase | -1.108 |
rador | -0.895 |
MB | -0.882 |
CAD | -0.833 |
ielding | -0.827 |
Token | At |
Token ID | 1629 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
abase | +0.013 |
MB | +0.010 |
rador | +0.010 |
CAD | +0.009 |
ielding | +0.009 |
Neg logit contributions | |
moons | -0.011 |
horm | -0.011 |
nerv | -0.010 |
mosqu | -0.010 |
behavi | -0.010 |
Token | m |
Token ID | 76 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
moons | +1.466 |
horm | +1.424 |
nerv | +1.371 |
mosqu | +1.322 |
behavi | +1.281 |
Neg logit contributions | |
abase | -1.594 |
rador | -1.265 |
MB | -1.254 |
CAD | -1.179 |
ielding | -1.159 |
Token | ew |
Token ID | 413 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
moons | +1.105 |
horm | +1.074 |
nerv | +1.040 |
mosqu | +0.999 |
seiz | +0.966 |
Neg logit contributions | |
abase | -1.157 |
rador | -0.911 |
MB | -0.907 |
CAD | -0.849 |
ielding | -0.835 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
moons | +1.241 |
horm | +1.201 |
nerv | +1.161 |
mosqu | +1.113 |
seiz | +1.078 |
Neg logit contributions | |
abase | -1.308 |
rador | -1.028 |
MB | -1.022 |
CAD | -0.957 |
ielding | -0.938 |
Token | king |
Token ID | 3364 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
abase | +0.334 |
rador | +0.263 |
MB | +0.261 |
CAD | +0.244 |
ielding | +0.241 |
Neg logit contributions | |
moons | -0.312 |
horm | -0.303 |
nerv | -0.292 |
mosqu | -0.283 |
behavi | -0.276 |
Token | > |
Token ID | 29 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
moons | +0.036 |
horm | +0.035 |
nerv | +0.034 |
mosqu | +0.033 |
behavi | +0.032 |
Neg logit contributions | |
abase | -0.032 |
rador | -0.024 |
MB | -0.024 |
CAD | -0.022 |
ielding | -0.022 |
Token | OM |
Token ID | 32468 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
moons | +0.541 |
horm | +0.523 |
nerv | +0.502 |
mosqu | +0.484 |
behavi | +0.471 |
Neg logit contributions | |
abase | -0.748 |
rador | -0.607 |
MB | -0.602 |
CAD | -0.568 |
ielding | -0.563 |
Token | FG |
Token ID | 30386 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
moons | +2.400 |
horm | +2.303 |
nerv | +2.239 |
mosqu | +2.142 |
behavi | +2.074 |
Neg logit contributions | |
abase | -3.067 |
rador | -2.475 |
MB | -2.410 |
ielding | -2.281 |
CAD | -2.262 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
moons | +0.359 |
horm | +0.349 |
nerv | +0.337 |
mosqu | +0.327 |
behavi | +0.319 |
Neg logit contributions | |
abase | -0.361 |
rador | -0.282 |
MB | -0.279 |
CAD | -0.260 |
ielding | -0.258 |
Token | By |
Token ID | 3886 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
moons | +0.325 |
horm | +0.314 |
nerv | +0.301 |
mosqu | +0.290 |
behavi | +0.282 |
Neg logit contributions | |
abase | -0.393 |
rador | -0.315 |
MB | -0.311 |
CAD | -0.293 |
ielding | -0.290 |
Token | Andrew |
Token ID | 6858 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
abase | +0.331 |
rador | +0.262 |
MB | +0.259 |
CAD | +0.243 |
ielding | +0.240 |
Neg logit contributions | |
moons | -0.304 |
horm | -0.295 |
nerv | -0.284 |
mosqu | -0.276 |
behavi | -0.269 |
Token | Benson |
Token ID | 33940 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
abase | +0.251 |
rador | +0.199 |
MB | +0.198 |
CAD | +0.185 |
ielding | +0.183 |
Neg logit contributions | |
moons | -0.224 |
horm | -0.217 |
nerv | -0.210 |
mosqu | -0.203 |
behavi | -0.198 |
Token | oring |
Token ID | 3255 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
abase | +0.046 |
rador | +0.032 |
MB | +0.032 |
CAD | +0.028 |
ielding | +0.028 |
Neg logit contributions | |
moons | -0.081 |
horm | -0.079 |
nerv | -0.077 |
mosqu | -0.075 |
behavi | -0.074 |
Token | fans |
Token ID | 3296 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
moons | +0.396 |
horm | +0.384 |
nerv | +0.369 |
mosqu | +0.358 |
behavi | +0.348 |
Neg logit contributions | |
abase | -0.497 |
rador | -0.400 |
MB | -0.398 |
CAD | -0.374 |
ielding | -0.371 |
Token | wanting |
Token ID | 10291 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
abase | +1.133 |
MB | +0.911 |
rador | +0.906 |
CAD | +0.852 |
ielding | +0.849 |
Neg logit contributions | |
moons | -0.904 |
horm | -0.892 |
nerv | -0.839 |
mosqu | -0.830 |
behavi | -0.804 |
Token | his |
Token ID | 465 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
moons | +0.512 |
horm | +0.494 |
nerv | +0.475 |
mosqu | +0.459 |
behavi | +0.446 |
Neg logit contributions | |
abase | -0.678 |
rador | -0.548 |
MB | -0.543 |
CAD | -0.512 |
ielding | -0.507 |
Token | aut |
Token ID | 1960 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
abase | +0.655 |
MB | +0.536 |
rador | +0.533 |
CAD | +0.506 |
ielding | +0.499 |
Neg logit contributions | |
moons | -0.450 |
horm | -0.439 |
nerv | -0.417 |
mosqu | -0.407 |
behavi | -0.393 |
Token | ograph |
Token ID | 2384 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
moons | +0.265 |
horm | +0.258 |
nerv | +0.250 |
mosqu | +0.243 |
behavi | +0.238 |
Neg logit contributions | |
abase | -0.225 |
rador | -0.171 |
MB | -0.169 |
CAD | -0.156 |
ielding | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
moons | +2.250 |
horm | +2.120 |
nerv | +2.070 |
mosqu | +1.956 |
behavi | +1.902 |
Neg logit contributions | |
abase | -3.217 |
rador | -2.627 |
MB | -2.551 |
CAD | -2.436 |
ielding | -2.432 |
Token | and |
Token ID | 290 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
abase | +0.308 |
rador | +0.251 |
MB | +0.250 |
CAD | +0.236 |
ielding | +0.234 |
Neg logit contributions | |
moons | -0.214 |
horm | -0.208 |
nerv | -0.198 |
mosqu | -0.192 |
behavi | -0.186 |
Token | so |
Token ID | 523 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
moons | +0.059 |
horm | +0.057 |
nerv | +0.055 |
mosqu | +0.053 |
behavi | +0.051 |
Neg logit contributions | |
abase | -0.082 |
rador | -0.067 |
MB | -0.066 |
CAD | -0.062 |
ielding | -0.062 |
Token | he |
Token ID | 339 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
moons | +0.476 |
horm | +0.457 |
nerv | +0.441 |
mosqu | +0.422 |
behavi | +0.412 |
Neg logit contributions | |
abase | -0.646 |
rador | -0.524 |
MB | -0.516 |
CAD | -0.489 |
ielding | -0.484 |
Token | drinks |
Token ID | 11758 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
moons | +0.247 |
horm | +0.239 |
nerv | +0.230 |
mosqu | +0.222 |
behavi | +0.216 |
Neg logit contributions | |
abase | -0.306 |
rador | -0.246 |
MB | -0.243 |
CAD | -0.229 |
ielding | -0.227 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
abase | +1.286 |
rador | +1.026 |
MB | +1.022 |
CAD | +0.958 |
ielding | +0.948 |
Neg logit contributions | |
moons | -1.101 |
horm | -1.070 |
nerv | -1.028 |
mosqu | -1.000 |
behavi | -0.973 |
Token | massive |
Token ID | 4858 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
abase | +0.108 |
rador | +0.086 |
MB | +0.085 |
CAD | +0.080 |
ielding | +0.079 |
Neg logit contributions | |
moons | -0.086 |
horm | -0.082 |
nerv | -0.080 |
mosqu | -0.076 |
behavi | -0.074 |
Token | audience |
Token ID | 5386 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
abase | +0.314 |
rador | +0.252 |
MB | +0.248 |
CAD | +0.234 |
ielding | +0.232 |
Neg logit contributions | |
moons | -0.250 |
horm | -0.241 |
nerv | -0.233 |
mosqu | -0.223 |
behavi | -0.217 |
Token | -- |
Token ID | 1377 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
abase | +0.313 |
rador | +0.255 |
MB | +0.255 |
CAD | +0.241 |
ielding | +0.238 |
Neg logit contributions | |
moons | -0.212 |
horm | -0.206 |
nerv | -0.196 |
mosqu | -0.191 |
behavi | -0.184 |
Token | and |
Token ID | 290 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
moons | +0.424 |
horm | +0.410 |
nerv | +0.392 |
mosqu | +0.379 |
behavi | +0.368 |
Neg logit contributions | |
abase | -0.601 |
rador | -0.489 |
MB | -0.485 |
CAD | -0.459 |
ielding | -0.455 |
Token | whichever |
Token ID | 26204 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
abase | +0.567 |
rador | +0.458 |
MB | +0.458 |
CAD | +0.431 |
ielding | +0.426 |
Neg logit contributions | |
moons | -0.420 |
horm | -0.409 |
nerv | -0.392 |
mosqu | -0.381 |
behavi | -0.370 |
Token | prevailed |
Token ID | 34429 |
Feature activation | -2.71e-03 |
Pos logit contributions | |
moons | +2.703 |
horm | +2.592 |
nerv | +2.523 |
mosqu | +2.406 |
behavi | +2.350 |
Neg logit contributions | |
abase | -2.797 |
rador | -2.204 |
MB | -2.089 |
ielding | -1.995 |
CAD | -1.994 |
Token | would |
Token ID | 561 |
Feature activation | -1.01e-03 |
Pos logit contributions | |
moons | +0.002 |
horm | +0.002 |
nerv | +0.002 |
mosqu | +0.002 |
behavi | +0.002 |
Neg logit contributions | |
abase | -0.003 |
MB | -0.002 |
rador | -0.002 |
CAD | -0.002 |
ielding | -0.002 |
Token | be |
Token ID | 307 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
moons | +0.001 |
horm | +0.001 |
nerv | +0.001 |
mosqu | +0.001 |
behavi | +0.001 |
Neg logit contributions | |
abase | -0.001 |
rador | -0.001 |
MB | -0.001 |
CAD | -0.001 |
ielding | -0.001 |
Token | required |
Token ID | 2672 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
moons | +0.222 |
horm | +0.215 |
nerv | +0.207 |
mosqu | +0.199 |
behavi | +0.194 |
Neg logit contributions | |
abase | -0.281 |
rador | -0.227 |
MB | -0.224 |
CAD | -0.211 |
ielding | -0.210 |
Token | to |
Token ID | 284 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
moons | +0.406 |
horm | +0.392 |
nerv | +0.376 |
mosqu | +0.362 |
behavi | +0.352 |
Neg logit contributions | |
abase | -0.555 |
rador | -0.450 |
MB | -0.444 |
CAD | -0.420 |
ielding | -0.417 |
Token | in |
Token ID | 287 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
moons | +0.350 |
horm | +0.339 |
nerv | +0.326 |
mosqu | +0.315 |
behavi | +0.306 |
Neg logit contributions | |
abase | -0.463 |
rador | -0.374 |
MB | -0.372 |
CAD | -0.350 |
ielding | -0.346 |
Token | January |
Token ID | 3269 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
moons | +0.143 |
horm | +0.139 |
nerv | +0.134 |
mosqu | +0.130 |
behavi | +0.127 |
Neg logit contributions | |
abase | -0.151 |
rador | -0.119 |
MB | -0.118 |
CAD | -0.110 |
ielding | -0.109 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
abase | +0.761 |
MB | +0.609 |
rador | +0.608 |
CAD | +0.570 |
ielding | +0.562 |
Neg logit contributions | |
moons | -0.637 |
horm | -0.621 |
nerv | -0.595 |
mosqu | -0.581 |
behavi | -0.565 |
Token | three |
Token ID | 1115 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
moons | +0.180 |
horm | +0.175 |
nerv | +0.167 |
mosqu | +0.162 |
behavi | +0.157 |
Neg logit contributions | |
abase | -0.254 |
rador | -0.207 |
MB | -0.205 |
CAD | -0.194 |
ielding | -0.192 |
Token | weeks |
Token ID | 2745 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
moons | +0.161 |
horm | +0.157 |
nerv | +0.150 |
mosqu | +0.146 |
behavi | +0.141 |
Neg logit contributions | |
abase | -0.208 |
rador | -0.168 |
MB | -0.167 |
CAD | -0.157 |
ielding | -0.156 |
Token | ahead |
Token ID | 4058 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
abase | +1.256 |
MB | +1.024 |
rador | +1.019 |
CAD | +0.970 |
ielding | +0.955 |
Neg logit contributions | |
moons | -0.871 |
horm | -0.848 |
nerv | -0.803 |
mosqu | -0.788 |
behavi | -0.761 |
Token | of |
Token ID | 286 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
moons | +2.386 |
horm | +2.217 |
nerv | +2.192 |
mosqu | +1.953 |
behavi | +1.942 |
Neg logit contributions | |
abase | -3.066 |
rador | -2.469 |
MB | -2.343 |
ielding | -2.267 |
CAD | -2.217 |
Token | its |
Token ID | 663 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
moons | +0.247 |
horm | +0.241 |
nerv | +0.231 |
mosqu | +0.224 |
behavi | +0.218 |
Neg logit contributions | |
abase | -0.299 |
MB | -0.239 |
rador | -0.239 |
CAD | -0.225 |
ielding | -0.222 |
Token | normal |
Token ID | 3487 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
moons | +0.050 |
horm | +0.049 |
nerv | +0.047 |
mosqu | +0.045 |
behavi | +0.044 |
Neg logit contributions | |
abase | -0.068 |
MB | -0.055 |
rador | -0.055 |
CAD | -0.052 |
ielding | -0.051 |
Token | security |
Token ID | 2324 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
moons | +0.050 |
horm | +0.049 |
nerv | +0.046 |
mosqu | +0.045 |
behavi | +0.043 |
Neg logit contributions | |
abase | -0.082 |
rador | -0.067 |
MB | -0.067 |
CAD | -0.064 |
ielding | -0.063 |
Token | updates |
Token ID | 5992 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
moons | +0.229 |
horm | +0.220 |
nerv | +0.210 |
mosqu | +0.202 |
behavi | +0.195 |
Neg logit contributions | |
abase | -0.375 |
rador | -0.309 |
MB | -0.307 |
CAD | -0.291 |
ielding | -0.289 |
Token | within |
Token ID | 1626 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
moons | +0.162 |
horm | +0.157 |
nerv | +0.150 |
mosqu | +0.146 |
behavi | +0.141 |
Neg logit contributions | |
abase | -0.234 |
rador | -0.191 |
MB | -0.190 |
CAD | -0.180 |
ielding | -0.177 |
Token | 2 |
Token ID | 362 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
moons | +0.315 |
horm | +0.306 |
nerv | +0.296 |
mosqu | +0.288 |
behavi | +0.281 |
Neg logit contributions | |
abase | -0.289 |
rador | -0.223 |
MB | -0.220 |
CAD | -0.204 |
ielding | -0.202 |
Token | weeks |
Token ID | 2745 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
abase | +0.022 |
rador | +0.017 |
MB | +0.017 |
CAD | +0.016 |
ielding | +0.016 |
Neg logit contributions | |
moons | -0.020 |
horm | -0.020 |
nerv | -0.019 |
mosqu | -0.018 |
behavi | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
abase | +1.436 |
MB | +1.174 |
rador | +1.168 |
CAD | +1.110 |
ielding | +1.091 |
Neg logit contributions | |
moons | -0.990 |
horm | -0.966 |
nerv | -0.916 |
mosqu | -0.898 |
behavi | -0.866 |
Token | This |
Token ID | 770 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
moons | +0.510 |
horm | +0.495 |
nerv | +0.477 |
mosqu | +0.462 |
behavi | +0.450 |
Neg logit contributions | |
abase | -0.574 |
rador | -0.456 |
MB | -0.451 |
CAD | -0.423 |
ielding | -0.419 |
Token | sub |
Token ID | 850 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
moons | +0.401 |
horm | +0.388 |
nerv | +0.374 |
mosqu | +0.362 |
behavi | +0.352 |
Neg logit contributions | |
abase | -0.479 |
rador | -0.383 |
MB | -0.379 |
CAD | -0.356 |
ielding | -0.353 |
Token | sounds |
Token ID | 5238 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
moons | +2.314 |
horm | +2.234 |
nerv | +2.145 |
mosqu | +2.056 |
behavi | +1.997 |
Neg logit contributions | |
abase | -3.016 |
rador | -2.433 |
MB | -2.407 |
CAD | -2.282 |
ielding | -2.274 |
Token | amazing |
Token ID | 4998 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
moons | +0.339 |
horm | +0.330 |
nerv | +0.317 |
mosqu | +0.308 |
behavi | +0.301 |
Neg logit contributions | |
abase | -0.388 |
rador | -0.308 |
MB | -0.307 |
CAD | -0.288 |
ielding | -0.284 |
Token | . |
Token ID | 13 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
moons | +0.122 |
horm | +0.119 |
nerv | +0.113 |
mosqu | +0.110 |
behavi | +0.106 |
Neg logit contributions | |
abase | -0.190 |
rador | -0.156 |
MB | -0.156 |
CAD | -0.147 |
ielding | -0.146 |
Token | It |
Token ID | 632 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
moons | +0.066 |
horm | +0.064 |
nerv | +0.062 |
mosqu | +0.060 |
behavi | +0.058 |
Neg logit contributions | |
abase | -0.073 |
rador | -0.058 |
MB | -0.057 |
CAD | -0.053 |
ielding | -0.053 |
Token | really |
Token ID | 1107 |
Feature activation | -9.63e-03 |
Pos logit contributions | |
moons | +0.706 |
horm | +0.682 |
nerv | +0.657 |
mosqu | +0.635 |
behavi | +0.618 |
Neg logit contributions | |
abase | -0.861 |
rador | -0.690 |
MB | -0.683 |
CAD | -0.642 |
ielding | -0.637 |
Token | � |
Token ID | 447 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
abase | +0.151 |
rador | +0.119 |
MB | +0.119 |
CAD | +0.111 |
ielding | +0.109 |
Neg logit contributions | |
moons | -0.141 |
horm | -0.137 |
nerv | -0.132 |
mosqu | -0.128 |
behavi | -0.125 |
Token | � |
Token ID | 247 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
abase | +0.043 |
rador | +0.034 |
MB | +0.033 |
CAD | +0.032 |
ielding | +0.031 |
Neg logit contributions | |
moons | -0.037 |
horm | -0.036 |
nerv | -0.035 |
mosqu | -0.033 |
behavi | -0.033 |
Token | s |
Token ID | 82 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
abase | +0.163 |
rador | +0.131 |
MB | +0.130 |
CAD | +0.122 |
ielding | +0.121 |
Neg logit contributions | |
moons | -0.130 |
horm | -0.127 |
nerv | -0.122 |
mosqu | -0.118 |
behavi | -0.114 |
Token | presidency |
Token ID | 12112 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
abase | +0.190 |
rador | +0.157 |
MB | +0.157 |
CAD | +0.149 |
ielding | +0.147 |
Neg logit contributions | |
moons | -0.108 |
horm | -0.105 |
nerv | -0.100 |
mosqu | -0.097 |
behavi | -0.093 |
Token | , |
Token ID | 11 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
abase | +0.453 |
rador | +0.370 |
MB | +0.368 |
CAD | +0.348 |
ielding | +0.344 |
Neg logit contributions | |
moons | -0.311 |
horm | -0.303 |
nerv | -0.287 |
mosqu | -0.279 |
behavi | -0.271 |
Token | whichever |
Token ID | 26204 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
moons | +0.032 |
horm | +0.031 |
nerv | +0.030 |
mosqu | +0.029 |
behavi | +0.028 |
Neg logit contributions | |
abase | -0.042 |
rador | -0.034 |
MB | -0.034 |
CAD | -0.032 |
ielding | -0.031 |
Token | comes |
Token ID | 2058 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
moons | +2.521 |
horm | +2.440 |
nerv | +2.354 |
mosqu | +2.268 |
behavi | +2.211 |
Neg logit contributions | |
abase | -2.843 |
rador | -2.265 |
MB | -2.196 |
ielding | -2.085 |
CAD | -2.073 |
Token | first |
Token ID | 717 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
moons | +0.111 |
horm | +0.108 |
nerv | +0.103 |
mosqu | +0.101 |
behavi | +0.097 |
Neg logit contributions | |
abase | -0.166 |
MB | -0.135 |
rador | -0.135 |
CAD | -0.128 |
ielding | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
moons | +0.365 |
horm | +0.352 |
nerv | +0.336 |
mosqu | +0.324 |
behavi | +0.314 |
Neg logit contributions | |
abase | -0.565 |
rador | -0.464 |
MB | -0.461 |
CAD | -0.436 |
ielding | -0.432 |
Token | Po |
Token ID | 7695 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
moons | +0.213 |
horm | +0.207 |
nerv | +0.199 |
mosqu | +0.194 |
behavi | +0.189 |
Neg logit contributions | |
abase | -0.252 |
rador | -0.201 |
MB | -0.201 |
CAD | -0.188 |
ielding | -0.185 |
Token | etic |
Token ID | 5139 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
moons | +0.282 |
horm | +0.273 |
nerv | +0.264 |
mosqu | +0.256 |
behavi | +0.250 |
Neg logit contributions | |
abase | -0.304 |
rador | -0.240 |
MB | -0.238 |
CAD | -0.222 |
ielding | -0.220 |
Token | the |
Token ID | 262 |
Feature activation | -5.67e-03 |
Pos logit contributions | |
moons | +0.227 |
horm | +0.219 |
nerv | +0.210 |
mosqu | +0.202 |
behavi | +0.196 |
Neg logit contributions | |
abase | -0.345 |
rador | -0.283 |
MB | -0.280 |
CAD | -0.265 |
ielding | -0.263 |
Token | question |
Token ID | 1808 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
moons | +0.004 |
horm | +0.004 |
nerv | +0.004 |
mosqu | +0.004 |
behavi | +0.003 |
Neg logit contributions | |
abase | -0.005 |
rador | -0.004 |
MB | -0.004 |
CAD | -0.004 |
ielding | -0.004 |
Token | ? |
Token ID | 30 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
abase | +0.384 |
rador | +0.305 |
MB | +0.303 |
CAD | +0.283 |
ielding | +0.281 |
Neg logit contributions | |
moons | -0.336 |
horm | -0.327 |
nerv | -0.315 |
mosqu | -0.306 |
behavi | -0.298 |
Token |
|
Token ID | 198 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
moons | +0.027 |
horm | +0.026 |
nerv | +0.025 |
mosqu | +0.024 |
behavi | +0.024 |
Neg logit contributions | |
abase | -0.032 |
rador | -0.026 |
MB | -0.025 |
CAD | -0.024 |
ielding | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
moons | +0.286 |
horm | +0.271 |
nerv | +0.263 |
mosqu | +0.241 |
behavi | +0.236 |
Neg logit contributions | |
abase | -0.373 |
rador | -0.301 |
MB | -0.291 |
ielding | -0.276 |
CAD | -0.275 |
Token | IGN |
Token ID | 16284 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
moons | +0.242 |
horm | +0.234 |
nerv | +0.224 |
mosqu | +0.216 |
behavi | +0.210 |
Neg logit contributions | |
abase | -0.346 |
rador | -0.282 |
MB | -0.280 |
CAD | -0.264 |
ielding | -0.262 |
Token | : |
Token ID | 25 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
moons | +2.011 |
horm | +1.834 |
nerv | +1.811 |
Sparrow | +1.572 |
kills | +1.547 |
Neg logit contributions | |
abase | -3.263 |
rador | -2.675 |
MB | -2.549 |
ielding | -2.482 |
CAD | -2.435 |
Token | Just |
Token ID | 2329 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
moons | +0.783 |
horm | +0.756 |
nerv | +0.728 |
mosqu | +0.701 |
behavi | +0.682 |
Neg logit contributions | |
abase | -0.971 |
rador | -0.781 |
MB | -0.770 |
CAD | -0.725 |
ielding | -0.721 |
Token | about |
Token ID | 546 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
moons | +0.268 |
horm | +0.259 |
nerv | +0.249 |
mosqu | +0.241 |
behavi | +0.234 |
Neg logit contributions | |
abase | -0.341 |
rador | -0.274 |
MB | -0.272 |
CAD | -0.256 |
ielding | -0.254 |
Token | the |
Token ID | 262 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
moons | +0.655 |
horm | +0.636 |
nerv | +0.611 |
mosqu | +0.593 |
behavi | +0.577 |
Neg logit contributions | |
abase | -0.805 |
rador | -0.644 |
MB | -0.641 |
CAD | -0.602 |
ielding | -0.595 |
Token | key |
Token ID | 1994 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
moons | +0.437 |
horm | +0.423 |
nerv | +0.406 |
mosqu | +0.393 |
behavi | +0.382 |
Neg logit contributions | |
abase | -0.562 |
rador | -0.453 |
MB | -0.449 |
CAD | -0.423 |
ielding | -0.419 |
Token | November |
Token ID | 3389 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
moons | +0.523 |
horm | +0.503 |
nerv | +0.486 |
mosqu | +0.465 |
behavi | +0.453 |
Neg logit contributions | |
abase | -0.629 |
rador | -0.503 |
MB | -0.493 |
ielding | -0.466 |
CAD | -0.464 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
abase | +0.193 |
rador | +0.153 |
MB | +0.152 |
CAD | +0.142 |
ielding | +0.141 |
Neg logit contributions | |
moons | -0.172 |
horm | -0.167 |
nerv | -0.161 |
mosqu | -0.156 |
behavi | -0.152 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
moons | +0.753 |
horm | +0.723 |
nerv | +0.701 |
mosqu | +0.673 |
behavi | +0.655 |
Neg logit contributions | |
abase | -0.903 |
rador | -0.723 |
MB | -0.712 |
CAD | -0.671 |
ielding | -0.667 |
Token | featured |
Token ID | 8096 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
abase | +0.096 |
rador | +0.077 |
MB | +0.076 |
CAD | +0.071 |
ielding | +0.071 |
Neg logit contributions | |
moons | -0.081 |
horm | -0.078 |
nerv | -0.075 |
mosqu | -0.072 |
behavi | -0.070 |
Token | the |
Token ID | 262 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
moons | +0.129 |
horm | +0.124 |
nerv | +0.120 |
mosqu | +0.116 |
behavi | +0.113 |
Neg logit contributions | |
abase | -0.152 |
rador | -0.121 |
MB | -0.119 |
CAD | -0.112 |
ielding | -0.112 |
Token | rather |
Token ID | 2138 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
moons | +0.164 |
horm | +0.158 |
nerv | +0.152 |
mosqu | +0.146 |
behavi | +0.142 |
Neg logit contributions | |
abase | -0.219 |
rador | -0.177 |
MB | -0.175 |
CAD | -0.165 |
ielding | -0.164 |
Token | violent |
Token ID | 6590 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
abase | +2.088 |
MB | +1.683 |
rador | +1.675 |
CAD | +1.576 |
ielding | +1.547 |
Neg logit contributions | |
moons | -1.693 |
horm | -1.654 |
nerv | -1.571 |
mosqu | -1.546 |
behavi | -1.504 |
Token | mating |
Token ID | 31993 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
abase | +0.032 |
rador | +0.026 |
MB | +0.025 |
CAD | +0.024 |
ielding | +0.024 |
Neg logit contributions | |
moons | -0.023 |
horm | -0.022 |
nerv | -0.021 |
mosqu | -0.020 |
behavi | -0.020 |
Token | fights |
Token ID | 11418 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
moons | +1.192 |
horm | +1.146 |
nerv | +1.107 |
mosqu | +1.068 |
behavi | +1.041 |
Neg logit contributions | |
abase | -1.488 |
rador | -1.194 |
MB | -1.179 |
CAD | -1.113 |
ielding | -1.105 |
Token | of |
Token ID | 286 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
abase | +0.302 |
MB | +0.243 |
rador | +0.243 |
CAD | +0.228 |
ielding | +0.226 |
Neg logit contributions | |
moons | -0.236 |
horm | -0.231 |
nerv | -0.219 |
mosqu | -0.216 |
behavi | -0.209 |
Token | snow |
Token ID | 6729 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
moons | +0.161 |
horm | +0.156 |
nerv | +0.150 |
mosqu | +0.145 |
behavi | +0.141 |
Neg logit contributions | |
abase | -0.194 |
rador | -0.155 |
MB | -0.153 |
CAD | -0.144 |
ielding | -0.143 |
Token | survey |
Token ID | 5526 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
moons | +0.458 |
horm | +0.442 |
nerv | +0.421 |
mosqu | +0.404 |
behavi | +0.392 |
Neg logit contributions | |
abase | -0.748 |
rador | -0.614 |
MB | -0.613 |
CAD | -0.581 |
ielding | -0.575 |
Token |
|
Token ID | 198 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
moons | +1.249 |
horm | +1.200 |
nerv | +1.159 |
mosqu | +1.114 |
behavi | +1.085 |
Neg logit contributions | |
abase | -1.673 |
rador | -1.357 |
MB | -1.333 |
CAD | -1.260 |
ielding | -1.253 |
Token |
|
Token ID | 198 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
moons | +0.217 |
horm | +0.207 |
nerv | +0.201 |
mosqu | +0.187 |
behavi | +0.183 |
Neg logit contributions | |
abase | -0.275 |
rador | -0.222 |
MB | -0.216 |
ielding | -0.204 |
CAD | -0.204 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
moons | +0.154 |
horm | +0.149 |
nerv | +0.143 |
mosqu | +0.139 |
behavi | +0.135 |
Neg logit contributions | |
abase | -0.183 |
rador | -0.147 |
MB | -0.145 |
CAD | -0.136 |
ielding | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
moons | +0.380 |
horm | +0.366 |
nerv | +0.354 |
mosqu | +0.342 |
behavi | +0.333 |
Neg logit contributions | |
abase | -0.445 |
rador | -0.356 |
MB | -0.350 |
CAD | -0.330 |
ielding | -0.328 |
Token | 600 |
Token ID | 8054 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
moons | +0.208 |
horm | +0.201 |
nerv | +0.195 |
mosqu | +0.188 |
behavi | +0.183 |
Neg logit contributions | |
abase | -0.220 |
rador | -0.174 |
MB | -0.171 |
CAD | -0.160 |
ielding | -0.159 |
Token | years |
Token ID | 812 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
abase | +1.875 |
MB | +1.500 |
rador | +1.480 |
CAD | +1.405 |
ielding | +1.373 |
Neg logit contributions | |
moons | -1.568 |
horm | -1.534 |
nerv | -1.466 |
mosqu | -1.423 |
behavi | -1.398 |
Token | Age |
Token ID | 7129 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
abase | +0.462 |
rador | +0.361 |
MB | +0.359 |
CAD | +0.335 |
ielding | +0.330 |
Neg logit contributions | |
moons | -0.456 |
horm | -0.444 |
nerv | -0.428 |
mosqu | -0.416 |
behavi | -0.406 |
Token | of |
Token ID | 286 |
Feature activation | +7.84e-03 |
Pos logit contributions | |
abase | +0.122 |
rador | +0.099 |
MB | +0.097 |
CAD | +0.091 |
ielding | +0.090 |
Neg logit contributions | |
moons | -0.100 |
horm | -0.096 |
nerv | -0.093 |
mosqu | -0.089 |
behavi | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
abase | +0.007 |
rador | +0.006 |
MB | +0.006 |
CAD | +0.005 |
ielding | +0.005 |
Neg logit contributions | |
moons | -0.006 |
horm | -0.005 |
nerv | -0.005 |
mosqu | -0.005 |
behavi | -0.005 |
Token | world |
Token ID | 995 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
abase | +0.329 |
rador | +0.256 |
MB | +0.252 |
CAD | +0.235 |
ielding | +0.233 |
Neg logit contributions | |
moons | -0.340 |
horm | -0.329 |
nerv | -0.318 |
mosqu | -0.309 |
behavi | -0.301 |
Token | nearly |
Token ID | 3016 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
moons | +0.613 |
horm | +0.589 |
nerv | +0.569 |
mosqu | +0.547 |
behavi | +0.534 |
Neg logit contributions | |
abase | -0.747 |
rador | -0.598 |
MB | -0.586 |
CAD | -0.553 |
ielding | -0.553 |
Token | 50 |
Token ID | 2026 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
abase | +0.712 |
rador | +0.568 |
MB | +0.565 |
CAD | +0.530 |
ielding | +0.524 |
Neg logit contributions | |
moons | -0.605 |
horm | -0.587 |
nerv | -0.565 |
mosqu | -0.548 |
behavi | -0.534 |
Token | products |
Token ID | 3186 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
abase | +0.059 |
rador | +0.047 |
MB | +0.046 |
CAD | +0.043 |
ielding | +0.043 |
Neg logit contributions | |
moons | -0.054 |
horm | -0.052 |
nerv | -0.050 |
mosqu | -0.049 |
behavi | -0.048 |
Token | over |
Token ID | 625 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
moons | +0.310 |
horm | +0.299 |
nerv | +0.288 |
mosqu | +0.278 |
behavi | +0.270 |
Neg logit contributions | |
abase | -0.410 |
rador | -0.332 |
MB | -0.328 |
CAD | -0.310 |
ielding | -0.307 |
Token | the |
Token ID | 262 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
moons | +0.559 |
horm | +0.539 |
nerv | +0.519 |
mosqu | +0.501 |
behavi | +0.488 |
Neg logit contributions | |
abase | -0.685 |
rador | -0.550 |
MB | -0.542 |
CAD | -0.510 |
ielding | -0.509 |
Token | past |
Token ID | 1613 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
abase | +0.323 |
rador | +0.263 |
MB | +0.261 |
CAD | +0.247 |
ielding | +0.244 |
Neg logit contributions | |
moons | -0.226 |
horm | -0.220 |
nerv | -0.210 |
mosqu | -0.203 |
behavi | -0.197 |
Token | few |
Token ID | 1178 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
abase | +1.856 |
MB | +1.480 |
rador | +1.468 |
CAD | +1.388 |
ielding | +1.357 |
Neg logit contributions | |
moons | -1.643 |
horm | -1.614 |
nerv | -1.549 |
mosqu | -1.516 |
behavi | -1.476 |
Token | years |
Token ID | 812 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
moons | +0.482 |
horm | +0.463 |
nerv | +0.447 |
mosqu | +0.431 |
behavi | +0.419 |
Neg logit contributions | |
abase | -0.599 |
rador | -0.482 |
MB | -0.474 |
CAD | -0.446 |
ielding | -0.444 |
Token | , |
Token ID | 11 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
abase | +0.606 |
MB | +0.487 |
rador | +0.486 |
CAD | +0.458 |
ielding | +0.452 |
Neg logit contributions | |
moons | -0.473 |
horm | -0.461 |
nerv | -0.439 |
mosqu | -0.429 |
behavi | -0.416 |
Token | from |
Token ID | 422 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
moons | +0.036 |
horm | +0.035 |
nerv | +0.033 |
mosqu | +0.032 |
behavi | +0.031 |
Neg logit contributions | |
abase | -0.057 |
rador | -0.047 |
MB | -0.046 |
CAD | -0.044 |
ielding | -0.044 |
Token | massive |
Token ID | 4858 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
abase | +0.538 |
rador | +0.431 |
MB | +0.428 |
CAD | +0.402 |
ielding | +0.396 |
Neg logit contributions | |
moons | -0.450 |
horm | -0.437 |
nerv | -0.420 |
mosqu | -0.407 |
behavi | -0.397 |
Token | > |
Token ID | 29 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
abase | +2.095 |
rador | +1.593 |
MB | +1.582 |
CAD | +1.461 |
ielding | +1.437 |
Neg logit contributions | |
moons | -2.510 |
horm | -2.450 |
nerv | -2.371 |
mosqu | -2.315 |
behavi | -2.261 |
Token | or |
Token ID | 393 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
abase | +1.880 |
rador | +1.464 |
MB | +1.459 |
CAD | +1.356 |
ielding | +1.341 |
Neg logit contributions | |
moons | -1.927 |
horm | -1.879 |
nerv | -1.812 |
mosqu | -1.766 |
behavi | -1.723 |
Token | < |
Token ID | 1279 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
moons | +0.400 |
horm | +0.388 |
nerv | +0.376 |
mosqu | +0.364 |
behavi | +0.356 |
Neg logit contributions | |
abase | -0.371 |
rador | -0.288 |
MB | -0.282 |
CAD | -0.263 |
ielding | -0.261 |
Token | Tab |
Token ID | 33349 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
abase | +0.307 |
rador | +0.243 |
MB | +0.241 |
CAD | +0.226 |
ielding | +0.224 |
Neg logit contributions | |
moons | -0.275 |
horm | -0.267 |
nerv | -0.258 |
mosqu | -0.250 |
behavi | -0.244 |
Token | >) |
Token ID | 43734 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
abase | +1.044 |
rador | +0.765 |
MB | +0.754 |
CAD | +0.688 |
ielding | +0.680 |
Neg logit contributions | |
moons | -1.505 |
horm | -1.467 |
nerv | -1.426 |
mosqu | -1.389 |
behavi | -1.362 |
Token | { |
Token ID | 1391 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
abase | +1.612 |
MB | +1.289 |
rador | +1.289 |
CAD | +1.208 |
ielding | +1.191 |
Neg logit contributions | |
moons | -1.358 |
horm | -1.324 |
nerv | -1.268 |
mosqu | -1.236 |
behavi | -1.201 |
Token | vi |
Token ID | 8903 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
abase | +2.478 |
MB | +1.974 |
rador | +1.964 |
CAD | +1.840 |
ielding | +1.821 |
Neg logit contributions | |
moons | -2.117 |
horm | -2.083 |
nerv | -2.004 |
mosqu | -1.948 |
behavi | -1.879 |
Token | : |
Token ID | 25 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
abase | +0.732 |
rador | +0.590 |
MB | +0.586 |
CAD | +0.551 |
ielding | +0.546 |
Neg logit contributions | |
moons | -0.568 |
horm | -0.549 |
nerv | -0.528 |
mosqu | -0.511 |
behavi | -0.497 |
Token | | |
Token ID | 91 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
abase | +0.477 |
rador | +0.379 |
MB | +0.377 |
CAD | +0.352 |
ielding | +0.349 |
Neg logit contributions | |
moons | -0.420 |
horm | -0.409 |
nerv | -0.393 |
mosqu | -0.381 |
behavi | -0.372 |
Token | vim |
Token ID | 31124 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
moons | +0.356 |
horm | +0.342 |
nerv | +0.325 |
mosqu | +0.311 |
behavi | +0.300 |
Neg logit contributions | |
abase | -0.663 |
rador | -0.551 |
MB | -0.547 |
CAD | -0.520 |
ielding | -0.516 |
Token | : |
Token ID | 25 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
moons | +0.456 |
horm | +0.439 |
nerv | +0.423 |
mosqu | +0.403 |
behavi | +0.393 |
Neg logit contributions | |
abase | -0.608 |
rador | -0.492 |
MB | -0.486 |
CAD | -0.459 |
ielding | -0.456 |
Token | approach |
Token ID | 3164 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
moons | +0.087 |
horm | +0.084 |
nerv | +0.081 |
mosqu | +0.078 |
behavi | +0.076 |
Neg logit contributions | |
abase | -0.115 |
rador | -0.093 |
MB | -0.092 |
CAD | -0.086 |
ielding | -0.086 |
Token | to |
Token ID | 284 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
moons | +0.365 |
horm | +0.351 |
nerv | +0.339 |
mosqu | +0.324 |
behavi | +0.315 |
Neg logit contributions | |
abase | -0.479 |
rador | -0.387 |
MB | -0.383 |
CAD | -0.361 |
ielding | -0.358 |
Token | designing |
Token ID | 18492 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
moons | +0.126 |
horm | +0.122 |
nerv | +0.118 |
mosqu | +0.114 |
behavi | +0.110 |
Neg logit contributions | |
abase | -0.177 |
rador | -0.143 |
MB | -0.143 |
CAD | -0.135 |
ielding | -0.134 |
Token | X |
Token ID | 1395 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
abase | +0.241 |
MB | +0.195 |
rador | +0.195 |
CAD | +0.184 |
ielding | +0.181 |
Neg logit contributions | |
moons | -0.179 |
horm | -0.174 |
nerv | -0.167 |
mosqu | -0.162 |
behavi | -0.158 |
Token | e |
Token ID | 68 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
abase | +1.033 |
rador | +0.809 |
MB | +0.806 |
CAD | +0.752 |
ielding | +0.744 |
Neg logit contributions | |
moons | -1.011 |
horm | -0.987 |
nerv | -0.950 |
mosqu | -0.926 |
behavi | -0.913 |
Token | od |
Token ID | 375 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
abase | +0.646 |
MB | +0.500 |
rador | +0.495 |
CAD | +0.463 |
ielding | +0.455 |
Neg logit contributions | |
moons | -0.709 |
horm | -0.693 |
nerv | -0.668 |
mosqu | -0.655 |
behavi | -0.644 |
Token | r |
Token ID | 81 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
abase | +2.770 |
rador | +2.170 |
MB | +2.154 |
ielding | +2.025 |
CAD | +2.004 |
Neg logit contributions | |
moons | -2.676 |
horm | -2.620 |
nerv | -2.511 |
mosqu | -2.483 |
behavi | -2.463 |
Token | ifter |
Token ID | 18171 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
abase | +0.727 |
rador | +0.572 |
MB | +0.569 |
CAD | +0.532 |
ielding | +0.527 |
Neg logit contributions | |
moons | -0.660 |
horm | -0.641 |
nerv | -0.617 |
mosqu | -0.602 |
behavi | -0.586 |
Token | was |
Token ID | 373 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
abase | +0.702 |
rador | +0.564 |
MB | +0.560 |
CAD | +0.526 |
ielding | +0.522 |
Neg logit contributions | |
moons | -0.561 |
horm | -0.543 |
nerv | -0.522 |
mosqu | -0.506 |
behavi | -0.493 |
Token | a |
Token ID | 257 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
abase | +0.170 |
rador | +0.134 |
MB | +0.133 |
CAD | +0.124 |
ielding | +0.123 |
Neg logit contributions | |
moons | -0.154 |
horm | -0.149 |
nerv | -0.144 |
mosqu | -0.139 |
behavi | -0.135 |
Token | case |
Token ID | 1339 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
abase | +0.784 |
rador | +0.628 |
MB | +0.625 |
CAD | +0.588 |
ielding | +0.581 |
Neg logit contributions | |
moons | -0.645 |
horm | -0.627 |
nerv | -0.602 |
mosqu | -0.588 |
behavi | -0.572 |
Token | the |
Token ID | 262 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
moons | +0.092 |
horm | +0.089 |
nerv | +0.086 |
mosqu | +0.082 |
behavi | +0.080 |
Neg logit contributions | |
abase | -0.117 |
rador | -0.094 |
MB | -0.092 |
CAD | -0.087 |
ielding | -0.087 |
Token | one |
Token ID | 530 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
moons | +0.180 |
horm | +0.176 |
nerv | +0.169 |
mosqu | +0.167 |
behavi | +0.162 |
Neg logit contributions | |
abase | -0.198 |
MB | -0.158 |
rador | -0.157 |
CAD | -0.147 |
ielding | -0.145 |
Token | that |
Token ID | 326 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
abase | +0.502 |
MB | +0.404 |
rador | +0.404 |
CAD | +0.379 |
ielding | +0.375 |
Neg logit contributions | |
moons | -0.381 |
horm | -0.371 |
nerv | -0.355 |
mosqu | -0.349 |
behavi | -0.338 |
Token | I |
Token ID | 314 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
moons | +0.087 |
horm | +0.085 |
nerv | +0.081 |
mosqu | +0.080 |
behavi | +0.078 |
Neg logit contributions | |
abase | -0.104 |
MB | -0.083 |
rador | -0.083 |
CAD | -0.078 |
ielding | -0.076 |
Token | find |
Token ID | 1064 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
moons | +0.170 |
horm | +0.164 |
nerv | +0.158 |
mosqu | +0.153 |
behavi | +0.148 |
Neg logit contributions | |
abase | -0.214 |
rador | -0.172 |
MB | -0.171 |
CAD | -0.161 |
ielding | -0.159 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
abase | +0.028 |
rador | +0.022 |
MB | +0.022 |
ielding | +0.021 |
CAD | +0.021 |
Neg logit contributions | |
moons | -0.021 |
horm | -0.020 |
nerv | -0.020 |
mosqu | -0.019 |
behavi | -0.018 |
Token | most |
Token ID | 749 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
abase | +0.011 |
rador | +0.009 |
MB | +0.008 |
CAD | +0.008 |
ielding | +0.008 |
Neg logit contributions | |
moons | -0.008 |
horm | -0.008 |
nerv | -0.008 |
mosqu | -0.007 |
behavi | -0.007 |
Token | annoying |
Token ID | 15774 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
abase | +0.328 |
rador | +0.269 |
MB | +0.266 |
CAD | +0.252 |
ielding | +0.250 |
Neg logit contributions | |
moons | -0.213 |
horm | -0.205 |
nerv | -0.196 |
mosqu | -0.188 |
behavi | -0.182 |
Token | / |
Token ID | 14 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
abase | +0.705 |
MB | +0.540 |
rador | +0.536 |
CAD | +0.499 |
ielding | +0.488 |
Neg logit contributions | |
moons | -0.837 |
horm | -0.823 |
nerv | -0.792 |
mosqu | -0.789 |
behavi | -0.768 |
Token | dist |
Token ID | 17080 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
moons | +0.632 |
horm | +0.612 |
nerv | +0.595 |
mosqu | +0.574 |
behavi | +0.565 |
Neg logit contributions | |
abase | -0.481 |
rador | -0.357 |
MB | -0.353 |
CAD | -0.324 |
ielding | -0.319 |
Token | ract |
Token ID | 974 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
abase | +0.048 |
rador | +0.038 |
MB | +0.038 |
CAD | +0.036 |
ielding | +0.035 |
Neg logit contributions | |
moons | -0.038 |
horm | -0.036 |
nerv | -0.035 |
mosqu | -0.034 |
seiz | -0.032 |
Token | platform |
Token ID | 3859 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
abase | +0.406 |
rador | +0.326 |
MB | +0.325 |
CAD | +0.306 |
ielding | +0.303 |
Neg logit contributions | |
moons | -0.318 |
horm | -0.308 |
nerv | -0.296 |
mosqu | -0.287 |
behavi | -0.279 |
Token | ing |
Token ID | 278 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
abase | +1.251 |
MB | +0.973 |
rador | +0.969 |
CAD | +0.897 |
ielding | +0.891 |
Neg logit contributions | |
moons | -1.334 |
horm | -1.305 |
nerv | -1.259 |
mosqu | -1.231 |
behavi | -1.196 |
Token | that |
Token ID | 326 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
abase | +0.275 |
rador | +0.222 |
MB | +0.221 |
CAD | +0.208 |
ielding | +0.206 |
Neg logit contributions | |
moons | -0.205 |
horm | -0.199 |
nerv | -0.190 |
mosqu | -0.184 |
behavi | -0.179 |
Token | under |
Token ID | 739 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
moons | +0.412 |
horm | +0.396 |
nerv | +0.382 |
mosqu | +0.367 |
behavi | +0.357 |
Neg logit contributions | |
abase | -0.567 |
rador | -0.459 |
MB | -0.452 |
CAD | -0.429 |
ielding | -0.425 |
Token | line |
Token ID | 1370 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
abase | +0.367 |
rador | +0.278 |
MB | +0.274 |
CAD | +0.253 |
ielding | +0.251 |
Neg logit contributions | |
moons | -0.447 |
horm | -0.435 |
nerv | -0.422 |
mosqu | -0.410 |
behavi | -0.401 |
Token | the |
Token ID | 262 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
abase | +0.232 |
rador | +0.185 |
MB | +0.184 |
CAD | +0.173 |
ielding | +0.171 |
Neg logit contributions | |
moons | -0.194 |
horm | -0.188 |
nerv | -0.181 |
mosqu | -0.175 |
behavi | -0.171 |
Token | original |
Token ID | 2656 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
abase | +0.348 |
rador | +0.281 |
MB | +0.278 |
CAD | +0.262 |
ielding | +0.260 |
Neg logit contributions | |
moons | -0.266 |
horm | -0.257 |
nerv | -0.247 |
mosqu | -0.239 |
behavi | -0.232 |
Token | game |
Token ID | 983 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
abase | +0.209 |
MB | +0.170 |
rador | +0.170 |
CAD | +0.160 |
ielding | +0.158 |
Neg logit contributions | |
moons | -0.151 |
horm | -0.147 |
nerv | -0.140 |
mosqu | -0.136 |
behavi | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
abase | +0.400 |
rador | +0.325 |
MB | +0.323 |
CAD | +0.305 |
ielding | +0.302 |
Neg logit contributions | |
moons | -0.293 |
horm | -0.284 |
nerv | -0.271 |
mosqu | -0.263 |
behavi | -0.254 |
Token | Much |
Token ID | 13111 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
abase | +0.038 |
rador | +0.030 |
MB | +0.030 |
CAD | +0.028 |
ielding | +0.028 |
Neg logit contributions | |
moons | -0.034 |
horm | -0.033 |
nerv | -0.031 |
mosqu | -0.030 |
behavi | -0.030 |
Token | of |
Token ID | 286 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
abase | +0.439 |
rador | +0.351 |
MB | +0.348 |
CAD | +0.327 |
ielding | +0.324 |
Neg logit contributions | |
moons | -0.363 |
horm | -0.352 |
nerv | -0.339 |
mosqu | -0.328 |
behavi | -0.319 |
Token | z |
Token ID | 89 |
Feature activation | -9.73e-03 |
Pos logit contributions | |
moons | +0.101 |
horm | +0.097 |
nerv | +0.093 |
mosqu | +0.090 |
behavi | +0.087 |
Neg logit contributions | |
abase | -0.148 |
rador | -0.121 |
MB | -0.120 |
CAD | -0.113 |
ielding | -0.112 |
Token | has |
Token ID | 468 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
moons | +0.007 |
horm | +0.007 |
nerv | +0.006 |
mosqu | +0.006 |
behavi | +0.006 |
Neg logit contributions | |
abase | -0.009 |
rador | -0.007 |
MB | -0.007 |
CAD | -0.007 |
ielding | -0.007 |
Token | denied |
Token ID | 6699 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
moons | +0.171 |
horm | +0.165 |
nerv | +0.159 |
mosqu | +0.153 |
behavi | +0.150 |
Neg logit contributions | |
abase | -0.208 |
rador | -0.167 |
MB | -0.165 |
CAD | -0.155 |
ielding | -0.154 |
Token | he |
Token ID | 339 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
abase | +0.136 |
rador | +0.110 |
MB | +0.109 |
CAD | +0.103 |
ielding | +0.102 |
Neg logit contributions | |
moons | -0.105 |
horm | -0.102 |
nerv | -0.098 |
mosqu | -0.095 |
behavi | -0.092 |
Token | coerced |
Token ID | 48474 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
moons | +0.317 |
horm | +0.306 |
nerv | +0.296 |
mosqu | +0.285 |
behavi | +0.278 |
Neg logit contributions | |
abase | -0.358 |
rador | -0.284 |
MB | -0.280 |
CAD | -0.264 |
ielding | -0.261 |
Token | La |
Token ID | 4689 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
moons | +0.391 |
horm | +0.378 |
nerv | +0.364 |
mosqu | +0.353 |
behavi | +0.343 |
Neg logit contributions | |
abase | -0.469 |
rador | -0.375 |
MB | -0.372 |
CAD | -0.349 |
ielding | -0.346 |
Token | Feb |
Token ID | 15146 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
abase | +0.534 |
rador | +0.409 |
MB | +0.400 |
CAD | +0.374 |
ielding | +0.370 |
Neg logit contributions | |
moons | -0.604 |
horm | -0.587 |
nerv | -0.566 |
mosqu | -0.547 |
behavi | -0.533 |
Token | re |
Token ID | 260 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
moons | +0.767 |
horm | +0.739 |
nerv | +0.713 |
mosqu | +0.672 |
behavi | +0.652 |
Neg logit contributions | |
abase | -0.810 |
MB | -0.629 |
rador | -0.627 |
CAD | -0.585 |
ielding | -0.574 |
Token | into |
Token ID | 656 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
moons | +0.974 |
horm | +0.935 |
nerv | +0.899 |
mosqu | +0.859 |
behavi | +0.834 |
Neg logit contributions | |
abase | -1.526 |
rador | -1.254 |
MB | -1.240 |
CAD | -1.177 |
ielding | -1.168 |
Token | filing |
Token ID | 12180 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
moons | +0.644 |
horm | +0.618 |
nerv | +0.591 |
mosqu | +0.563 |
behavi | +0.546 |
Neg logit contributions | |
abase | -1.097 |
rador | -0.906 |
MB | -0.894 |
CAD | -0.850 |
ielding | -0.846 |
Token | the |
Token ID | 262 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
abase | +0.038 |
rador | +0.030 |
MB | +0.030 |
CAD | +0.028 |
ielding | +0.028 |
Neg logit contributions | |
moons | -0.032 |
horm | -0.031 |
nerv | -0.029 |
mosqu | -0.029 |
behavi | -0.028 |
Token | s |
Token ID | 82 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
moons | +0.183 |
horm | +0.177 |
nerv | +0.170 |
mosqu | +0.165 |
behavi | +0.160 |
Neg logit contributions | |
abase | -0.237 |
rador | -0.191 |
MB | -0.190 |
CAD | -0.178 |
ielding | -0.177 |
Token | a |
Token ID | 257 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
abase | +0.582 |
rador | +0.462 |
MB | +0.460 |
CAD | +0.431 |
ielding | +0.424 |
Neg logit contributions | |
moons | -0.518 |
horm | -0.505 |
nerv | -0.483 |
mosqu | -0.472 |
behavi | -0.460 |
Token | moving |
Token ID | 3867 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
moons | +0.316 |
horm | +0.307 |
nerv | +0.295 |
mosqu | +0.286 |
behavi | +0.279 |
Neg logit contributions | |
abase | -0.367 |
rador | -0.293 |
MB | -0.290 |
CAD | -0.272 |
ielding | -0.269 |
Token | target |
Token ID | 2496 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
moons | +0.488 |
horm | +0.474 |
nerv | +0.454 |
mosqu | +0.443 |
behavi | +0.430 |
Neg logit contributions | |
abase | -0.596 |
rador | -0.478 |
MB | -0.477 |
CAD | -0.447 |
ielding | -0.440 |
Token | because |
Token ID | 780 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
moons | +0.334 |
horm | +0.324 |
nerv | +0.309 |
mosqu | +0.301 |
behavi | +0.291 |
Neg logit contributions | |
abase | -0.458 |
rador | -0.371 |
MB | -0.369 |
CAD | -0.347 |
ielding | -0.344 |
Token | it |
Token ID | 340 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
moons | +0.624 |
horm | +0.597 |
nerv | +0.582 |
mosqu | +0.556 |
behavi | +0.542 |
Neg logit contributions | |
abase | -0.736 |
rador | -0.591 |
MB | -0.576 |
CAD | -0.543 |
ielding | -0.543 |
Token | keeps |
Token ID | 7622 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
abase | +0.054 |
rador | +0.043 |
MB | +0.043 |
CAD | +0.040 |
ielding | +0.040 |
Neg logit contributions | |
moons | -0.044 |
horm | -0.043 |
nerv | -0.041 |
mosqu | -0.040 |
behavi | -0.039 |
Token | changing |
Token ID | 5609 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
abase | +0.020 |
rador | +0.016 |
MB | +0.016 |
CAD | +0.015 |
ielding | +0.015 |
Neg logit contributions | |
moons | -0.016 |
horm | -0.016 |
nerv | -0.015 |
mosqu | -0.015 |
behavi | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
moons | +0.041 |
horm | +0.040 |
nerv | +0.038 |
mosqu | +0.037 |
behavi | +0.036 |
Neg logit contributions | |
abase | -0.057 |
MB | -0.047 |
rador | -0.046 |
CAD | -0.044 |
ielding | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
moons | +0.183 |
horm | +0.176 |
nerv | +0.171 |
mosqu | +0.163 |
behavi | +0.160 |
Neg logit contributions | |
abase | -0.210 |
rador | -0.167 |
MB | -0.164 |
ielding | -0.154 |
CAD | -0.154 |
Token |
|
Token ID | 198 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
moons | +0.516 |
horm | +0.487 |
nerv | +0.475 |
mosqu | +0.429 |
behavi | +0.422 |
Neg logit contributions | |
abase | -0.685 |
rador | -0.554 |
MB | -0.533 |
ielding | -0.509 |
CAD | -0.506 |
Token | Drive |
Token ID | 9974 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
abase | +0.171 |
rador | +0.137 |
MB | +0.136 |
CAD | +0.128 |
ielding | +0.127 |
Neg logit contributions | |
moons | -0.136 |
horm | -0.132 |
nerv | -0.127 |
mosqu | -0.123 |
behavi | -0.120 |
Token | In |
Token ID | 554 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
abase | +0.639 |
MB | +0.484 |
rador | +0.484 |
CAD | +0.448 |
ielding | +0.443 |
Neg logit contributions | |
moons | -0.739 |
horm | -0.722 |
nerv | -0.700 |
mosqu | -0.679 |
behavi | -0.667 |
Token | . |
Token ID | 13 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
abase | +0.091 |
rador | +0.074 |
MB | +0.073 |
CAD | +0.069 |
ielding | +0.068 |
Neg logit contributions | |
moons | -0.071 |
horm | -0.069 |
nerv | -0.066 |
mosqu | -0.064 |
behavi | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
moons | +0.245 |
horm | +0.236 |
nerv | +0.228 |
mosqu | +0.220 |
behavi | +0.214 |
Neg logit contributions | |
abase | -0.285 |
rador | -0.227 |
MB | -0.224 |
CAD | -0.210 |
ielding | -0.209 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
moons | +0.263 |
horm | +0.250 |
nerv | +0.243 |
mosqu | +0.223 |
behavi | +0.218 |
Neg logit contributions | |
abase | -0.341 |
rador | -0.276 |
MB | -0.267 |
ielding | -0.253 |
CAD | -0.253 |
Token | Call |
Token ID | 14134 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
moons | +0.186 |
horm | +0.180 |
nerv | +0.173 |
mosqu | +0.167 |
behavi | +0.163 |
Neg logit contributions | |
abase | -0.201 |
rador | -0.159 |
MB | -0.157 |
CAD | -0.147 |
ielding | -0.145 |
Token | 440 |
Token ID | 33879 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
abase | +0.482 |
rador | +0.381 |
MB | +0.376 |
CAD | +0.352 |
ielding | +0.350 |
Neg logit contributions | |
moons | -0.447 |
horm | -0.433 |
nerv | -0.418 |
mosqu | -0.405 |
behavi | -0.395 |
Token | - |
Token ID | 12 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
moons | +0.639 |
horm | +0.616 |
nerv | +0.599 |
mosqu | +0.583 |
behavi | +0.569 |
Neg logit contributions | |
abase | -0.568 |
rador | -0.434 |
MB | -0.424 |
CAD | -0.395 |
ielding | -0.393 |
Token | 327 |
Token ID | 34159 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
abase | +0.155 |
rador | +0.123 |
MB | +0.122 |
CAD | +0.114 |
ielding | +0.113 |
Neg logit contributions | |
moons | -0.138 |
horm | -0.134 |
nerv | -0.129 |
mosqu | -0.125 |
behavi | -0.122 |
Token | - |
Token ID | 12 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
abase | +0.505 |
rador | +0.386 |
MB | +0.378 |
CAD | +0.350 |
ielding | +0.348 |
Neg logit contributions | |
moons | -0.587 |
horm | -0.569 |
nerv | -0.552 |
mosqu | -0.532 |
behavi | -0.521 |
Token | 9 |
Token ID | 24 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
abase | +0.439 |
rador | +0.354 |
MB | +0.351 |
CAD | +0.330 |
ielding | +0.327 |
Neg logit contributions | |
moons | -0.343 |
horm | -0.331 |
nerv | -0.319 |
mosqu | -0.308 |
behavi | -0.300 |
Token | in |
Token ID | 259 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
moons | +0.687 |
horm | +0.661 |
nerv | +0.640 |
mosqu | +0.618 |
behavi | +0.603 |
Neg logit contributions | |
abase | -0.661 |
rador | -0.514 |
MB | -0.508 |
CAD | -0.472 |
ielding | -0.468 |
Token | support |
Token ID | 1104 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
moons | +0.190 |
horm | +0.183 |
nerv | +0.175 |
mosqu | +0.169 |
behavi | +0.164 |
Neg logit contributions | |
abase | -0.293 |
rador | -0.240 |
MB | -0.238 |
CAD | -0.225 |
ielding | -0.224 |
Token | for |
Token ID | 329 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
moons | +0.232 |
horm | +0.225 |
nerv | +0.217 |
mosqu | +0.210 |
behavi | +0.205 |
Neg logit contributions | |
abase | -0.258 |
rador | -0.204 |
MB | -0.202 |
CAD | -0.189 |
ielding | -0.188 |
Token | Snap |
Token ID | 16026 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
moons | +0.264 |
horm | +0.253 |
nerv | +0.242 |
mosqu | +0.232 |
behavi | +0.225 |
Neg logit contributions | |
abase | -0.428 |
rador | -0.353 |
MB | -0.348 |
CAD | -0.330 |
ielding | -0.329 |
Token | . |
Token ID | 13 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
abase | +0.242 |
rador | +0.198 |
MB | +0.197 |
CAD | +0.186 |
ielding | +0.185 |
Neg logit contributions | |
moons | -0.157 |
horm | -0.152 |
nerv | -0.145 |
mosqu | -0.140 |
behavi | -0.135 |
Token | Meanwhile |
Token ID | 11214 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
moons | +0.016 |
horm | +0.016 |
nerv | +0.015 |
mosqu | +0.015 |
behavi | +0.014 |
Neg logit contributions | |
abase | -0.019 |
rador | -0.015 |
MB | -0.015 |
CAD | -0.014 |
ielding | -0.014 |
Token | Flat |
Token ID | 21939 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
moons | +1.290 |
horm | +1.226 |
nerv | +1.191 |
mosqu | +1.152 |
behavi | +1.110 |
Neg logit contributions | |
abase | -1.551 |
rador | -1.247 |
MB | -1.216 |
ielding | -1.149 |
CAD | -1.145 |
Token | pak |
Token ID | 41091 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
abase | +0.347 |
rador | +0.254 |
MB | +0.251 |
CAD | +0.228 |
ielding | +0.225 |
Neg logit contributions | |
moons | -0.505 |
horm | -0.494 |
nerv | -0.479 |
mosqu | -0.469 |
behavi | -0.460 |
Token | has |
Token ID | 468 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
moons | +0.087 |
horm | +0.085 |
nerv | +0.081 |
mosqu | +0.079 |
behavi | +0.077 |
Neg logit contributions | |
abase | -0.112 |
rador | -0.090 |
MB | -0.090 |
CAD | -0.085 |
ielding | -0.084 |
Token | not |
Token ID | 407 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
abase | +0.551 |
rador | +0.438 |
MB | +0.434 |
CAD | +0.407 |
ielding | +0.403 |
Neg logit contributions | |
moons | -0.480 |
horm | -0.465 |
nerv | -0.449 |
mosqu | -0.435 |
behavi | -0.423 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
moons | +0.096 |
horm | +0.093 |
nerv | +0.089 |
mosqu | +0.086 |
behavi | +0.084 |
Neg logit contributions | |
abase | -0.119 |
rador | -0.095 |
MB | -0.094 |
CAD | -0.089 |
ielding | -0.088 |
Token | stats |
Token ID | 9756 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
moons | +0.311 |
horm | +0.302 |
nerv | +0.291 |
mosqu | +0.282 |
behavi | +0.275 |
Neg logit contributions | |
abase | -0.346 |
rador | -0.274 |
MB | -0.272 |
CAD | -0.255 |
ielding | -0.252 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
abase | +0.267 |
rador | +0.215 |
MB | +0.214 |
CAD | +0.202 |
ielding | +0.200 |
Neg logit contributions | |
moons | -0.207 |
horm | -0.202 |
nerv | -0.193 |
mosqu | -0.188 |
behavi | -0.182 |
Token | including |
Token ID | 1390 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
moons | +0.108 |
horm | +0.105 |
nerv | +0.100 |
mosqu | +0.097 |
behavi | +0.094 |
Neg logit contributions | |
abase | -0.156 |
rador | -0.127 |
MB | -0.126 |
CAD | -0.119 |
ielding | -0.118 |
Token | last |
Token ID | 938 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
abase | +0.018 |
rador | +0.015 |
MB | +0.014 |
CAD | +0.013 |
ielding | +0.013 |
Neg logit contributions | |
moons | -0.018 |
horm | -0.017 |
nerv | -0.017 |
mosqu | -0.016 |
behavi | -0.016 |
Token | week |
Token ID | 1285 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
moons | +0.677 |
horm | +0.652 |
nerv | +0.631 |
mosqu | +0.607 |
behavi | +0.591 |
Neg logit contributions | |
abase | -0.779 |
rador | -0.622 |
MB | -0.611 |
CAD | -0.574 |
ielding | -0.573 |
Token | against |
Token ID | 1028 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
abase | +0.224 |
rador | +0.180 |
MB | +0.178 |
CAD | +0.168 |
ielding | +0.166 |
Neg logit contributions | |
moons | -0.176 |
horm | -0.170 |
nerv | -0.163 |
mosqu | -0.158 |
behavi | -0.153 |
Token | San |
Token ID | 2986 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
moons | +0.226 |
horm | +0.219 |
nerv | +0.211 |
mosqu | +0.205 |
behavi | +0.200 |
Neg logit contributions | |
abase | -0.258 |
rador | -0.205 |
MB | -0.203 |
CAD | -0.190 |
ielding | -0.189 |
Token | Diego |
Token ID | 9500 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
abase | +0.222 |
rador | +0.179 |
MB | +0.177 |
CAD | +0.167 |
ielding | +0.165 |
Neg logit contributions | |
moons | -0.172 |
horm | -0.166 |
nerv | -0.160 |
mosqu | -0.154 |
behavi | -0.150 |
Token | when |
Token ID | 618 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
abase | +0.183 |
rador | +0.149 |
MB | +0.148 |
CAD | +0.139 |
ielding | +0.138 |
Neg logit contributions | |
moons | -0.130 |
horm | -0.126 |
nerv | -0.120 |
mosqu | -0.116 |
behavi | -0.113 |
Token | he |
Token ID | 339 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
abase | +0.229 |
rador | +0.186 |
MB | +0.184 |
CAD | +0.174 |
ielding | +0.172 |
Neg logit contributions | |
moons | -0.166 |
horm | -0.160 |
nerv | -0.154 |
mosqu | -0.148 |
behavi | -0.144 |
Token | scored |
Token ID | 7781 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
abase | +0.462 |
rador | +0.377 |
MB | +0.372 |
CAD | +0.352 |
ielding | +0.349 |
Neg logit contributions | |
moons | -0.323 |
horm | -0.309 |
nerv | -0.299 |
mosqu | -0.285 |
behavi | -0.276 |
Token | T |
Token ID | 51 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
abase | +0.571 |
rador | +0.462 |
MB | +0.456 |
CAD | +0.433 |
ielding | +0.429 |
Neg logit contributions | |
moons | -0.453 |
horm | -0.431 |
nerv | -0.416 |
mosqu | -0.406 |
behavi | -0.392 |
Token | unes |
Token ID | 4015 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
abase | +0.254 |
rador | +0.199 |
MB | +0.196 |
CAD | +0.183 |
ielding | +0.181 |
Neg logit contributions | |
moons | -0.256 |
horm | -0.249 |
nerv | -0.241 |
mosqu | -0.234 |
behavi | -0.228 |
Token | feed |
Token ID | 3745 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
abase | +1.460 |
rador | +1.117 |
MB | +1.107 |
CAD | +1.020 |
ielding | +1.007 |
Neg logit contributions | |
moons | -1.723 |
horm | -1.688 |
nerv | -1.631 |
mosqu | -1.593 |
behavi | -1.553 |
Token | ) |
Token ID | 8 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
abase | +0.295 |
rador | +0.221 |
MB | +0.217 |
CAD | +0.200 |
ielding | +0.198 |
Neg logit contributions | |
moons | -0.374 |
horm | -0.364 |
nerv | -0.353 |
mosqu | -0.343 |
behavi | -0.336 |
Token |
|
Token ID | 198 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
moons | +0.600 |
horm | +0.579 |
nerv | +0.556 |
mosqu | +0.539 |
behavi | +0.524 |
Neg logit contributions | |
abase | -0.769 |
rador | -0.618 |
MB | -0.611 |
CAD | -0.576 |
ielding | -0.573 |
Token |
|
Token ID | 198 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
abase | +0.033 |
rador | +0.027 |
MB | +0.026 |
CAD | +0.025 |
ielding | +0.025 |
Neg logit contributions | |
moons | -0.026 |
horm | -0.025 |
nerv | -0.024 |
mosqu | -0.023 |
behavi | -0.022 |
Token | If |
Token ID | 1532 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
moons | +0.025 |
horm | +0.024 |
nerv | +0.023 |
mosqu | +0.022 |
behavi | +0.021 |
Neg logit contributions | |
abase | -0.035 |
rador | -0.029 |
MB | -0.028 |
CAD | -0.027 |
ielding | -0.027 |
Token | you |
Token ID | 345 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
abase | +0.217 |
rador | +0.170 |
MB | +0.168 |
CAD | +0.157 |
ielding | +0.155 |
Neg logit contributions | |
moons | -0.212 |
horm | -0.206 |
nerv | -0.199 |
mosqu | -0.193 |
behavi | -0.188 |
Token | have |
Token ID | 423 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
abase | +0.229 |
rador | +0.184 |
MB | +0.183 |
CAD | +0.173 |
ielding | +0.170 |
Neg logit contributions | |
moons | -0.180 |
horm | -0.175 |
nerv | -0.168 |
mosqu | -0.163 |
behavi | -0.159 |
Token | a |
Token ID | 257 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
moons | +0.303 |
horm | +0.291 |
nerv | +0.280 |
mosqu | +0.269 |
behavi | +0.261 |
Neg logit contributions | |
abase | -0.422 |
rador | -0.344 |
MB | -0.338 |
CAD | -0.320 |
ielding | -0.319 |
Token | moment |
Token ID | 2589 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
moons | +0.129 |
horm | +0.124 |
nerv | +0.120 |
mosqu | +0.115 |
behavi | +0.112 |
Neg logit contributions | |
abase | -0.172 |
rador | -0.139 |
MB | -0.138 |
CAD | -0.130 |
ielding | -0.129 |
Token | exponentially |
Token ID | 35529 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
moons | +0.153 |
horm | +0.148 |
nerv | +0.142 |
mosqu | +0.137 |
behavi | +0.133 |
Neg logit contributions | |
abase | -0.207 |
rador | -0.167 |
MB | -0.166 |
CAD | -0.156 |
ielding | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
abase | +0.014 |
MB | +0.011 |
rador | +0.011 |
CAD | +0.011 |
ielding | +0.010 |
Neg logit contributions | |
moons | -0.010 |
horm | -0.010 |
nerv | -0.009 |
mosqu | -0.009 |
behavi | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
abase | +0.269 |
rador | +0.220 |
MB | +0.220 |
CAD | +0.208 |
ielding | +0.206 |
Neg logit contributions | |
moons | -0.176 |
horm | -0.170 |
nerv | -0.163 |
mosqu | -0.158 |
behavi | -0.153 |
Token | implications |
Token ID | 10939 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
moons | +0.164 |
horm | +0.159 |
nerv | +0.153 |
mosqu | +0.148 |
behavi | +0.144 |
Neg logit contributions | |
abase | -0.197 |
rador | -0.158 |
MB | -0.156 |
CAD | -0.146 |
ielding | -0.145 |
Token | for |
Token ID | 329 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
moons | +0.084 |
horm | +0.082 |
nerv | +0.079 |
mosqu | +0.077 |
behavi | +0.075 |
Neg logit contributions | |
abase | -0.092 |
rador | -0.073 |
MB | -0.073 |
CAD | -0.068 |
ielding | -0.067 |
Token | our |
Token ID | 674 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
moons | +0.621 |
horm | +0.600 |
nerv | +0.576 |
mosqu | +0.556 |
behavi | +0.542 |
Neg logit contributions | |
abase | -0.783 |
rador | -0.630 |
MB | -0.622 |
CAD | -0.585 |
ielding | -0.582 |
Token | common |
Token ID | 2219 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
moons | +0.421 |
horm | +0.406 |
nerv | +0.389 |
mosqu | +0.374 |
behavi | +0.364 |
Neg logit contributions | |
abase | -0.591 |
rador | -0.481 |
MB | -0.475 |
CAD | -0.449 |
ielding | -0.446 |
Token | security |
Token ID | 2324 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
abase | +0.703 |
rador | +0.576 |
MB | +0.574 |
CAD | +0.543 |
ielding | +0.539 |
Neg logit contributions | |
moons | -0.450 |
horm | -0.435 |
nerv | -0.416 |
mosqu | -0.402 |
behavi | -0.387 |
Token | . |
Token ID | 13 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
abase | +0.737 |
rador | +0.599 |
MB | +0.595 |
CAD | +0.563 |
ielding | +0.558 |
Neg logit contributions | |
moons | -0.524 |
horm | -0.507 |
nerv | -0.485 |
mosqu | -0.470 |
behavi | -0.455 |
Token |
|
Token ID | 198 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
abase | +0.003 |
rador | +0.003 |
MB | +0.003 |
CAD | +0.002 |
ielding | +0.002 |
Neg logit contributions | |
moons | -0.003 |
horm | -0.003 |
nerv | -0.003 |
mosqu | -0.003 |
behavi | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
abase | +0.139 |
rador | +0.112 |
MB | +0.109 |
CAD | +0.103 |
ielding | +0.103 |
Neg logit contributions | |
moons | -0.113 |
horm | -0.108 |
nerv | -0.105 |
mosqu | -0.099 |
behavi | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
moons | +0.221 |
horm | +0.214 |
nerv | +0.205 |
mosqu | +0.198 |
behavi | +0.192 |
Neg logit contributions | |
abase | -0.314 |
rador | -0.256 |
MB | -0.254 |
CAD | -0.240 |
ielding | -0.237 |
Token | On |
Token ID | 1550 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
moons | +0.122 |
horm | +0.118 |
nerv | +0.114 |
mosqu | +0.110 |
behavi | +0.107 |
Neg logit contributions | |
abase | -0.144 |
rador | -0.115 |
MB | -0.114 |
CAD | -0.107 |
ielding | -0.106 |
Token | 28 |
Token ID | 2579 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
abase | +0.115 |
rador | +0.089 |
MB | +0.087 |
CAD | +0.081 |
ielding | +0.081 |
Neg logit contributions | |
moons | -0.120 |
horm | -0.116 |
nerv | -0.112 |
mosqu | -0.108 |
behavi | -0.106 |
Token | April |
Token ID | 3035 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
moons | +0.375 |
horm | +0.361 |
nerv | +0.349 |
mosqu | +0.336 |
behavi | +0.327 |
Neg logit contributions | |
abase | -0.451 |
rador | -0.361 |
MB | -0.356 |
CAD | -0.335 |
ielding | -0.333 |
Token | , |
Token ID | 11 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
abase | +0.246 |
rador | +0.195 |
MB | +0.193 |
CAD | +0.181 |
ielding | +0.180 |
Neg logit contributions | |
moons | -0.218 |
horm | -0.211 |
nerv | -0.204 |
mosqu | -0.197 |
behavi | -0.192 |
Token | European |
Token ID | 3427 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
moons | +0.032 |
horm | +0.030 |
nerv | +0.029 |
mosqu | +0.028 |
behavi | +0.027 |
Neg logit contributions | |
abase | -0.041 |
rador | -0.033 |
MB | -0.032 |
CAD | -0.031 |
ielding | -0.031 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
moons | +0.258 |
horm | +0.248 |
nerv | +0.238 |
mosqu | +0.229 |
behavi | +0.223 |
Neg logit contributions | |
abase | -0.346 |
rador | -0.279 |
MB | -0.275 |
CAD | -0.260 |
ielding | -0.258 |
Token | of |
Token ID | 286 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
moons | +0.875 |
horm | +0.847 |
nerv | +0.816 |
mosqu | +0.787 |
behavi | +0.765 |
Neg logit contributions | |
abase | -1.036 |
rador | -0.820 |
MB | -0.808 |
CAD | -0.761 |
ielding | -0.761 |
Token | Human |
Token ID | 5524 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
abase | +0.335 |
rador | +0.266 |
MB | +0.261 |
CAD | +0.247 |
ielding | +0.245 |
Neg logit contributions | |
moons | -0.289 |
horm | -0.280 |
nerv | -0.270 |
mosqu | -0.260 |
behavi | -0.254 |
Token | Rights |
Token ID | 6923 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
abase | +0.490 |
rador | +0.398 |
MB | +0.395 |
CAD | +0.372 |
ielding | +0.369 |
Neg logit contributions | |
moons | -0.352 |
horm | -0.340 |
nerv | -0.327 |
mosqu | -0.315 |
behavi | -0.306 |
Token | demanded |
Token ID | 12284 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
moons | +0.031 |
horm | +0.030 |
nerv | +0.029 |
mosqu | +0.028 |
behavi | +0.027 |
Neg logit contributions | |
abase | -0.042 |
rador | -0.034 |
MB | -0.034 |
CAD | -0.032 |
ielding | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
moons | +0.006 |
horm | +0.005 |
nerv | +0.005 |
mosqu | +0.005 |
behavi | +0.005 |
Neg logit contributions | |
abase | -0.007 |
rador | -0.005 |
MB | -0.005 |
CAD | -0.005 |
ielding | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
moons | +0.272 |
horm | +0.259 |
nerv | +0.252 |
mosqu | +0.233 |
behavi | +0.228 |
Neg logit contributions | |
abase | -0.349 |
rador | -0.281 |
MB | -0.273 |
ielding | -0.259 |
CAD | -0.258 |
Token | How |
Token ID | 2437 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
moons | +0.175 |
horm | +0.169 |
nerv | +0.163 |
mosqu | +0.156 |
behavi | +0.152 |
Neg logit contributions | |
abase | -0.220 |
rador | -0.177 |
MB | -0.174 |
CAD | -0.164 |
ielding | -0.163 |
Token | in |
Token ID | 287 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
moons | +0.376 |
horm | +0.363 |
nerv | +0.350 |
mosqu | +0.338 |
behavi | +0.329 |
Neg logit contributions | |
abase | -0.469 |
rador | -0.377 |
MB | -0.373 |
CAD | -0.351 |
ielding | -0.349 |
Token | the |
Token ID | 262 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
abase | +0.784 |
rador | +0.628 |
MB | +0.625 |
CAD | +0.586 |
ielding | +0.580 |
Neg logit contributions | |
moons | -0.651 |
horm | -0.629 |
nerv | -0.607 |
mosqu | -0.589 |
behavi | -0.572 |
Token | hell |
Token ID | 5968 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
abase | +0.033 |
rador | +0.027 |
MB | +0.026 |
CAD | +0.025 |
ielding | +0.025 |
Neg logit contributions | |
moons | -0.025 |
horm | -0.024 |
nerv | -0.023 |
mosqu | -0.023 |
behavi | -0.022 |
Token | could |
Token ID | 714 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
moons | +1.492 |
horm | +1.425 |
nerv | +1.379 |
mosqu | +1.307 |
behavi | +1.282 |
Neg logit contributions | |
abase | -2.165 |
rador | -1.767 |
MB | -1.731 |
ielding | -1.647 |
CAD | -1.640 |
Token | a |
Token ID | 257 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
moons | +0.713 |
horm | +0.690 |
nerv | +0.665 |
mosqu | +0.638 |
behavi | +0.624 |
Neg logit contributions | |
abase | -0.803 |
rador | -0.636 |
MB | -0.622 |
ielding | -0.586 |
CAD | -0.584 |
Token | man |
Token ID | 582 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
abase | +0.017 |
rador | +0.014 |
MB | +0.014 |
CAD | +0.013 |
ielding | +0.013 |
Neg logit contributions | |
moons | -0.014 |
horm | -0.014 |
nerv | -0.013 |
mosqu | -0.013 |
behavi | -0.012 |
Token | enjoy |
Token ID | 2883 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
abase | +0.840 |
rador | +0.679 |
MB | +0.675 |
CAD | +0.637 |
ielding | +0.630 |
Neg logit contributions | |
moons | -0.614 |
horm | -0.596 |
nerv | -0.569 |
mosqu | -0.556 |
behavi | -0.540 |
Token | being |
Token ID | 852 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
moons | +0.627 |
horm | +0.604 |
nerv | +0.582 |
mosqu | +0.560 |
behavi | +0.546 |
Neg logit contributions | |
abase | -0.789 |
rador | -0.633 |
MB | -0.624 |
CAD | -0.588 |
ielding | -0.587 |
Token | 07 |
Token ID | 8753 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
moons | +0.647 |
horm | +0.627 |
nerv | +0.610 |
mosqu | +0.587 |
behavi | +0.574 |
Neg logit contributions | |
abase | -0.502 |
rador | -0.377 |
MB | -0.362 |
ielding | -0.337 |
CAD | -0.334 |
Token | : |
Token ID | 25 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
moons | +0.140 |
horm | +0.134 |
nerv | +0.129 |
mosqu | +0.122 |
behavi | +0.118 |
Neg logit contributions | |
abase | -0.190 |
rador | -0.154 |
MB | -0.151 |
CAD | -0.143 |
ielding | -0.142 |
Token | 44 |
Token ID | 2598 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
moons | +0.391 |
horm | +0.375 |
nerv | +0.358 |
mosqu | +0.340 |
behavi | +0.329 |
Neg logit contributions | |
abase | -0.647 |
rador | -0.534 |
MB | -0.527 |
CAD | -0.501 |
ielding | -0.498 |
Token | Se |
Token ID | 1001 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
moons | +0.221 |
horm | +0.214 |
nerv | +0.205 |
mosqu | +0.198 |
behavi | +0.193 |
Neg logit contributions | |
abase | -0.315 |
rador | -0.257 |
MB | -0.256 |
CAD | -0.241 |
ielding | -0.238 |
Token | eker |
Token ID | 28233 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
moons | +1.369 |
horm | +1.339 |
nerv | +1.290 |
mosqu | +1.246 |
behavi | +1.210 |
Neg logit contributions | |
abase | -1.349 |
rador | -1.061 |
MB | -1.047 |
CAD | -0.979 |
ielding | -0.962 |
Token | wrote |
Token ID | 2630 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
moons | +0.711 |
horm | +0.690 |
nerv | +0.664 |
mosqu | +0.644 |
behavi | +0.628 |
Neg logit contributions | |
abase | -0.813 |
rador | -0.647 |
MB | -0.641 |
CAD | -0.601 |
ielding | -0.595 |
Token | : |
Token ID | 25 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
moons | +1.816 |
horm | +1.669 |
nerv | +1.658 |
Sparrow | +1.404 |
Quake | +1.400 |
Neg logit contributions | |
abase | -2.900 |
rador | -2.385 |
MB | -2.277 |
ielding | -2.210 |
CAD | -2.173 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
moons | +1.102 |
horm | +1.053 |
nerv | +1.021 |
mosqu | +0.950 |
behavi | +0.931 |
Neg logit contributions | |
abase | -1.398 |
rador | -1.125 |
MB | -1.098 |
CAD | -1.036 |
ielding | -1.035 |
Token |
|
Token ID | 198 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
moons | +1.205 |
horm | +1.134 |
nerv | +1.107 |
mosqu | +0.985 |
behavi | +0.976 |
Neg logit contributions | |
abase | -1.629 |
rador | -1.322 |
MB | -1.268 |
ielding | -1.210 |
CAD | -1.201 |
Token | Cl |
Token ID | 2601 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
moons | +1.131 |
horm | +1.090 |
nerv | +1.044 |
mosqu | +0.998 |
behavi | +0.969 |
Neg logit contributions | |
abase | -1.623 |
rador | -1.326 |
MB | -1.313 |
CAD | -1.244 |
ielding | -1.231 |
Token | arity |
Token ID | 6806 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
moons | +0.780 |
horm | +0.757 |
nerv | +0.734 |
mosqu | +0.709 |
behavi | +0.691 |
Neg logit contributions | |
abase | -0.704 |
rador | -0.542 |
MB | -0.538 |
CAD | -0.499 |
ielding | -0.489 |
Token | you |
Token ID | 345 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
moons | +0.082 |
horm | +0.080 |
nerv | +0.077 |
mosqu | +0.074 |
behavi | +0.072 |
Neg logit contributions | |
abase | -0.094 |
rador | -0.075 |
MB | -0.074 |
CAD | -0.069 |
ielding | -0.069 |
Token | � |
Token ID | 447 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
moons | +0.123 |
horm | +0.119 |
nerv | +0.114 |
mosqu | +0.111 |
behavi | +0.108 |
Neg logit contributions | |
abase | -0.150 |
rador | -0.120 |
MB | -0.119 |
CAD | -0.112 |
ielding | -0.111 |
Token | � |
Token ID | 247 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
moons | +0.297 |
horm | +0.288 |
nerv | +0.277 |
mosqu | +0.266 |
behavi | +0.258 |
Neg logit contributions | |
abase | -0.361 |
rador | -0.289 |
MB | -0.284 |
CAD | -0.269 |
ielding | -0.266 |
Token | re |
Token ID | 260 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
moons | +0.360 |
horm | +0.350 |
nerv | +0.338 |
mosqu | +0.331 |
behavi | +0.324 |
Neg logit contributions | |
abase | -0.338 |
rador | -0.262 |
MB | -0.260 |
CAD | -0.241 |
ielding | -0.239 |
Token | not |
Token ID | 407 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
moons | +0.140 |
horm | +0.135 |
nerv | +0.131 |
mosqu | +0.125 |
behavi | +0.122 |
Neg logit contributions | |
abase | -0.168 |
rador | -0.135 |
MB | -0.133 |
CAD | -0.125 |
ielding | -0.124 |
Token | just |
Token ID | 655 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
abase | +0.236 |
rador | +0.188 |
MB | +0.187 |
CAD | +0.176 |
ielding | +0.174 |
Neg logit contributions | |
moons | -0.199 |
horm | -0.193 |
nerv | -0.186 |
mosqu | -0.180 |
behavi | -0.176 |
Token | waiting |
Token ID | 4953 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
moons | +1.813 |
horm | +1.733 |
nerv | +1.702 |
mosqu | +1.606 |
behavi | +1.576 |
Neg logit contributions | |
abase | -2.253 |
rador | -1.819 |
MB | -1.771 |
CAD | -1.676 |
ielding | -1.675 |
Token | for |
Token ID | 329 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
abase | +0.286 |
rador | +0.226 |
MB | +0.224 |
CAD | +0.210 |
ielding | +0.208 |
Neg logit contributions | |
moons | -0.260 |
horm | -0.253 |
nerv | -0.244 |
mosqu | -0.237 |
behavi | -0.231 |
Token | a |
Token ID | 257 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
abase | +1.112 |
MB | +0.890 |
rador | +0.882 |
CAD | +0.827 |
ielding | +0.810 |
Neg logit contributions | |
moons | -0.968 |
horm | -0.948 |
nerv | -0.904 |
mosqu | -0.888 |
behavi | -0.866 |
Token | surprise |
Token ID | 5975 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
abase | +0.099 |
rador | +0.080 |
MB | +0.079 |
CAD | +0.074 |
ielding | +0.074 |
Neg logit contributions | |
moons | -0.075 |
horm | -0.073 |
nerv | -0.070 |
mosqu | -0.067 |
behavi | -0.065 |
Token | — |
Token ID | 851 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
abase | +0.662 |
rador | +0.533 |
MB | +0.533 |
CAD | +0.501 |
ielding | +0.494 |
Neg logit contributions | |
moons | -0.507 |
horm | -0.493 |
nerv | -0.470 |
mosqu | -0.458 |
behavi | -0.445 |
Token | [ |
Token ID | 685 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
moons | +0.124 |
horm | +0.121 |
nerv | +0.117 |
mosqu | +0.114 |
behavi | +0.111 |
Neg logit contributions | |
abase | -0.113 |
rador | -0.087 |
MB | -0.087 |
CAD | -0.080 |
ielding | -0.079 |
Token | 10 |
Token ID | 940 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
moons | +0.038 |
horm | +0.037 |
nerv | +0.035 |
mosqu | +0.034 |
behavi | +0.033 |
Neg logit contributions | |
abase | -0.051 |
rador | -0.041 |
MB | -0.041 |
CAD | -0.038 |
ielding | -0.038 |
Token | : |
Token ID | 25 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
moons | +0.624 |
horm | +0.585 |
nerv | +0.570 |
mosqu | +0.507 |
behavi | +0.495 |
Neg logit contributions | |
abase | -0.915 |
rador | -0.749 |
MB | -0.721 |
ielding | -0.691 |
CAD | -0.686 |
Token | 47 |
Token ID | 2857 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
moons | +1.025 |
horm | +0.986 |
nerv | +0.951 |
mosqu | +0.921 |
behavi | +0.888 |
Neg logit contributions | |
abase | -1.362 |
rador | -1.102 |
MB | -1.073 |
CAD | -1.023 |
ielding | -1.018 |
Token | ] |
Token ID | 60 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
moons | +1.677 |
horm | +1.572 |
nerv | +1.557 |
Sparrow | +1.397 |
Quake | +1.394 |
Neg logit contributions | |
abase | -1.547 |
rador | -1.196 |
MB | -1.111 |
ielding | -1.066 |
olesc | -1.038 |
Token | < |
Token ID | 1279 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
moons | +1.502 |
horm | +1.463 |
nerv | +1.419 |
mosqu | +1.384 |
behavi | +1.352 |
Neg logit contributions | |
abase | -1.177 |
rador | -0.885 |
MB | -0.867 |
CAD | -0.799 |
ielding | -0.794 |
Token | abal |
Token ID | 44349 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
moons | +1.704 |
horm | +1.654 |
nerv | +1.590 |
mosqu | +1.535 |
behavi | +1.485 |
Neg logit contributions | |
abase | -1.865 |
rador | -1.482 |
MB | -1.474 |
CAD | -1.387 |
ielding | -1.360 |
Token | icious |
Token ID | 6243 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
moons | +0.254 |
horm | +0.247 |
nerv | +0.238 |
mosqu | +0.230 |
behavi | +0.225 |
Neg logit contributions | |
abase | -0.277 |
rador | -0.219 |
MB | -0.217 |
CAD | -0.203 |
ielding | -0.201 |
Token | s |
Token ID | 82 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
abase | +0.409 |
rador | +0.322 |
MB | +0.319 |
CAD | +0.297 |
ielding | +0.295 |
Neg logit contributions | |
moons | -0.393 |
horm | -0.382 |
nerv | -0.369 |
mosqu | -0.358 |
behavi | -0.349 |
Token | > |
Token ID | 29 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
moons | +0.605 |
horm | +0.586 |
nerv | +0.565 |
mosqu | +0.546 |
behavi | +0.530 |
Neg logit contributions | |
abase | -0.682 |
rador | -0.541 |
MB | -0.537 |
CAD | -0.504 |
ielding | -0.498 |
Token | lol |
Token ID | 19462 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
moons | +0.874 |
horm | +0.845 |
nerv | +0.812 |
mosqu | +0.785 |
behavi | +0.764 |
Neg logit contributions | |
abase | -1.139 |
rador | -0.919 |
MB | -0.912 |
CAD | -0.859 |
ielding | -0.851 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
abase | +0.118 |
rador | +0.095 |
MB | +0.094 |
CAD | +0.089 |
ielding | +0.088 |
Neg logit contributions | |
moons | -0.094 |
horm | -0.091 |
nerv | -0.088 |
mosqu | -0.085 |
behavi | -0.083 |
Token | trial |
Token ID | 4473 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
abase | +0.195 |
rador | +0.159 |
MB | +0.158 |
CAD | +0.149 |
ielding | +0.148 |
Neg logit contributions | |
moons | -0.137 |
horm | -0.132 |
nerv | -0.126 |
mosqu | -0.122 |
behavi | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
moons | +0.371 |
horm | +0.359 |
nerv | +0.344 |
mosqu | +0.334 |
behavi | +0.325 |
Neg logit contributions | |
abase | -0.470 |
rador | -0.379 |
MB | -0.377 |
CAD | -0.355 |
ielding | -0.351 |
Token | As |
Token ID | 1081 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
moons | +0.154 |
horm | +0.149 |
nerv | +0.144 |
mosqu | +0.139 |
behavi | +0.136 |
Neg logit contributions | |
abase | -0.181 |
rador | -0.144 |
MB | -0.142 |
CAD | -0.133 |
ielding | -0.133 |
Token | you |
Token ID | 345 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
abase | +0.416 |
rador | +0.332 |
MB | +0.326 |
CAD | +0.306 |
ielding | +0.305 |
Neg logit contributions | |
moons | -0.360 |
horm | -0.348 |
nerv | -0.337 |
mosqu | -0.324 |
behavi | -0.316 |
Token | may |
Token ID | 743 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
moons | +0.507 |
horm | +0.490 |
nerv | +0.472 |
mosqu | +0.455 |
behavi | +0.443 |
Neg logit contributions | |
abase | -0.606 |
rador | -0.484 |
MB | -0.479 |
CAD | -0.450 |
ielding | -0.447 |
Token | recall |
Token ID | 10014 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
moons | +1.768 |
horm | +1.693 |
nerv | +1.649 |
mosqu | +1.559 |
behavi | +1.523 |
Neg logit contributions | |
abase | -1.765 |
rador | -1.389 |
MB | -1.364 |
ielding | -1.258 |
CAD | -1.255 |
Token | , |
Token ID | 11 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
moons | +0.610 |
horm | +0.589 |
nerv | +0.569 |
mosqu | +0.548 |
behavi | +0.536 |
Neg logit contributions | |
abase | -0.713 |
rador | -0.568 |
MB | -0.554 |
ielding | -0.525 |
CAD | -0.522 |
Token | on |
Token ID | 319 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
moons | +0.195 |
horm | +0.189 |
nerv | +0.182 |
mosqu | +0.176 |
behavi | +0.171 |
Neg logit contributions | |
abase | -0.238 |
rador | -0.191 |
MB | -0.188 |
CAD | -0.177 |
ielding | -0.176 |
Token | Monday |
Token ID | 3321 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
abase | +0.332 |
rador | +0.262 |
MB | +0.258 |
CAD | +0.242 |
ielding | +0.240 |
Neg logit contributions | |
moons | -0.310 |
horm | -0.300 |
nerv | -0.290 |
mosqu | -0.281 |
behavi | -0.274 |
Token | it |
Token ID | 340 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
moons | +0.042 |
horm | +0.040 |
nerv | +0.039 |
mosqu | +0.038 |
behavi | +0.037 |
Neg logit contributions | |
abase | -0.049 |
rador | -0.039 |
MB | -0.038 |
ielding | -0.036 |
CAD | -0.036 |