Token | Community |
Token ID | 8108 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
ariat | +0.066 |
rium | +0.064 |
Merit | +0.060 |
anity | +0.058 |
sup | +0.056 |
Neg logit contributions | |
hetical | -0.066 |
sequ | -0.065 |
pneum | -0.063 |
stro | -0.060 |
helic | -0.060 |
Token | Newspaper |
Token ID | 49598 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
hetical | +0.698 |
sequ | +0.671 |
pneum | +0.651 |
helic | +0.627 |
stro | +0.625 |
Neg logit contributions | |
ariat | -0.563 |
rium | -0.551 |
Merit | -0.494 |
anity | -0.484 |
sup | -0.468 |
Token | Group |
Token ID | 4912 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
ariat | +0.054 |
rium | +0.053 |
Merit | +0.050 |
anity | +0.048 |
sup | +0.047 |
Neg logit contributions | |
hetical | -0.040 |
sequ | -0.039 |
pneum | -0.037 |
helic | -0.035 |
stro | -0.035 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
hetical | +0.426 |
sequ | +0.419 |
pneum | +0.406 |
helic | +0.389 |
stro | +0.387 |
Neg logit contributions | |
ariat | -0.397 |
rium | -0.386 |
Merit | -0.356 |
anity | -0.345 |
sup | -0.328 |
Token | W |
Token ID | 54 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
hetical | +0.099 |
sequ | +0.097 |
pneum | +0.093 |
stro | +0.090 |
helic | +0.088 |
Neg logit contributions | |
ariat | -0.104 |
rium | -0.100 |
Merit | -0.093 |
anity | -0.091 |
sup | -0.089 |
Token | ired |
Token ID | 1202 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
ariat | +0.281 |
rium | +0.271 |
Merit | +0.253 |
anity | +0.245 |
sup | +0.238 |
Neg logit contributions | |
hetical | -0.296 |
sequ | -0.290 |
pneum | -0.279 |
stro | -0.268 |
helic | -0.267 |
Token | Equ |
Token ID | 7889 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ariat | +2.769 |
rium | +2.677 |
Merit | +2.505 |
anity | +2.445 |
sup | +2.362 |
Neg logit contributions | |
hetical | -2.872 |
sequ | -2.796 |
pneum | -2.704 |
helic | -2.592 |
stro | -2.579 |
Token | ivalent |
Token ID | 29540 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ariat | +0.977 |
rium | +0.943 |
Merit | +0.875 |
anity | +0.852 |
sup | +0.822 |
Neg logit contributions | |
hetical | -1.075 |
sequ | -1.054 |
pneum | -1.016 |
helic | -0.977 |
stro | -0.974 |
Token | Privacy |
Token ID | 16777 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
ariat | +0.897 |
rium | +0.868 |
Merit | +0.809 |
anity | +0.787 |
sup | +0.761 |
Neg logit contributions | |
hetical | -0.899 |
sequ | -0.881 |
pneum | -0.847 |
helic | -0.812 |
stro | -0.810 |
Token | ( |
Token ID | 357 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
hetical | +0.018 |
sequ | +0.018 |
pneum | +0.017 |
stro | +0.016 |
helic | +0.016 |
Neg logit contributions | |
ariat | -0.018 |
rium | -0.018 |
Merit | -0.016 |
anity | -0.016 |
sup | -0.015 |
Token | WE |
Token ID | 8845 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
hetical | +0.101 |
sequ | +0.098 |
pneum | +0.095 |
stro | +0.092 |
helic | +0.092 |
Neg logit contributions | |
ariat | -0.079 |
rium | -0.075 |
Merit | -0.069 |
anity | -0.068 |
sup | -0.065 |
Token | - |
Token ID | 12 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
ariat | +0.380 |
rium | +0.367 |
Merit | +0.341 |
anity | +0.331 |
sup | +0.321 |
Neg logit contributions | |
hetical | -0.386 |
sequ | -0.379 |
pneum | -0.363 |
stro | -0.349 |
helic | -0.348 |
Token | 08 |
Token ID | 2919 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
ariat | +0.442 |
rium | +0.428 |
Merit | +0.394 |
anity | +0.385 |
sup | +0.373 |
Neg logit contributions | |
hetical | -0.464 |
sequ | -0.456 |
pneum | -0.438 |
stro | -0.423 |
helic | -0.419 |
Token | Election |
Token ID | 14219 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ariat | +0.493 |
rium | +0.479 |
Merit | +0.450 |
anity | +0.438 |
sup | +0.426 |
Neg logit contributions | |
hetical | -0.401 |
sequ | -0.391 |
pneum | -0.375 |
stro | -0.357 |
helic | -0.357 |
Token | - |
Token ID | 12 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ariat | +0.897 |
rium | +0.866 |
Merit | +0.807 |
anity | +0.786 |
sup | +0.760 |
Neg logit contributions | |
hetical | -0.906 |
sequ | -0.888 |
pneum | -0.854 |
helic | -0.818 |
stro | -0.817 |
Token | W |
Token ID | 54 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
ariat | +0.182 |
rium | +0.176 |
Merit | +0.162 |
anity | +0.159 |
sup | +0.154 |
Neg logit contributions | |
hetical | -0.192 |
sequ | -0.188 |
pneum | -0.181 |
stro | -0.175 |
helic | -0.173 |
Token | asting |
Token ID | 9222 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
ariat | +0.450 |
rium | +0.436 |
Merit | +0.406 |
anity | +0.390 |
sup | +0.381 |
Neg logit contributions | |
hetical | -0.509 |
sequ | -0.496 |
pneum | -0.478 |
stro | -0.463 |
helic | -0.459 |
Token | Food |
Token ID | 7318 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
ariat | +2.310 |
rium | +2.235 |
Merit | +2.081 |
anity | +2.035 |
sup | +1.959 |
Neg logit contributions | |
hetical | -2.350 |
sequ | -2.305 |
pneum | -2.219 |
helic | -2.130 |
stro | -2.118 |
Token | - |
Token ID | 12 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ariat | +0.540 |
rium | +0.521 |
Merit | +0.487 |
anity | +0.471 |
sup | +0.457 |
Neg logit contributions | |
hetical | -0.536 |
sequ | -0.525 |
pneum | -0.503 |
stro | -0.486 |
helic | -0.482 |
Token | Night |
Token ID | 24732 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ariat | +0.507 |
rium | +0.490 |
Merit | +0.451 |
anity | +0.442 |
sup | +0.429 |
Neg logit contributions | |
hetical | -0.531 |
sequ | -0.521 |
pneum | -0.500 |
stro | -0.483 |
helic | -0.479 |
Token | mares |
Token ID | 23745 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
hetical | +0.283 |
sequ | +0.278 |
pneum | +0.269 |
stro | +0.260 |
helic | +0.258 |
Neg logit contributions | |
ariat | -0.216 |
rium | -0.209 |
Merit | -0.194 |
anity | -0.186 |
sup | -0.181 |
Token | - |
Token ID | 12 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ariat | +0.877 |
rium | +0.847 |
Merit | +0.791 |
anity | +0.767 |
sup | +0.742 |
Neg logit contributions | |
hetical | -0.887 |
sequ | -0.870 |
pneum | -0.836 |
helic | -0.801 |
stro | -0.801 |
Token | are |
Token ID | 389 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
ariat | +0.223 |
rium | +0.216 |
Merit | +0.202 |
anity | +0.197 |
sup | +0.189 |
Neg logit contributions | |
hetical | -0.212 |
sequ | -0.209 |
pneum | -0.200 |
helic | -0.191 |
stro | -0.191 |
Token | in |
Token ID | 287 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
ariat | +0.300 |
rium | +0.292 |
Merit | +0.272 |
anity | +0.266 |
sup | +0.256 |
Neg logit contributions | |
hetical | -0.270 |
sequ | -0.265 |
pneum | -0.253 |
helic | -0.242 |
stro | -0.242 |
Token | the |
Token ID | 262 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ariat | +0.256 |
rium | +0.248 |
Merit | +0.231 |
anity | +0.225 |
sup | +0.217 |
Neg logit contributions | |
hetical | -0.264 |
sequ | -0.259 |
pneum | -0.248 |
helic | -0.239 |
stro | -0.238 |
Token | process |
Token ID | 1429 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
ariat | +0.283 |
rium | +0.276 |
Merit | +0.259 |
anity | +0.254 |
sup | +0.244 |
Neg logit contributions | |
hetical | -0.219 |
sequ | -0.215 |
pneum | -0.205 |
helic | -0.195 |
stro | -0.194 |
Token | of |
Token ID | 286 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
hetical | +0.572 |
sequ | +0.562 |
pneum | +0.535 |
stro | +0.511 |
helic | +0.509 |
Neg logit contributions | |
ariat | -0.625 |
rium | -0.605 |
Merit | -0.567 |
anity | -0.557 |
sup | -0.529 |
Token | reim |
Token ID | 21123 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
ariat | +0.410 |
rium | +0.398 |
Merit | +0.374 |
anity | +0.365 |
sup | +0.356 |
Neg logit contributions | |
hetical | -0.324 |
sequ | -0.316 |
pneum | -0.302 |
helic | -0.288 |
stro | -0.288 |
Token | plement |
Token ID | 26908 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
ariat | +1.914 |
rium | +1.826 |
Merit | +1.666 |
anity | +1.633 |
sup | +1.579 |
Neg logit contributions | |
hetical | -2.698 |
sequ | -2.654 |
pneum | -2.571 |
helic | -2.500 |
stro | -2.480 |
Token | ing |
Token ID | 278 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
ariat | +0.042 |
rium | +0.040 |
Merit | +0.038 |
anity | +0.036 |
sup | +0.035 |
Neg logit contributions | |
hetical | -0.044 |
sequ | -0.043 |
pneum | -0.042 |
helic | -0.040 |
stro | -0.040 |
Token | our |
Token ID | 674 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
ariat | +0.068 |
rium | +0.066 |
Merit | +0.062 |
anity | +0.061 |
sup | +0.059 |
Neg logit contributions | |
hetical | -0.058 |
sequ | -0.057 |
pneum | -0.054 |
helic | -0.052 |
stro | -0.052 |
Token | message |
Token ID | 3275 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ariat | +0.065 |
rium | +0.063 |
Merit | +0.059 |
anity | +0.058 |
sup | +0.056 |
Neg logit contributions | |
hetical | -0.057 |
sequ | -0.056 |
pneum | -0.054 |
helic | -0.051 |
stro | -0.051 |
Token | bus |
Token ID | 1323 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
hetical | +0.131 |
sequ | +0.130 |
pneum | +0.124 |
helic | +0.118 |
stro | +0.118 |
Neg logit contributions | |
ariat | -0.151 |
rium | -0.147 |
Merit | -0.138 |
anity | -0.134 |
sup | -0.129 |
Token | restaurants |
Token ID | 10808 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
ariat | +0.421 |
rium | +0.407 |
Merit | +0.379 |
anity | +0.368 |
sup | +0.354 |
Neg logit contributions | |
hetical | -0.448 |
sequ | -0.441 |
pneum | -0.425 |
helic | -0.408 |
stro | -0.407 |
Token | . |
Token ID | 13 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
ariat | +0.025 |
rium | +0.024 |
Merit | +0.023 |
anity | +0.022 |
sup | +0.021 |
Neg logit contributions | |
hetical | -0.026 |
sequ | -0.026 |
pneum | -0.025 |
stro | -0.024 |
helic | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ariat | +0.070 |
rium | +0.068 |
Merit | +0.063 |
anity | +0.062 |
sup | +0.060 |
Neg logit contributions | |
hetical | -0.070 |
sequ | -0.069 |
pneum | -0.066 |
stro | -0.063 |
helic | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ariat | +0.125 |
rium | +0.121 |
Merit | +0.112 |
anity | +0.109 |
sup | +0.105 |
Neg logit contributions | |
hetical | -0.138 |
sequ | -0.136 |
pneum | -0.130 |
stro | -0.126 |
helic | -0.124 |
Token | Me |
Token ID | 5308 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ariat | +0.106 |
rium | +0.102 |
Merit | +0.094 |
anity | +0.093 |
sup | +0.090 |
Neg logit contributions | |
hetical | -0.096 |
sequ | -0.094 |
pneum | -0.090 |
stro | -0.087 |
helic | -0.085 |
Token | ghan |
Token ID | 6064 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
ariat | +0.360 |
rium | +0.349 |
Merit | +0.324 |
anity | +0.315 |
sup | +0.306 |
Neg logit contributions | |
hetical | -0.371 |
sequ | -0.362 |
pneum | -0.348 |
stro | -0.335 |
helic | -0.334 |
Token | C |
Token ID | 327 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
ariat | +2.347 |
rium | +2.276 |
Merit | +2.124 |
anity | +2.074 |
sup | +2.012 |
Neg logit contributions | |
hetical | -2.206 |
sequ | -2.150 |
pneum | -2.073 |
helic | -1.993 |
stro | -1.972 |
Token | order |
Token ID | 2875 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
ariat | +0.474 |
rium | +0.458 |
Merit | +0.431 |
anity | +0.417 |
sup | +0.405 |
Neg logit contributions | |
hetical | -0.460 |
sequ | -0.448 |
pneum | -0.431 |
stro | -0.414 |
helic | -0.412 |
Token | o |
Token ID | 78 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
hetical | +0.563 |
sequ | +0.549 |
pneum | +0.529 |
stro | +0.510 |
helic | +0.509 |
Neg logit contributions | |
ariat | -0.487 |
rium | -0.472 |
Merit | -0.438 |
anity | -0.424 |
sup | -0.409 |
Token | , |
Token ID | 11 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
hetical | +0.075 |
sequ | +0.074 |
pneum | +0.071 |
stro | +0.068 |
helic | +0.068 |
Neg logit contributions | |
ariat | -0.066 |
rium | -0.064 |
Merit | -0.059 |
anity | -0.058 |
sup | -0.056 |
Token | who |
Token ID | 508 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
ariat | +0.026 |
rium | +0.025 |
Merit | +0.023 |
anity | +0.023 |
sup | +0.022 |
Neg logit contributions | |
hetical | -0.028 |
sequ | -0.027 |
pneum | -0.026 |
helic | -0.025 |
stro | -0.025 |
Token | is |
Token ID | 318 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
hetical | +0.173 |
sequ | +0.170 |
pneum | +0.162 |
stro | +0.156 |
helic | +0.156 |
Neg logit contributions | |
ariat | -0.172 |
rium | -0.167 |
Merit | -0.157 |
anity | -0.151 |
sup | -0.144 |
Token | apparently |
Token ID | 5729 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
hetical | +0.302 |
sequ | +0.297 |
pneum | +0.285 |
stro | +0.273 |
helic | +0.272 |
Neg logit contributions | |
ariat | -0.315 |
rium | -0.305 |
Merit | -0.285 |
anity | -0.275 |
sup | -0.266 |
Token | on |
Token ID | 319 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ariat | +0.637 |
rium | +0.616 |
Merit | +0.575 |
anity | +0.558 |
sup | +0.539 |
Neg logit contributions | |
hetical | -0.622 |
sequ | -0.611 |
pneum | -0.587 |
helic | -0.562 |
stro | -0.561 |
Token | the |
Token ID | 262 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
ariat | +0.085 |
rium | +0.081 |
Merit | +0.076 |
anity | +0.074 |
sup | +0.071 |
Neg logit contributions | |
hetical | -0.086 |
sequ | -0.085 |
pneum | -0.082 |
stro | -0.078 |
helic | -0.078 |
Token | w |
Token ID | 266 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ariat | +0.041 |
rium | +0.039 |
Merit | +0.036 |
anity | +0.035 |
sup | +0.034 |
Neg logit contributions | |
hetical | -0.041 |
sequ | -0.041 |
pneum | -0.039 |
helic | -0.037 |
stro | -0.037 |
Token | ane |
Token ID | 1531 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ariat | +0.184 |
rium | +0.175 |
Merit | +0.157 |
anity | +0.143 |
sup | +0.140 |
Neg logit contributions | |
hetical | -0.402 |
sequ | -0.395 |
pneum | -0.383 |
stro | -0.374 |
helic | -0.372 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ariat | +2.011 |
rium | +1.948 |
Merit | +1.800 |
anity | +1.747 |
sup | +1.698 |
Neg logit contributions | |
hetical | -2.494 |
sequ | -2.420 |
pneum | -2.359 |
helic | -2.267 |
stro | -2.257 |
Token | They |
Token ID | 1119 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ariat | +0.214 |
rium | +0.207 |
Merit | +0.193 |
anity | +0.188 |
sup | +0.181 |
Neg logit contributions | |
hetical | -0.214 |
sequ | -0.210 |
pneum | -0.202 |
helic | -0.193 |
stro | -0.193 |
Token | are |
Token ID | 389 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
hetical | +0.198 |
sequ | +0.194 |
pneum | +0.186 |
helic | +0.177 |
stro | +0.177 |
Neg logit contributions | |
ariat | -0.217 |
rium | -0.211 |
Merit | -0.198 |
anity | -0.192 |
sup | -0.184 |
Token | at |
Token ID | 379 |
Feature activation | +1.13e-03 |
Pos logit contributions | |
hetical | +0.035 |
sequ | +0.035 |
pneum | +0.033 |
stro | +0.032 |
helic | +0.032 |
Neg logit contributions | |
ariat | -0.039 |
rium | -0.038 |
Merit | -0.035 |
anity | -0.034 |
sup | -0.033 |
Token | their |
Token ID | 511 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
ariat | +0.001 |
rium | +0.001 |
Merit | +0.001 |
anity | +0.001 |
sup | +0.001 |
Neg logit contributions | |
hetical | -0.001 |
sequ | -0.001 |
pneum | -0.001 |
stro | -0.001 |
helic | -0.001 |
Token | treacher |
Token ID | 32550 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ariat | +0.091 |
rium | +0.088 |
Merit | +0.082 |
anity | +0.079 |
sup | +0.076 |
Neg logit contributions | |
hetical | -0.095 |
sequ | -0.094 |
pneum | -0.091 |
helic | -0.086 |
stro | -0.086 |
Token | y |
Token ID | 88 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
ariat | +0.937 |
rium | +0.904 |
Merit | +0.830 |
anity | +0.806 |
sup | +0.773 |
Neg logit contributions | |
hetical | -1.259 |
sequ | -1.237 |
pneum | -1.198 |
helic | -1.158 |
stro | -1.149 |
Token | : |
Token ID | 25 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
hetical | +0.045 |
sequ | +0.045 |
pneum | +0.043 |
helic | +0.041 |
stro | +0.041 |
Neg logit contributions | |
ariat | -0.040 |
rium | -0.038 |
Merit | -0.035 |
anity | -0.034 |
sup | -0.033 |
Token | When |
Token ID | 1649 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ariat | +0.182 |
rium | +0.175 |
Merit | +0.163 |
anity | +0.158 |
sup | +0.151 |
Neg logit contributions | |
hetical | -0.198 |
sequ | -0.195 |
pneum | -0.187 |
stro | -0.178 |
helic | -0.178 |
Token | the |
Token ID | 262 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
ariat | +0.899 |
rium | +0.870 |
Merit | +0.810 |
anity | +0.789 |
sup | +0.763 |
Neg logit contributions | |
hetical | -0.919 |
sequ | -0.900 |
pneum | -0.867 |
helic | -0.832 |
stro | -0.830 |
Token | Lord |
Token ID | 4453 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ariat | +0.416 |
rium | +0.405 |
Merit | +0.382 |
anity | +0.374 |
sup | +0.360 |
Neg logit contributions | |
hetical | -0.295 |
sequ | -0.290 |
pneum | -0.277 |
helic | -0.261 |
stro | -0.259 |
Token | thy |
Token ID | 11906 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ariat | +2.345 |
rium | +2.265 |
Merit | +2.127 |
anity | +2.066 |
sup | +2.027 |
Neg logit contributions | |
hetical | -2.166 |
sequ | -2.107 |
pneum | -2.031 |
helic | -1.956 |
stro | -1.947 |
Token | God |
Token ID | 1793 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ariat | +0.727 |
rium | +0.697 |
Merit | +0.633 |
anity | +0.625 |
sup | +0.584 |
Neg logit contributions | |
hetical | -1.036 |
sequ | -1.020 |
pneum | -0.984 |
helic | -0.949 |
stro | -0.947 |
Token | hath |
Token ID | 22027 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ariat | +0.992 |
rium | +0.963 |
Merit | +0.898 |
anity | +0.877 |
sup | +0.842 |
Neg logit contributions | |
hetical | -0.923 |
sequ | -0.908 |
pneum | -0.868 |
helic | -0.830 |
stro | -0.828 |
Token | delivered |
Token ID | 6793 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ariat | +1.023 |
rium | +0.991 |
Merit | +0.926 |
anity | +0.904 |
sup | +0.871 |
Neg logit contributions | |
hetical | -0.942 |
sequ | -0.925 |
pneum | -0.887 |
helic | -0.848 |
stro | -0.845 |
Token | it |
Token ID | 340 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ariat | +0.154 |
rium | +0.148 |
Merit | +0.138 |
anity | +0.134 |
sup | +0.130 |
Neg logit contributions | |
hetical | -0.158 |
sequ | -0.155 |
pneum | -0.149 |
helic | -0.143 |
stro | -0.143 |
Token | snow |
Token ID | 6729 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ariat | +0.043 |
rium | +0.041 |
Merit | +0.039 |
anity | +0.038 |
sup | +0.037 |
Neg logit contributions | |
hetical | -0.035 |
sequ | -0.035 |
pneum | -0.033 |
helic | -0.032 |
stro | -0.032 |
Token | le |
Token ID | 443 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
hetical | +0.270 |
sequ | +0.262 |
pneum | +0.251 |
helic | +0.239 |
stro | +0.239 |
Neg logit contributions | |
ariat | -0.351 |
rium | -0.341 |
Merit | -0.320 |
anity | -0.314 |
sup | -0.305 |
Token | opard |
Token ID | 15478 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
hetical | +0.037 |
sequ | +0.036 |
pneum | +0.034 |
helic | +0.033 |
stro | +0.032 |
Neg logit contributions | |
ariat | -0.053 |
rium | -0.051 |
Merit | -0.048 |
anity | -0.047 |
sup | -0.046 |
Token | 's |
Token ID | 338 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
hetical | +0.828 |
sequ | +0.816 |
pneum | +0.781 |
helic | +0.746 |
stro | +0.743 |
Neg logit contributions | |
ariat | -0.909 |
rium | -0.883 |
Merit | -0.828 |
anity | -0.804 |
sup | -0.774 |
Token | ch |
Token ID | 442 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
hetical | +0.345 |
sequ | +0.339 |
pneum | +0.325 |
helic | +0.309 |
stro | +0.309 |
Neg logit contributions | |
ariat | -0.404 |
rium | -0.392 |
Merit | -0.368 |
anity | -0.359 |
sup | -0.346 |
Token | uff |
Token ID | 1648 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
hetical | +0.389 |
sequ | +0.380 |
pneum | +0.364 |
stro | +0.349 |
helic | +0.347 |
Neg logit contributions | |
ariat | -0.416 |
rium | -0.403 |
Merit | -0.380 |
anity | -0.368 |
sup | -0.358 |
Token | ing |
Token ID | 278 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
ariat | +2.195 |
rium | +2.125 |
Merit | +1.962 |
anity | +1.928 |
sup | +1.863 |
Neg logit contributions | |
hetical | -2.294 |
sequ | -2.233 |
pneum | -2.150 |
helic | -2.079 |
actionDate | -2.059 |
Token | and |
Token ID | 290 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
hetical | +0.622 |
sequ | +0.614 |
pneum | +0.591 |
stro | +0.565 |
helic | +0.564 |
Neg logit contributions | |
ariat | -0.617 |
rium | -0.596 |
Merit | -0.557 |
anity | -0.542 |
sup | -0.521 |
Token | w |
Token ID | 266 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ariat | +0.056 |
rium | +0.054 |
Merit | +0.051 |
anity | +0.050 |
sup | +0.048 |
Neg logit contributions | |
hetical | -0.052 |
sequ | -0.051 |
pneum | -0.049 |
helic | -0.047 |
stro | -0.047 |
Token | ailing |
Token ID | 11608 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ariat | +0.245 |
rium | +0.238 |
Merit | +0.224 |
anity | +0.219 |
sup | +0.213 |
Neg logit contributions | |
hetical | -0.171 |
sequ | -0.167 |
pneum | -0.159 |
helic | -0.151 |
stro | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ariat | +1.689 |
rium | +1.633 |
Merit | +1.517 |
anity | +1.485 |
sup | +1.448 |
Neg logit contributions | |
hetical | -1.631 |
sequ | -1.582 |
pneum | -1.523 |
helic | -1.466 |
stro | -1.461 |
Token | business |
Token ID | 1597 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ariat | +0.166 |
rium | +0.161 |
Merit | +0.150 |
anity | +0.146 |
sup | +0.140 |
Neg logit contributions | |
hetical | -0.172 |
sequ | -0.169 |
pneum | -0.163 |
helic | -0.156 |
stro | -0.156 |
Token | of |
Token ID | 286 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
hetical | +0.227 |
sequ | +0.222 |
pneum | +0.213 |
helic | +0.205 |
stro | +0.204 |
Neg logit contributions | |
ariat | -0.231 |
rium | -0.223 |
Merit | -0.208 |
anity | -0.203 |
sup | -0.196 |
Token | ignoring |
Token ID | 15482 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
ariat | +0.156 |
rium | +0.151 |
Merit | +0.140 |
anity | +0.136 |
sup | +0.131 |
Neg logit contributions | |
hetical | -0.156 |
sequ | -0.154 |
pneum | -0.148 |
helic | -0.141 |
stro | -0.141 |
Token | what |
Token ID | 644 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ariat | +0.454 |
rium | +0.440 |
Merit | +0.410 |
anity | +0.399 |
sup | +0.386 |
Neg logit contributions | |
hetical | -0.441 |
sequ | -0.433 |
pneum | -0.417 |
helic | -0.398 |
stro | -0.397 |
Token | The |
Token ID | 383 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ariat | +0.095 |
rium | +0.092 |
Merit | +0.086 |
anity | +0.084 |
sup | +0.080 |
Neg logit contributions | |
hetical | -0.098 |
sequ | -0.096 |
pneum | -0.093 |
helic | -0.089 |
stro | -0.088 |
Token | Lord |
Token ID | 4453 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
ariat | +0.246 |
rium | +0.237 |
Merit | +0.220 |
anity | +0.215 |
sup | +0.207 |
Neg logit contributions | |
hetical | -0.271 |
sequ | -0.265 |
pneum | -0.256 |
helic | -0.246 |
stro | -0.245 |
Token | commands |
Token ID | 9729 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
ariat | +1.980 |
rium | +1.892 |
Merit | +1.755 |
anity | +1.702 |
sup | +1.662 |
Neg logit contributions | |
hetical | -2.458 |
sequ | -2.406 |
pneum | -2.330 |
helic | -2.253 |
stro | -2.239 |
Token | of |
Token ID | 286 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
ariat | +0.305 |
rium | +0.295 |
Merit | +0.272 |
anity | +0.265 |
sup | +0.254 |
Neg logit contributions | |
hetical | -0.363 |
sequ | -0.358 |
pneum | -0.347 |
stro | -0.331 |
helic | -0.331 |
Token | me |
Token ID | 502 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ariat | +0.258 |
rium | +0.248 |
Merit | +0.231 |
anity | +0.224 |
sup | +0.216 |
Neg logit contributions | |
hetical | -0.280 |
sequ | -0.275 |
pneum | -0.266 |
helic | -0.254 |
stro | -0.254 |
Token | , |
Token ID | 11 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ariat | +0.161 |
rium | +0.155 |
Merit | +0.144 |
anity | +0.140 |
sup | +0.135 |
Neg logit contributions | |
hetical | -0.172 |
sequ | -0.170 |
pneum | -0.163 |
helic | -0.157 |
stro | -0.157 |
Token | especially |
Token ID | 2592 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
ariat | +0.111 |
rium | +0.107 |
Merit | +0.099 |
anity | +0.095 |
sup | +0.091 |
Neg logit contributions | |
hetical | -0.133 |
sequ | -0.131 |
pneum | -0.126 |
helic | -0.121 |
stro | -0.121 |
Token | bonuses |
Token ID | 17568 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ariat | +0.505 |
rium | +0.487 |
Merit | +0.449 |
anity | +0.437 |
sup | +0.419 |
Neg logit contributions | |
hetical | -0.598 |
sequ | -0.590 |
pneum | -0.567 |
helic | -0.545 |
stro | -0.545 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ariat | +0.776 |
rium | +0.749 |
Merit | +0.694 |
anity | +0.674 |
sup | +0.650 |
Neg logit contributions | |
hetical | -0.877 |
sequ | -0.863 |
pneum | -0.831 |
helic | -0.798 |
stro | -0.797 |
Token |
|
Token ID | 198 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ariat | +0.122 |
rium | +0.118 |
Merit | +0.109 |
anity | +0.107 |
sup | +0.103 |
Neg logit contributions | |
hetical | -0.127 |
sequ | -0.124 |
pneum | -0.119 |
stro | -0.115 |
helic | -0.114 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
hetical | +0.111 |
sequ | +0.110 |
pneum | +0.105 |
stro | +0.101 |
helic | +0.100 |
Neg logit contributions | |
ariat | -0.103 |
rium | -0.099 |
Merit | -0.092 |
anity | -0.090 |
sup | -0.086 |
Token | Ch |
Token ID | 1925 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
hetical | +0.147 |
sequ | +0.143 |
pneum | +0.137 |
stro | +0.132 |
helic | +0.129 |
Neg logit contributions | |
ariat | -0.177 |
rium | -0.171 |
Merit | -0.158 |
anity | -0.156 |
sup | -0.152 |
Token | asta |
Token ID | 40197 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ariat | +0.106 |
rium | +0.102 |
Merit | +0.097 |
anity | +0.092 |
sup | +0.090 |
Neg logit contributions | |
hetical | -0.115 |
sequ | -0.113 |
pneum | -0.108 |
stro | -0.105 |
helic | -0.103 |
Token | Un |
Token ID | 791 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ariat | +2.202 |
rium | +2.136 |
Merit | +2.009 |
anity | +1.952 |
sup | +1.888 |
Neg logit contributions | |
hetical | -2.140 |
sequ | -2.087 |
pneum | -2.013 |
helic | -1.928 |
stro | -1.917 |
Token | win |
Token ID | 5404 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
ariat | +0.795 |
rium | +0.768 |
Merit | +0.712 |
anity | +0.692 |
sup | +0.667 |
Neg logit contributions | |
hetical | -0.905 |
sequ | -0.888 |
pneum | -0.855 |
helic | -0.822 |
stro | -0.822 |
Token | said |
Token ID | 531 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
ariat | +0.498 |
rium | +0.479 |
Merit | +0.444 |
anity | +0.431 |
sup | +0.415 |
Neg logit contributions | |
hetical | -0.592 |
sequ | -0.582 |
pneum | -0.561 |
helic | -0.540 |
stro | -0.539 |
Token | she |
Token ID | 673 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
hetical | +0.052 |
sequ | +0.050 |
pneum | +0.048 |
helic | +0.046 |
stro | +0.046 |
Neg logit contributions | |
ariat | -0.063 |
rium | -0.062 |
Merit | -0.058 |
anity | -0.056 |
sup | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
ariat | +0.332 |
rium | +0.321 |
Merit | +0.299 |
anity | +0.291 |
sup | +0.280 |
Neg logit contributions | |
hetical | -0.336 |
sequ | -0.330 |
pneum | -0.317 |
helic | -0.304 |
stro | -0.303 |
Token | I |
Token ID | 314 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
hetical | +0.138 |
sequ | +0.135 |
pneum | +0.130 |
helic | +0.125 |
stro | +0.125 |
Neg logit contributions | |
ariat | -0.143 |
rium | -0.138 |
Merit | -0.129 |
anity | -0.126 |
sup | -0.122 |
Token | started |
Token ID | 2067 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
ariat | +0.058 |
rium | +0.057 |
Merit | +0.053 |
anity | +0.052 |
sup | +0.051 |
Neg logit contributions | |
hetical | -0.051 |
sequ | -0.049 |
pneum | -0.047 |
helic | -0.045 |
stro | -0.045 |
Token | thinking |
Token ID | 3612 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
ariat | +0.071 |
rium | +0.069 |
Merit | +0.065 |
anity | +0.063 |
sup | +0.062 |
Neg logit contributions | |
hetical | -0.057 |
sequ | -0.055 |
pneum | -0.053 |
helic | -0.051 |
stro | -0.050 |
Token | about |
Token ID | 546 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
hetical | +0.054 |
sequ | +0.053 |
pneum | +0.051 |
helic | +0.049 |
stro | +0.049 |
Neg logit contributions | |
ariat | -0.048 |
rium | -0.047 |
Merit | -0.043 |
anity | -0.042 |
sup | -0.041 |
Token | W |
Token ID | 370 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
hetical | +0.107 |
sequ | +0.105 |
pneum | +0.101 |
helic | +0.097 |
stro | +0.096 |
Neg logit contributions | |
ariat | -0.113 |
rium | -0.109 |
Merit | -0.102 |
anity | -0.100 |
sup | -0.096 |
Token | ile |
Token ID | 576 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
hetical | +0.138 |
sequ | +0.135 |
pneum | +0.130 |
stro | +0.125 |
helic | +0.124 |
Neg logit contributions | |
ariat | -0.132 |
rium | -0.127 |
Merit | -0.119 |
anity | -0.115 |
sup | -0.112 |
Token | E |
Token ID | 412 |
Feature activation | +8.88e-02 |
Pos logit contributions | |
ariat | +2.111 |
rium | +2.075 |
Merit | +1.950 |
anity | +1.884 |
sup | +1.838 |
Neg logit contributions | |
hetical | -2.232 |
sequ | -2.164 |
pneum | -2.102 |
helic | -2.008 |
actionDate | -1.996 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ariat | +0.061 |
rium | +0.059 |
Merit | +0.054 |
anity | +0.052 |
sup | +0.051 |
Neg logit contributions | |
hetical | -0.072 |
sequ | -0.071 |
pneum | -0.068 |
stro | -0.066 |
helic | -0.066 |
Token | Coy |
Token ID | 26887 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
hetical | +0.064 |
sequ | +0.061 |
pneum | +0.058 |
helic | +0.056 |
stro | +0.055 |
Neg logit contributions | |
ariat | -0.107 |
rium | -0.105 |
Merit | -0.100 |
anity | -0.097 |
sup | -0.095 |
Token | ote |
Token ID | 1258 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
hetical | +0.012 |
sequ | +0.011 |
pneum | +0.011 |
helic | +0.010 |
stro | +0.010 |
Neg logit contributions | |
ariat | -0.014 |
rium | -0.013 |
Merit | -0.013 |
anity | -0.012 |
sup | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ariat | +0.230 |
rium | +0.222 |
Merit | +0.206 |
anity | +0.201 |
sup | +0.194 |
Neg logit contributions | |
hetical | -0.255 |
sequ | -0.250 |
pneum | -0.241 |
helic | -0.232 |
stro | -0.231 |
Token | , |
Token ID | 11 |
Feature activation | -9.59e-02 |
Pos logit contributions | |
hetical | +1.142 |
sequ | +1.124 |
pneum | +1.079 |
helic | +1.033 |
stro | +1.032 |
Neg logit contributions | |
ariat | -1.061 |
rium | -1.029 |
Merit | -0.950 |
anity | -0.925 |
sup | -0.892 |
Token | and |
Token ID | 290 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
hetical | +0.071 |
sequ | +0.069 |
pneum | +0.067 |
helic | +0.064 |
stro | +0.064 |
Neg logit contributions | |
ariat | -0.073 |
rium | -0.071 |
Merit | -0.066 |
anity | -0.064 |
sup | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
ariat | +0.028 |
rium | +0.027 |
Merit | +0.026 |
anity | +0.025 |
sup | +0.024 |
Neg logit contributions | |
hetical | -0.029 |
sequ | -0.028 |
pneum | -0.027 |
helic | -0.026 |
stro | -0.026 |
Token | only |
Token ID | 691 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
hetical | +0.044 |
sequ | +0.044 |
pneum | +0.042 |
helic | +0.040 |
stro | +0.040 |
Neg logit contributions | |
ariat | -0.042 |
rium | -0.041 |
Merit | -0.038 |
anity | -0.037 |
sup | -0.036 |
Token | w |
Token ID | 266 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
hetical | +0.259 |
sequ | +0.253 |
pneum | +0.243 |
helic | +0.232 |
stro | +0.232 |
Neg logit contributions | |
ariat | -0.297 |
rium | -0.287 |
Merit | -0.269 |
anity | -0.263 |
sup | -0.255 |
Token | isp |
Token ID | 8802 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
ariat | +0.334 |
rium | +0.324 |
Merit | +0.304 |
anity | +0.298 |
sup | +0.288 |
Neg logit contributions | |
hetical | -0.265 |
sequ | -0.260 |
pneum | -0.249 |
helic | -0.238 |
stro | -0.236 |
Token | of |
Token ID | 286 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
ariat | +1.802 |
rium | +1.735 |
Merit | +1.585 |
anity | +1.549 |
sup | +1.486 |
Neg logit contributions | |
hetical | -2.495 |
sequ | -2.450 |
pneum | -2.371 |
helic | -2.302 |
actionDate | -2.301 |
Token | political |
Token ID | 1964 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
ariat | +0.073 |
rium | +0.070 |
Merit | +0.066 |
anity | +0.064 |
sup | +0.062 |
Neg logit contributions | |
hetical | -0.067 |
sequ | -0.066 |
pneum | -0.063 |
helic | -0.060 |
stro | -0.060 |
Token | activity |
Token ID | 3842 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
ariat | +0.501 |
rium | +0.485 |
Merit | +0.454 |
anity | +0.442 |
sup | +0.428 |
Neg logit contributions | |
hetical | -0.462 |
sequ | -0.452 |
pneum | -0.434 |
helic | -0.416 |
stro | -0.415 |
Token | in |
Token ID | 287 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ariat | +0.734 |
rium | +0.713 |
Merit | +0.669 |
anity | +0.654 |
sup | +0.634 |
Neg logit contributions | |
hetical | -0.586 |
sequ | -0.573 |
pneum | -0.548 |
helic | -0.523 |
stro | -0.521 |
Token | her |
Token ID | 607 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
ariat | +0.123 |
rium | +0.119 |
Merit | +0.111 |
anity | +0.107 |
sup | +0.104 |
Neg logit contributions | |
hetical | -0.120 |
sequ | -0.119 |
pneum | -0.113 |
helic | -0.108 |
stro | -0.108 |
Token | Charlie |
Token ID | 11526 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
hetical | +0.011 |
sequ | +0.010 |
pneum | +0.010 |
helic | +0.010 |
stro | +0.009 |
Neg logit contributions | |
ariat | -0.011 |
rium | -0.011 |
Merit | -0.010 |
anity | -0.010 |
sup | -0.009 |
Token | Cameron |
Token ID | 10821 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ariat | +0.010 |
rium | +0.009 |
Merit | +0.009 |
anity | +0.009 |
sup | +0.008 |
Neg logit contributions | |
hetical | -0.009 |
sequ | -0.009 |
pneum | -0.008 |
stro | -0.008 |
helic | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
ariat | +0.930 |
rium | +0.898 |
Merit | +0.834 |
anity | +0.810 |
sup | +0.782 |
Neg logit contributions | |
hetical | -1.016 |
sequ | -0.997 |
pneum | -0.961 |
helic | -0.923 |
stro | -0.921 |
Token | Harrison |
Token ID | 17281 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
ariat | +0.017 |
rium | +0.016 |
Merit | +0.015 |
anity | +0.014 |
sup | +0.014 |
Neg logit contributions | |
hetical | -0.018 |
sequ | -0.018 |
pneum | -0.017 |
helic | -0.016 |
stro | -0.016 |
Token | W |
Token ID | 370 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
ariat | +0.374 |
rium | +0.363 |
Merit | +0.338 |
anity | +0.327 |
sup | +0.316 |
Neg logit contributions | |
hetical | -0.355 |
sequ | -0.349 |
pneum | -0.336 |
helic | -0.321 |
stro | -0.319 |
Token | igg |
Token ID | 6950 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
ariat | +0.071 |
rium | +0.068 |
Merit | +0.064 |
anity | +0.062 |
sup | +0.060 |
Neg logit contributions | |
hetical | -0.067 |
sequ | -0.066 |
pneum | -0.063 |
stro | -0.060 |
helic | -0.060 |
Token | moving |
Token ID | 3867 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ariat | +1.994 |
rium | +1.933 |
Merit | +1.784 |
anity | +1.743 |
sup | +1.675 |
Neg logit contributions | |
hetical | -2.325 |
sequ | -2.263 |
pneum | -2.183 |
helic | -2.110 |
stro | -2.100 |
Token | elsewhere |
Token ID | 8057 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
sequ | +0.200 |
hetical | +0.200 |
pneum | +0.191 |
helic | +0.182 |
stro | +0.181 |
Neg logit contributions | |
ariat | -0.210 |
rium | -0.203 |
Merit | -0.191 |
anity | -0.186 |
sup | -0.176 |
Token | . |
Token ID | 13 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
ariat | +1.389 |
rium | +1.341 |
Merit | +1.244 |
anity | +1.210 |
sup | +1.167 |
Neg logit contributions | |
hetical | -1.566 |
sequ | -1.535 |
pneum | -1.481 |
helic | -1.424 |
stro | -1.420 |
Token |
|
Token ID | 198 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
ariat | +0.491 |
rium | +0.473 |
Merit | +0.440 |
anity | +0.426 |
sup | +0.411 |
Neg logit contributions | |
hetical | -0.557 |
sequ | -0.546 |
pneum | -0.526 |
helic | -0.506 |
stro | -0.505 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ariat | +0.293 |
rium | +0.282 |
Merit | +0.262 |
anity | +0.255 |
sup | +0.244 |
Neg logit contributions | |
hetical | -0.327 |
sequ | -0.321 |
pneum | -0.308 |
stro | -0.297 |
helic | -0.294 |
Token | Vs |
Token ID | 31280 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
ariat | +1.230 |
rium | +1.191 |
Merit | +1.111 |
anity | +1.084 |
sup | +1.048 |
Neg logit contributions | |
hetical | -1.191 |
sequ | -1.167 |
pneum | -1.122 |
helic | -1.075 |
stro | -1.072 |
Token | Colin |
Token ID | 18373 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
hetical | +0.025 |
sequ | +0.025 |
pneum | +0.024 |
stro | +0.023 |
helic | +0.023 |
Neg logit contributions | |
ariat | -0.024 |
rium | -0.023 |
Merit | -0.022 |
anity | -0.021 |
sup | -0.020 |
Token | - |
Token ID | 12 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
ariat | +0.650 |
rium | +0.632 |
Merit | +0.591 |
anity | +0.572 |
sup | +0.557 |
Neg logit contributions | |
hetical | -0.626 |
sequ | -0.613 |
pneum | -0.586 |
stro | -0.559 |
helic | -0.558 |
Token | Ant |
Token ID | 13217 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ariat | +0.308 |
rium | +0.298 |
Merit | +0.275 |
anity | +0.269 |
sup | +0.261 |
Neg logit contributions | |
hetical | -0.320 |
sequ | -0.314 |
pneum | -0.301 |
stro | -0.291 |
helic | -0.288 |
Token | W |
Token ID | 370 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ariat | +0.823 |
rium | +0.794 |
Merit | +0.736 |
anity | +0.714 |
sup | +0.689 |
Neg logit contributions | |
hetical | -0.952 |
sequ | -0.933 |
pneum | -0.900 |
helic | -0.866 |
stro | -0.865 |
Token | ears |
Token ID | 4127 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ariat | +0.172 |
rium | +0.165 |
Merit | +0.152 |
anity | +0.144 |
sup | +0.141 |
Neg logit contributions | |
hetical | -0.261 |
sequ | -0.255 |
pneum | -0.246 |
stro | -0.239 |
helic | -0.237 |
Token | Pant |
Token ID | 11427 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
ariat | +2.171 |
rium | +2.093 |
Merit | +1.943 |
anity | +1.920 |
sup | +1.859 |
Neg logit contributions | |
hetical | -2.111 |
sequ | -2.050 |
pneum | -1.983 |
helic | -1.918 |
stro | -1.894 |
Token | ies |
Token ID | 444 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
hetical | +0.459 |
sequ | +0.450 |
pneum | +0.431 |
stro | +0.416 |
helic | +0.412 |
Neg logit contributions | |
ariat | -0.361 |
rium | -0.346 |
Merit | -0.323 |
anity | -0.308 |
sup | -0.300 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
hetical | +0.488 |
sequ | +0.480 |
pneum | +0.460 |
stro | +0.442 |
helic | +0.440 |
Neg logit contributions | |
ariat | -0.491 |
rium | -0.472 |
Merit | -0.444 |
anity | -0.429 |
sup | -0.415 |
Token | 01 |
Token ID | 486 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
ariat | +0.258 |
rium | +0.247 |
Merit | +0.226 |
anity | +0.219 |
sup | +0.209 |
Neg logit contributions | |
hetical | -0.368 |
sequ | -0.363 |
pneum | -0.349 |
stro | -0.338 |
helic | -0.337 |
Token | 18 |
Token ID | 1507 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
hetical | +0.310 |
sequ | +0.304 |
pneum | +0.294 |
stro | +0.285 |
helic | +0.283 |
Neg logit contributions | |
ariat | -0.208 |
rium | -0.200 |
Merit | -0.179 |
anity | -0.176 |
sup | -0.169 |
Token | business |
Token ID | 1597 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ariat | +0.241 |
rium | +0.234 |
Merit | +0.219 |
anity | +0.214 |
sup | +0.206 |
Neg logit contributions | |
hetical | -0.214 |
sequ | -0.210 |
pneum | -0.201 |
helic | -0.192 |
stro | -0.192 |
Token | of |
Token ID | 286 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
hetical | +0.244 |
sequ | +0.239 |
pneum | +0.229 |
stro | +0.219 |
helic | +0.219 |
Neg logit contributions | |
ariat | -0.250 |
rium | -0.243 |
Merit | -0.227 |
anity | -0.221 |
sup | -0.213 |
Token | ignoring |
Token ID | 15482 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
ariat | +0.199 |
rium | +0.193 |
Merit | +0.180 |
anity | +0.175 |
sup | +0.169 |
Neg logit contributions | |
hetical | -0.188 |
sequ | -0.184 |
pneum | -0.177 |
helic | -0.170 |
stro | -0.169 |
Token | what |
Token ID | 644 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
ariat | +0.424 |
rium | +0.411 |
Merit | +0.380 |
anity | +0.368 |
sup | +0.354 |
Neg logit contributions | |
hetical | -0.486 |
sequ | -0.479 |
pneum | -0.462 |
helic | -0.444 |
stro | -0.442 |
Token | The |
Token ID | 383 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
ariat | +0.254 |
rium | +0.245 |
Merit | +0.228 |
anity | +0.222 |
sup | +0.213 |
Neg logit contributions | |
hetical | -0.281 |
sequ | -0.276 |
pneum | -0.266 |
helic | -0.256 |
stro | -0.256 |
Token | Lord |
Token ID | 4453 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
ariat | +0.305 |
rium | +0.295 |
Merit | +0.275 |
anity | +0.267 |
sup | +0.260 |
Neg logit contributions | |
hetical | -0.289 |
sequ | -0.283 |
pneum | -0.271 |
stro | -0.261 |
helic | -0.259 |
Token | has |
Token ID | 468 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
ariat | +2.120 |
rium | +2.039 |
Merit | +1.908 |
anity | +1.856 |
sup | +1.814 |
Neg logit contributions | |
hetical | -2.174 |
sequ | -2.123 |
pneum | -2.044 |
helic | -1.966 |
stro | -1.954 |
Token | commanded |
Token ID | 22419 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ariat | +0.436 |
rium | +0.423 |
Merit | +0.397 |
anity | +0.387 |
sup | +0.375 |
Neg logit contributions | |
hetical | -0.369 |
sequ | -0.361 |
pneum | -0.346 |
helic | -0.330 |
stro | -0.329 |
Token | me |
Token ID | 502 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ariat | +0.693 |
rium | +0.669 |
Merit | +0.617 |
anity | +0.600 |
sup | +0.575 |
Neg logit contributions | |
hetical | -0.843 |
sequ | -0.830 |
pneum | -0.803 |
stro | -0.770 |
helic | -0.769 |
Token | to |
Token ID | 284 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
ariat | +0.229 |
rium | +0.222 |
Merit | +0.207 |
anity | +0.202 |
sup | +0.194 |
Neg logit contributions | |
hetical | -0.226 |
sequ | -0.222 |
pneum | -0.214 |
helic | -0.204 |
stro | -0.204 |
Token | do |
Token ID | 466 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
ariat | +0.442 |
rium | +0.428 |
Merit | +0.398 |
anity | +0.387 |
sup | +0.373 |
Neg logit contributions | |
hetical | -0.461 |
sequ | -0.453 |
pneum | -0.436 |
helic | -0.418 |
stro | -0.417 |
Token | - |
Token ID | 12 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ariat | +0.261 |
rium | +0.252 |
Merit | +0.234 |
anity | +0.230 |
sup | +0.221 |
Neg logit contributions | |
hetical | -0.251 |
sequ | -0.246 |
pneum | -0.235 |
stro | -0.226 |
helic | -0.225 |
Token | 08 |
Token ID | 2919 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ariat | +0.130 |
rium | +0.125 |
Merit | +0.114 |
anity | +0.112 |
sup | +0.109 |
Neg logit contributions | |
hetical | -0.154 |
sequ | -0.151 |
pneum | -0.145 |
stro | -0.141 |
helic | -0.139 |
Token | Election |
Token ID | 14219 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ariat | +0.110 |
rium | +0.107 |
Merit | +0.101 |
anity | +0.098 |
sup | +0.096 |
Neg logit contributions | |
hetical | -0.086 |
sequ | -0.083 |
pneum | -0.080 |
helic | -0.076 |
stro | -0.076 |
Token | - |
Token ID | 12 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ariat | +0.842 |
rium | +0.813 |
Merit | +0.759 |
anity | +0.740 |
sup | +0.715 |
Neg logit contributions | |
hetical | -0.825 |
sequ | -0.809 |
pneum | -0.776 |
helic | -0.743 |
stro | -0.743 |
Token | V |
Token ID | 53 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ariat | +0.090 |
rium | +0.086 |
Merit | +0.080 |
anity | +0.078 |
sup | +0.076 |
Neg logit contributions | |
hetical | -0.094 |
sequ | -0.092 |
pneum | -0.088 |
stro | -0.085 |
helic | -0.084 |
Token | ince |
Token ID | 924 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ariat | +0.848 |
rium | +0.822 |
Merit | +0.765 |
anity | +0.734 |
sup | +0.720 |
Neg logit contributions | |
hetical | -0.892 |
sequ | -0.871 |
pneum | -0.837 |
stro | -0.807 |
helic | -0.805 |
Token | Mc |
Token ID | 1982 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ariat | +2.194 |
rium | +2.121 |
Merit | +1.974 |
anity | +1.952 |
sup | +1.872 |
Neg logit contributions | |
hetical | -2.053 |
sequ | -2.001 |
pneum | -1.929 |
helic | -1.866 |
stro | -1.843 |
Token | Man |
Token ID | 5124 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ariat | +1.015 |
rium | +0.980 |
Merit | +0.918 |
anity | +0.894 |
sup | +0.868 |
Neg logit contributions | |
hetical | -0.944 |
sequ | -0.928 |
pneum | -0.888 |
helic | -0.853 |
stro | -0.851 |
Token | - |
Token ID | 12 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
hetical | +0.315 |
sequ | +0.310 |
pneum | +0.301 |
stro | +0.293 |
helic | +0.292 |
Neg logit contributions | |
ariat | -0.145 |
rium | -0.138 |
Merit | -0.125 |
anity | -0.117 |
sup | -0.111 |
Token | Tw |
Token ID | 5080 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
ariat | +0.375 |
rium | +0.362 |
Merit | +0.333 |
anity | +0.326 |
sup | +0.317 |
Neg logit contributions | |
hetical | -0.396 |
sequ | -0.389 |
pneum | -0.373 |
stro | -0.361 |
helic | -0.357 |
Token | ister |
Token ID | 1694 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ariat | +1.304 |
rium | +1.262 |
Merit | +1.177 |
anity | +1.144 |
sup | +1.108 |
Neg logit contributions | |
hetical | -1.318 |
sequ | -1.290 |
pneum | -1.241 |
helic | -1.190 |
stro | -1.188 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
hetical | +1.328 |
sequ | +1.327 |
pneum | +1.262 |
stro | +1.217 |
helic | +1.211 |
Neg logit contributions | |
ariat | -1.190 |
rium | -1.147 |
Merit | -1.069 |
anity | -1.039 |
sup | -0.984 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ariat | +0.013 |
rium | +0.013 |
Merit | +0.012 |
anity | +0.012 |
sup | +0.011 |
Neg logit contributions | |
hetical | -0.013 |
sequ | -0.013 |
pneum | -0.012 |
stro | -0.012 |
helic | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
hetical | +0.113 |
sequ | +0.111 |
pneum | +0.106 |
stro | +0.102 |
actionDate | +0.101 |
Neg logit contributions | |
ariat | -0.103 |
rium | -0.100 |
Merit | -0.091 |
anity | -0.090 |
sup | -0.086 |
Token | W |
Token ID | 54 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
hetical | +0.160 |
sequ | +0.156 |
pneum | +0.149 |
stro | +0.144 |
helic | +0.142 |
Neg logit contributions | |
ariat | -0.185 |
rium | -0.179 |
Merit | -0.167 |
anity | -0.164 |
sup | -0.159 |
Token | MD |
Token ID | 12740 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ariat | +0.259 |
rium | +0.250 |
Merit | +0.233 |
anity | +0.226 |
sup | +0.219 |
Neg logit contributions | |
hetical | -0.275 |
sequ | -0.269 |
pneum | -0.259 |
stro | -0.249 |
helic | -0.248 |
Token | ream |
Token ID | 1476 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ariat | +1.150 |
rium | +1.109 |
Merit | +1.035 |
anity | +1.002 |
sup | +0.963 |
Neg logit contributions | |
hetical | -1.241 |
sequ | -1.225 |
pneum | -1.175 |
helic | -1.131 |
stro | -1.129 |
Token | Remote |
Token ID | 36510 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
ariat | +2.073 |
rium | +2.005 |
Merit | +1.862 |
anity | +1.814 |
sup | +1.758 |
Neg logit contributions | |
hetical | -2.175 |
sequ | -2.126 |
pneum | -2.052 |
helic | -1.969 |
stro | -1.962 |
Token | is |
Token ID | 318 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
hetical | +0.698 |
sequ | +0.695 |
pneum | +0.664 |
stro | +0.639 |
helic | +0.637 |
Neg logit contributions | |
ariat | -0.659 |
rium | -0.639 |
Merit | -0.594 |
anity | -0.577 |
sup | -0.546 |
Token | bound |
Token ID | 5421 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
hetical | +0.159 |
sequ | +0.157 |
pneum | +0.151 |
helic | +0.144 |
stro | +0.144 |
Neg logit contributions | |
ariat | -0.163 |
rium | -0.157 |
Merit | -0.148 |
anity | -0.143 |
sup | -0.137 |
Token | to |
Token ID | 284 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ariat | +0.209 |
rium | +0.202 |
Merit | +0.189 |
anity | +0.184 |
sup | +0.178 |
Neg logit contributions | |
hetical | -0.210 |
sequ | -0.206 |
pneum | -0.198 |
helic | -0.190 |
stro | -0.190 |
Token | make |
Token ID | 787 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
hetical | +0.009 |
sequ | +0.009 |
pneum | +0.008 |
helic | +0.008 |
stro | +0.008 |
Neg logit contributions | |
ariat | -0.009 |
rium | -0.009 |
Merit | -0.009 |
anity | -0.008 |
sup | -0.008 |
Token | against |
Token ID | 1028 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
ariat | +0.163 |
rium | +0.158 |
Merit | +0.147 |
anity | +0.144 |
sup | +0.138 |
Neg logit contributions | |
hetical | -0.150 |
sequ | -0.148 |
pneum | -0.141 |
helic | -0.135 |
stro | -0.135 |
Token | BJP |
Token ID | 18317 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
hetical | +0.562 |
sequ | +0.558 |
pneum | +0.534 |
helic | +0.513 |
stro | +0.507 |
Neg logit contributions | |
ariat | -0.570 |
rium | -0.555 |
Merit | -0.518 |
anity | -0.509 |
sup | -0.479 |
Token | MLA |
Token ID | 43265 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
ariat | +0.218 |
rium | +0.212 |
Merit | +0.198 |
anity | +0.194 |
sup | +0.187 |
Neg logit contributions | |
hetical | -0.190 |
sequ | -0.186 |
pneum | -0.178 |
helic | -0.170 |
stro | -0.170 |
Token | Narendra |
Token ID | 28113 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
hetical | +0.201 |
sequ | +0.198 |
pneum | +0.190 |
stro | +0.182 |
helic | +0.182 |
Neg logit contributions | |
ariat | -0.194 |
rium | -0.188 |
Merit | -0.174 |
anity | -0.170 |
sup | -0.163 |
Token | Me |
Token ID | 2185 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ariat | +0.450 |
rium | +0.434 |
Merit | +0.403 |
anity | +0.393 |
sup | +0.377 |
Neg logit contributions | |
hetical | -0.490 |
sequ | -0.481 |
pneum | -0.463 |
stro | -0.445 |
helic | -0.443 |
Token | ht |
Token ID | 4352 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
hetical | +0.271 |
sequ | +0.259 |
pneum | +0.249 |
stro | +0.246 |
helic | +0.238 |
Neg logit contributions | |
ariat | -0.253 |
rium | -0.248 |
Merit | -0.233 |
anity | -0.223 |
sup | -0.218 |
Token | a |
Token ID | 64 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ariat | +1.461 |
rium | +1.392 |
Merit | +1.251 |
anity | +1.203 |
sup | +1.141 |
Neg logit contributions | |
hetical | -2.782 |
sequ | -2.739 |
pneum | -2.661 |
helic | -2.579 |
stro | -2.572 |
Token | � |
Token ID | 447 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
ariat | +0.746 |
rium | +0.722 |
Merit | +0.671 |
anity | +0.653 |
sup | +0.629 |
Neg logit contributions | |
hetical | -0.775 |
sequ | -0.762 |
pneum | -0.728 |
stro | -0.699 |
helic | -0.699 |
Token | � |
Token ID | 247 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
ariat | +0.334 |
rium | +0.324 |
anity | +0.300 |
Merit | +0.299 |
sup | +0.286 |
Neg logit contributions | |
hetical | -0.313 |
sequ | -0.306 |
pneum | -0.294 |
stro | -0.281 |
helic | -0.279 |
Token | s |
Token ID | 82 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ariat | +0.272 |
rium | +0.262 |
Merit | +0.244 |
anity | +0.239 |
sup | +0.229 |
Neg logit contributions | |
hetical | -0.281 |
sequ | -0.276 |
pneum | -0.264 |
stro | -0.255 |
helic | -0.252 |
Token | younger |
Token ID | 7099 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ariat | +0.201 |
rium | +0.196 |
Merit | +0.183 |
anity | +0.179 |
sup | +0.171 |
Neg logit contributions | |
hetical | -0.178 |
sequ | -0.174 |
pneum | -0.167 |
helic | -0.160 |
stro | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
hetical | +0.133 |
sequ | +0.133 |
pneum | +0.126 |
stro | +0.121 |
helic | +0.121 |
Neg logit contributions | |
ariat | -0.137 |
rium | -0.134 |
Merit | -0.125 |
anity | -0.122 |
sup | -0.116 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ariat | +0.125 |
rium | +0.121 |
Merit | +0.112 |
anity | +0.109 |
sup | +0.105 |
Neg logit contributions | |
hetical | -0.137 |
sequ | -0.134 |
pneum | -0.129 |
stro | -0.124 |
helic | -0.124 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ariat | +0.171 |
rium | +0.165 |
Merit | +0.152 |
anity | +0.149 |
sup | +0.143 |
Neg logit contributions | |
hetical | -0.185 |
sequ | -0.182 |
pneum | -0.174 |
stro | -0.168 |
helic | -0.165 |
Token | ' |
Token ID | 6 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ariat | +0.115 |
rium | +0.112 |
Merit | +0.103 |
anity | +0.102 |
sup | +0.099 |
Neg logit contributions | |
hetical | -0.104 |
sequ | -0.102 |
pneum | -0.097 |
stro | -0.094 |
──── | -0.091 |
Token | Now |
Token ID | 3844 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
ariat | +0.126 |
rium | +0.122 |
Merit | +0.112 |
anity | +0.110 |
sup | +0.107 |
Neg logit contributions | |
hetical | -0.126 |
sequ | -0.124 |
pneum | -0.119 |
stro | -0.115 |
helic | -0.113 |
Token | here |
Token ID | 1456 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
hetical | +0.319 |
sequ | +0.315 |
pneum | +0.303 |
stro | +0.290 |
helic | +0.289 |
Neg logit contributions | |
ariat | -0.319 |
rium | -0.308 |
Merit | -0.289 |
anity | -0.279 |
sup | -0.267 |
Token | is |
Token ID | 318 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ariat | +2.081 |
rium | +2.005 |
Merit | +1.879 |
anity | +1.822 |
sup | +1.778 |
Neg logit contributions | |
hetical | -2.147 |
sequ | -2.097 |
pneum | -2.032 |
helic | -1.948 |
stro | -1.942 |
Token | safe |
Token ID | 3338 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ariat | +0.207 |
rium | +0.201 |
Merit | +0.186 |
anity | +0.181 |
sup | +0.173 |
Neg logit contributions | |
hetical | -0.224 |
sequ | -0.221 |
pneum | -0.212 |
helic | -0.204 |
stro | -0.202 |
Token | ' |
Token ID | 6 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
hetical | +0.132 |
sequ | +0.130 |
pneum | +0.124 |
stro | +0.117 |
helic | +0.117 |
Neg logit contributions | |
ariat | -0.169 |
rium | -0.163 |
Merit | -0.154 |
anity | -0.151 |
sup | -0.145 |
Token |
|
Token ID | 198 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ariat | +0.248 |
rium | +0.239 |
Merit | +0.222 |
anity | +0.217 |
sup | +0.207 |
Neg logit contributions | |
hetical | -0.279 |
sequ | -0.275 |
pneum | -0.265 |
helic | -0.254 |
stro | -0.253 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ariat | +0.212 |
rium | +0.204 |
Merit | +0.189 |
anity | +0.185 |
sup | +0.177 |
Neg logit contributions | |
hetical | -0.232 |
sequ | -0.229 |
pneum | -0.219 |
stro | -0.211 |
helic | -0.208 |
Token | extremely |
Token ID | 4457 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
ariat | +0.225 |
rium | +0.218 |
Merit | +0.204 |
anity | +0.199 |
sup | +0.192 |
Neg logit contributions | |
hetical | -0.197 |
sequ | -0.194 |
pneum | -0.186 |
helic | -0.177 |
stro | -0.177 |
Token | rewarding |
Token ID | 23404 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ariat | +0.504 |
rium | +0.489 |
Merit | +0.460 |
anity | +0.449 |
sup | +0.437 |
Neg logit contributions | |
hetical | -0.397 |
sequ | -0.387 |
pneum | -0.370 |
helic | -0.353 |
stro | -0.352 |
Token | ," |
Token ID | 553 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
hetical | +0.266 |
sequ | +0.262 |
pneum | +0.251 |
helic | +0.240 |
stro | +0.240 |
Neg logit contributions | |
ariat | -0.275 |
rium | -0.266 |
Merit | -0.248 |
anity | -0.241 |
sup | -0.233 |
Token | says |
Token ID | 1139 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
hetical | +0.202 |
sequ | +0.199 |
pneum | +0.190 |
helic | +0.182 |
stro | +0.181 |
Neg logit contributions | |
ariat | -0.223 |
rium | -0.216 |
Merit | -0.202 |
anity | -0.197 |
sup | -0.190 |
Token | W |
Token ID | 370 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
hetical | +0.086 |
sequ | +0.085 |
pneum | +0.082 |
helic | +0.078 |
stro | +0.078 |
Neg logit contributions | |
ariat | -0.086 |
rium | -0.084 |
Merit | -0.078 |
anity | -0.076 |
sup | -0.073 |
Token | ats |
Token ID | 1381 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ariat | +0.113 |
rium | +0.109 |
Merit | +0.099 |
anity | +0.096 |
sup | +0.092 |
Neg logit contributions | |
hetical | -0.175 |
sequ | -0.172 |
pneum | -0.166 |
stro | -0.161 |
helic | -0.160 |
Token | ham |
Token ID | 2763 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ariat | +2.463 |
rium | +2.406 |
Merit | +2.245 |
anity | +2.219 |
sup | +2.148 |
Neg logit contributions | |
hetical | -1.729 |
sequ | -1.695 |
pneum | -1.653 |
conduc | -1.634 |
helic | -1.594 |
Token | . |
Token ID | 13 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
ariat | +0.659 |
rium | +0.634 |
Merit | +0.585 |
anity | +0.569 |
sup | +0.546 |
Neg logit contributions | |
hetical | -0.854 |
sequ | -0.837 |
pneum | -0.811 |
helic | -0.781 |
stro | -0.779 |
Token | His |
Token ID | 2399 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
ariat | +0.635 |
rium | +0.613 |
Merit | +0.570 |
anity | +0.555 |
sup | +0.535 |
Neg logit contributions | |
hetical | -0.693 |
sequ | -0.679 |
pneum | -0.656 |
helic | -0.631 |
stro | -0.627 |
Token | approach |
Token ID | 3164 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ariat | +0.367 |
rium | +0.356 |
Merit | +0.335 |
anity | +0.327 |
sup | +0.318 |
Neg logit contributions | |
hetical | -0.290 |
sequ | -0.283 |
pneum | -0.271 |
helic | -0.259 |
stro | -0.257 |
Token | to |
Token ID | 284 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ariat | +0.836 |
rium | +0.810 |
Merit | +0.753 |
anity | +0.733 |
sup | +0.704 |
Neg logit contributions | |
hetical | -0.886 |
sequ | -0.870 |
pneum | -0.835 |
stro | -0.802 |
helic | -0.801 |
Token | explains |
Token ID | 6688 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ariat | +0.090 |
rium | +0.088 |
Merit | +0.082 |
anity | +0.080 |
sup | +0.077 |
Neg logit contributions | |
hetical | -0.082 |
sequ | -0.080 |
pneum | -0.077 |
helic | -0.074 |
stro | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
hetical | +1.269 |
sequ | +1.258 |
pneum | +1.208 |
stro | +1.162 |
helic | +1.158 |
Neg logit contributions | |
ariat | -1.061 |
rium | -1.025 |
Merit | -0.946 |
anity | -0.914 |
sup | -0.877 |
Token |
|
Token ID | 198 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ariat | +0.230 |
rium | +0.221 |
Merit | +0.206 |
anity | +0.201 |
sup | +0.193 |
Neg logit contributions | |
hetical | -0.237 |
sequ | -0.233 |
pneum | -0.224 |
stro | -0.215 |
helic | -0.214 |
Token |
|
Token ID | 198 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
hetical | +0.218 |
sequ | +0.215 |
pneum | +0.205 |
stro | +0.198 |
helic | +0.195 |
Neg logit contributions | |
ariat | -0.200 |
rium | -0.193 |
Merit | -0.179 |
anity | -0.175 |
sup | -0.167 |
Token | Setting |
Token ID | 34149 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
hetical | +0.209 |
sequ | +0.204 |
pneum | +0.195 |
stro | +0.187 |
helic | +0.185 |
Neg logit contributions | |
ariat | -0.253 |
rium | -0.244 |
Merit | -0.228 |
anity | -0.224 |
sup | -0.217 |
Token | aside |
Token ID | 7263 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
hetical | +0.239 |
sequ | +0.235 |
pneum | +0.226 |
helic | +0.217 |
stro | +0.216 |
Neg logit contributions | |
ariat | -0.214 |
rium | -0.207 |
Merit | -0.192 |
anity | -0.187 |
sup | -0.179 |
Token | the |
Token ID | 262 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
ariat | +1.937 |
rium | +1.890 |
Merit | +1.735 |
anity | +1.700 |
sup | +1.654 |
Neg logit contributions | |
hetical | -2.268 |
sequ | -2.207 |
pneum | -2.134 |
stro | -2.067 |
helic | -2.058 |
Token | drama |
Token ID | 10512 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ariat | +0.073 |
rium | +0.071 |
Merit | +0.066 |
anity | +0.065 |
sup | +0.063 |
Neg logit contributions | |
hetical | -0.065 |
sequ | -0.063 |
pneum | -0.061 |
helic | -0.058 |
stro | -0.058 |
Token | of |
Token ID | 286 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
hetical | +0.950 |
sequ | +0.937 |
pneum | +0.899 |
helic | +0.858 |
stro | +0.857 |
Neg logit contributions | |
ariat | -0.914 |
rium | -0.881 |
Merit | -0.821 |
anity | -0.802 |
sup | -0.767 |
Token | tsun |
Token ID | 28798 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
hetical | +0.037 |
sequ | +0.036 |
pneum | +0.035 |
helic | +0.034 |
stro | +0.034 |
Neg logit contributions | |
ariat | -0.035 |
rium | -0.034 |
Merit | -0.032 |
anity | -0.031 |
sup | -0.030 |
Token | am |
Token ID | 321 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ariat | +0.342 |
rium | +0.330 |
Merit | +0.312 |
anity | +0.303 |
sup | +0.293 |
Neg logit contributions | |
hetical | -0.273 |
sequ | -0.268 |
pneum | -0.257 |
stro | -0.245 |
helic | -0.243 |
Token | iff |
Token ID | 733 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
hetical | +0.502 |
sequ | +0.485 |
pneum | +0.459 |
stro | +0.440 |
helic | +0.435 |
Neg logit contributions | |
ariat | -0.695 |
rium | -0.680 |
Merit | -0.639 |
anity | -0.620 |
sup | -0.610 |
Token | Tra |
Token ID | 15721 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ariat | +0.455 |
rium | +0.442 |
Merit | +0.418 |
anity | +0.409 |
sup | +0.398 |
Neg logit contributions | |
hetical | -0.297 |
sequ | -0.289 |
pneum | -0.275 |
stro | -0.260 |
helic | -0.260 |
Token | x |
Token ID | 87 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
hetical | +0.192 |
sequ | +0.188 |
pneum | +0.181 |
stro | +0.176 |
helic | +0.172 |
Neg logit contributions | |
ariat | -0.145 |
rium | -0.139 |
Merit | -0.128 |
anity | -0.123 |
sup | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
hetical | +0.853 |
sequ | +0.835 |
pneum | +0.806 |
helic | +0.774 |
stro | +0.772 |
Neg logit contributions | |
ariat | -0.776 |
rium | -0.751 |
Merit | -0.695 |
anity | -0.675 |
sup | -0.652 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
hetical | +0.083 |
sequ | +0.081 |
pneum | +0.078 |
stro | +0.075 |
helic | +0.074 |
Neg logit contributions | |
ariat | -0.077 |
rium | -0.074 |
Merit | -0.068 |
anity | -0.067 |
sup | -0.064 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
hetical | +0.086 |
sequ | +0.084 |
pneum | +0.079 |
stro | +0.077 |
helic | +0.075 |
Neg logit contributions | |
ariat | -0.133 |
rium | -0.129 |
Merit | -0.121 |
anity | -0.119 |
sup | -0.116 |
Token | : |
Token ID | 25 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
sequ | +2.888 |
hetical | +2.883 |
pneum | +2.646 |
stro | +2.592 |
──── | +2.513 |
Neg logit contributions | |
ariat | -3.830 |
rium | -3.706 |
Merit | -3.447 |
merce | -3.443 |
anity | -3.407 |
Token | V |
Token ID | 569 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
ariat | +0.554 |
rium | +0.536 |
Merit | +0.500 |
anity | +0.487 |
sup | +0.469 |
Neg logit contributions | |
hetical | -0.542 |
sequ | -0.532 |
pneum | -0.512 |
helic | -0.491 |
stro | -0.489 |
Token | the |
Token ID | 1169 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ariat | +0.539 |
rium | +0.521 |
Merit | +0.486 |
anity | +0.468 |
sup | +0.455 |
Neg logit contributions | |
hetical | -0.590 |
sequ | -0.577 |
pneum | -0.556 |
stro | -0.536 |
helic | -0.534 |
Token | Happy |
Token ID | 25082 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ariat | +0.193 |
rium | +0.185 |
Merit | +0.173 |
anity | +0.168 |
sup | +0.163 |
Neg logit contributions | |
hetical | -0.207 |
sequ | -0.203 |
pneum | -0.195 |
stro | -0.189 |
helic | -0.187 |
Token | L |
Token ID | 43 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
hetical | +1.382 |
sequ | +1.373 |
pneum | +1.314 |
stro | +1.285 |
helic | +1.263 |
Neg logit contributions | |
ariat | -1.186 |
rium | -1.139 |
Merit | -1.051 |
anity | -1.025 |
sup | -0.988 |
Token | / |
Token ID | 14 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
ariat | +0.660 |
rium | +0.641 |
Merit | +0.603 |
anity | +0.589 |
sup | +0.571 |
Neg logit contributions | |
hetical | -0.551 |
sequ | -0.539 |
pneum | -0.517 |
helic | -0.495 |
stro | -0.492 |
Token | File |
Token ID | 8979 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
hetical | +0.643 |
sequ | +0.631 |
pneum | +0.604 |
stro | +0.581 |
helic | +0.578 |
Neg logit contributions | |
ariat | -0.726 |
rium | -0.704 |
Merit | -0.657 |
anity | -0.642 |
sup | -0.622 |
Token | photo |
Token ID | 4590 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
hetical | +0.166 |
sequ | +0.162 |
pneum | +0.156 |
stro | +0.151 |
helic | +0.150 |
Neg logit contributions | |
ariat | -0.169 |
rium | -0.163 |
Merit | -0.152 |
anity | -0.148 |
sup | -0.143 |
Token | TP |
Token ID | 24525 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
hetical | +0.847 |
sequ | +0.827 |
pneum | +0.789 |
stro | +0.752 |
helic | +0.751 |
Neg logit contributions | |
ariat | -1.134 |
rium | -1.103 |
Merit | -1.038 |
anity | -1.014 |
sup | -0.983 |
Token | X |
Token ID | 55 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
hetical | +0.126 |
sequ | +0.123 |
pneum | +0.118 |
helic | +0.113 |
stro | +0.113 |
Neg logit contributions | |
ariat | -0.136 |
rium | -0.132 |
Merit | -0.123 |
anity | -0.120 |
sup | -0.116 |
Token | IMAGES |
Token ID | 45325 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
hetical | +0.662 |
sequ | +0.657 |
pneum | +0.634 |
helic | +0.612 |
stro | +0.604 |
Neg logit contributions | |
ariat | -0.778 |
rium | -0.763 |
Merit | -0.724 |
anity | -0.700 |
merce | -0.674 |
Token | OF |
Token ID | 3963 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
hetical | +2.913 |
sequ | +2.808 |
pneum | +2.645 |
stro | +2.564 |
Tolkien | +2.500 |
Neg logit contributions | |
ariat | -3.546 |
rium | -3.517 |
Merit | -3.390 |
anity | -3.282 |
merce | -3.275 |
Token | THE |
Token ID | 3336 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
hetical | +1.394 |
sequ | +1.363 |
pneum | +1.308 |
helic | +1.248 |
stro | +1.246 |
Neg logit contributions | |
ariat | -1.621 |
rium | -1.573 |
Merit | -1.470 |
anity | -1.437 |
sup | -1.395 |
Token | DAY |
Token ID | 24644 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
hetical | +0.525 |
sequ | +0.516 |
pneum | +0.489 |
helic | +0.467 |
stro | +0.459 |
Neg logit contributions | |
ariat | -0.731 |
rium | -0.713 |
Merit | -0.668 |
anity | -0.657 |
sup | -0.634 |
Token | ) |
Token ID | 8 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
hetical | +0.345 |
sequ | +0.338 |
pneum | +0.325 |
helic | +0.311 |
stro | +0.310 |
Neg logit contributions | |
ariat | -0.363 |
rium | -0.352 |
Merit | -0.327 |
anity | -0.320 |
sup | -0.308 |
Token | Chris |
Token ID | 5180 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
hetical | +0.879 |
sequ | +0.862 |
pneum | +0.830 |
stro | +0.793 |
helic | +0.791 |
Neg logit contributions | |
ariat | -0.724 |
rium | -0.699 |
Merit | -0.638 |
anity | -0.628 |
sup | -0.594 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
hetical | +0.440 |
sequ | +0.439 |
pneum | +0.424 |
stro | +0.400 |
helic | +0.398 |
Neg logit contributions | |
ariat | -0.371 |
rium | -0.355 |
Merit | -0.324 |
anity | -0.316 |
merce | -0.307 |
Token | boys |
Token ID | 13202 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
hetical | +0.326 |
sequ | +0.323 |
stro | +0.311 |
pneum | +0.308 |
helic | +0.299 |
Neg logit contributions | |
ariat | -0.132 |
rium | -0.121 |
Merit | -0.104 |
anity | -0.100 |
sup | -0.097 |
Token | beware |
Token ID | 40600 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
ariat | +0.158 |
rium | +0.151 |
Merit | +0.139 |
anity | +0.133 |
sup | +0.129 |
Neg logit contributions | |
hetical | -0.195 |
sequ | -0.190 |
pneum | -0.185 |
helic | -0.176 |
stro | -0.176 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
hetical | +0.647 |
sequ | +0.639 |
pneum | +0.615 |
helic | +0.588 |
stro | +0.588 |
Neg logit contributions | |
ariat | -0.598 |
rium | -0.577 |
Merit | -0.534 |
anity | -0.518 |
sup | -0.500 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ariat | +0.152 |
rium | +0.147 |
Merit | +0.136 |
anity | +0.133 |
sup | +0.127 |
Neg logit contributions | |
hetical | -0.163 |
sequ | -0.161 |
pneum | -0.154 |
stro | -0.149 |
helic | -0.146 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
ariat | +0.182 |
rium | +0.176 |
Merit | +0.165 |
anity | +0.162 |
sup | +0.159 |
Neg logit contributions | |
hetical | -0.117 |
sequ | -0.113 |
pneum | -0.107 |
stro | -0.104 |
helic | -0.101 |
Token | : |
Token ID | 25 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
sequ | +2.729 |
hetical | +2.726 |
pneum | +2.506 |
stro | +2.458 |
──── | +2.375 |
Neg logit contributions | |
ariat | -3.575 |
rium | -3.457 |
Merit | -3.217 |
merce | -3.201 |
anity | -3.175 |
Token | j |
Token ID | 474 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ariat | +0.837 |
rium | +0.811 |
Merit | +0.757 |
anity | +0.737 |
sup | +0.712 |
Neg logit contributions | |
hetical | -0.814 |
sequ | -0.798 |
pneum | -0.767 |
helic | -0.735 |
stro | -0.733 |
Token | wt |
Token ID | 46569 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
hetical | +0.423 |
sequ | +0.416 |
pneum | +0.400 |
stro | +0.389 |
helic | +0.383 |
Neg logit contributions | |
ariat | -0.382 |
rium | -0.369 |
Merit | -0.346 |
anity | -0.331 |
sup | -0.323 |
Token | 0001 |
Token ID | 18005 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ariat | +0.312 |
rium | +0.300 |
Merit | +0.279 |
anity | +0.269 |
sup | +0.259 |
Neg logit contributions | |
hetical | -0.380 |
sequ | -0.373 |
pneum | -0.360 |
stro | -0.348 |
helic | -0.346 |
Token | - |
Token ID | 532 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ariat | +0.141 |
rium | +0.133 |
Merit | +0.119 |
anity | +0.113 |
sup | +0.107 |
Neg logit contributions | |
hetical | -0.301 |
sequ | -0.297 |
pneum | -0.289 |
helic | -0.281 |
stro | -0.280 |
Token | , |
Token ID | 11 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ariat | +0.195 |
rium | +0.189 |
Merit | +0.170 |
anity | +0.168 |
sup | +0.161 |
Neg logit contributions | |
hetical | -0.229 |
sequ | -0.226 |
pneum | -0.217 |
stro | -0.210 |
helic | -0.208 |
Token | I |
Token ID | 314 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
hetical | +0.353 |
sequ | +0.347 |
pneum | +0.335 |
helic | +0.321 |
stro | +0.319 |
Neg logit contributions | |
ariat | -0.331 |
rium | -0.321 |
Merit | -0.297 |
anity | -0.289 |
sup | -0.278 |
Token | think |
Token ID | 892 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
ariat | +0.099 |
rium | +0.096 |
Merit | +0.090 |
anity | +0.088 |
sup | +0.085 |
Neg logit contributions | |
hetical | -0.088 |
sequ | -0.087 |
pneum | -0.083 |
stro | -0.079 |
helic | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
hetical | +0.009 |
sequ | +0.009 |
pneum | +0.009 |
helic | +0.008 |
stro | +0.008 |
Neg logit contributions | |
ariat | -0.008 |
rium | -0.008 |
Merit | -0.007 |
anity | -0.007 |
sup | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
ariat | +0.039 |
rium | +0.037 |
Merit | +0.035 |
anity | +0.034 |
sup | +0.032 |
Neg logit contributions | |
hetical | -0.041 |
sequ | -0.041 |
pneum | -0.039 |
stro | -0.037 |
helic | -0.037 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
hetical | +0.021 |
sequ | +0.020 |
pneum | +0.019 |
stro | +0.019 |
helic | +0.018 |
Neg logit contributions | |
ariat | -0.034 |
rium | -0.033 |
Merit | -0.030 |
anity | -0.030 |
sup | -0.029 |
Token | : |
Token ID | 25 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
hetical | +2.670 |
sequ | +2.666 |
pneum | +2.455 |
stro | +2.399 |
──── | +2.329 |
Neg logit contributions | |
ariat | -3.476 |
rium | -3.367 |
Merit | -3.123 |
merce | -3.116 |
anity | -3.091 |
Token | B |
Token ID | 347 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ariat | +0.583 |
rium | +0.565 |
Merit | +0.527 |
anity | +0.513 |
sup | +0.494 |
Neg logit contributions | |
hetical | -0.575 |
sequ | -0.565 |
pneum | -0.543 |
helic | -0.521 |
stro | -0.519 |
Token | iz |
Token ID | 528 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
ariat | +0.448 |
rium | +0.433 |
Merit | +0.404 |
anity | +0.392 |
sup | +0.379 |
Neg logit contributions | |
hetical | -0.467 |
sequ | -0.458 |
pneum | -0.440 |
helic | -0.423 |
stro | -0.422 |
Token | r |
Token ID | 81 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
hetical | +0.783 |
sequ | +0.767 |
pneum | +0.740 |
stro | +0.714 |
helic | +0.707 |
Neg logit contributions | |
ariat | -0.689 |
rium | -0.659 |
Merit | -0.616 |
anity | -0.594 |
sup | -0.579 |
Token | Pix |
Token ID | 21642 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
hetical | +0.464 |
sequ | +0.454 |
pneum | +0.437 |
stro | +0.423 |
helic | +0.420 |
Neg logit contributions | |
ariat | -0.400 |
rium | -0.386 |
Merit | -0.358 |
anity | -0.347 |
sup | -0.336 |
Token | was |
Token ID | 373 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
hetical | +0.147 |
sequ | +0.144 |
pneum | +0.138 |
stro | +0.132 |
helic | +0.132 |
Neg logit contributions | |
ariat | -0.156 |
rium | -0.151 |
Merit | -0.142 |
anity | -0.137 |
sup | -0.132 |
Token | about |
Token ID | 546 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
ariat | +0.455 |
rium | +0.440 |
Merit | +0.411 |
anity | +0.399 |
sup | +0.386 |
Neg logit contributions | |
hetical | -0.439 |
sequ | -0.432 |
pneum | -0.415 |
helic | -0.397 |
stro | -0.396 |
Token | homosexuality |
Token ID | 19822 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
hetical | +0.272 |
sequ | +0.269 |
pneum | +0.259 |
helic | +0.248 |
stro | +0.246 |
Neg logit contributions | |
ariat | -0.268 |
rium | -0.259 |
Merit | -0.241 |
anity | -0.235 |
sup | -0.225 |
Token |
|
Token ID | 198 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
ariat | +0.123 |
rium | +0.119 |
Merit | +0.111 |
anity | +0.106 |
sup | +0.103 |
Neg logit contributions | |
hetical | -0.133 |
sequ | -0.132 |
pneum | -0.127 |
helic | -0.122 |
stro | -0.121 |
Token |
|
Token ID | 198 |
Feature activation | -6.30e-03 |
Pos logit contributions | |
ariat | +0.044 |
rium | +0.042 |
Merit | +0.039 |
anity | +0.038 |
sup | +0.037 |
Neg logit contributions | |
hetical | -0.048 |
sequ | -0.047 |
pneum | -0.045 |
stro | -0.043 |
helic | -0.043 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
hetical | +0.005 |
sequ | +0.005 |
pneum | +0.004 |
stro | +0.004 |
helic | +0.004 |
Neg logit contributions | |
ariat | -0.005 |
rium | -0.005 |
Merit | -0.004 |
anity | -0.004 |
sup | -0.004 |
Token | : |
Token ID | 25 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
hetical | +2.732 |
sequ | +2.722 |
pneum | +2.540 |
stro | +2.426 |
helic | +2.416 |
Neg logit contributions | |
ariat | -3.302 |
rium | -3.193 |
Merit | -2.963 |
anity | -2.907 |
merce | -2.796 |
Token | k |
Token ID | 479 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
ariat | +0.702 |
rium | +0.680 |
Merit | +0.635 |
anity | +0.618 |
sup | +0.597 |
Neg logit contributions | |
hetical | -0.681 |
sequ | -0.668 |
pneum | -0.642 |
helic | -0.616 |
stro | -0.614 |
Token | imp |
Token ID | 11011 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
ariat | +0.403 |
rium | +0.389 |
Merit | +0.363 |
anity | +0.351 |
sup | +0.340 |
Neg logit contributions | |
hetical | -0.443 |
sequ | -0.434 |
pneum | -0.417 |
stro | -0.402 |
helic | -0.401 |
Token | unk |
Token ID | 2954 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ariat | +0.541 |
rium | +0.522 |
Merit | +0.485 |
anity | +0.468 |
sup | +0.452 |
Neg logit contributions | |
hetical | -0.639 |
sequ | -0.628 |
pneum | -0.604 |
stro | -0.584 |
helic | -0.582 |
Token | rock |
Token ID | 10823 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
hetical | +0.219 |
sequ | +0.217 |
pneum | +0.209 |
stro | +0.204 |
helic | +0.203 |
Neg logit contributions | |
ariat | -0.138 |
rium | -0.133 |
Merit | -0.122 |
anity | -0.116 |
sup | -0.111 |
Token | bad |
Token ID | 2089 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
ariat | +0.068 |
rium | +0.067 |
Merit | +0.063 |
anity | +0.062 |
sup | +0.060 |
Neg logit contributions | |
hetical | -0.040 |
sequ | -0.040 |
pneum | -0.037 |
stro | -0.035 |
helic | -0.035 |
Token | idea |
Token ID | 2126 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ariat | +0.257 |
rium | +0.251 |
Merit | +0.239 |
anity | +0.235 |
sup | +0.230 |
Neg logit contributions | |
hetical | -0.112 |
sequ | -0.108 |
pneum | -0.102 |
helic | -0.095 |
stro | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
hetical | +0.011 |
sequ | +0.011 |
pneum | +0.010 |
stro | +0.010 |
helic | +0.010 |
Neg logit contributions | |
ariat | -0.009 |
rium | -0.009 |
Merit | -0.008 |
anity | -0.008 |
sup | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
ariat | +0.199 |
rium | +0.193 |
Merit | +0.179 |
anity | +0.174 |
sup | +0.168 |
Neg logit contributions | |
hetical | -0.201 |
sequ | -0.197 |
pneum | -0.190 |
helic | -0.182 |
stro | -0.181 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ariat | +0.211 |
rium | +0.204 |
Merit | +0.188 |
anity | +0.184 |
sup | +0.176 |
Neg logit contributions | |
hetical | -0.228 |
sequ | -0.224 |
pneum | -0.215 |
stro | -0.208 |
helic | -0.204 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
ariat | +0.118 |
rium | +0.115 |
Merit | +0.107 |
anity | +0.106 |
sup | +0.104 |
Neg logit contributions | |
hetical | -0.076 |
sequ | -0.073 |
pneum | -0.069 |
stro | -0.067 |
helic | -0.065 |
Token | : |
Token ID | 25 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
sequ | +2.590 |
hetical | +2.588 |
pneum | +2.388 |
stro | +2.324 |
──── | +2.250 |
Neg logit contributions | |
ariat | -3.325 |
rium | -3.219 |
Merit | -2.993 |
merce | -2.957 |
anity | -2.957 |
Token | Mike |
Token ID | 4995 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
ariat | +0.662 |
rium | +0.641 |
Merit | +0.598 |
anity | +0.582 |
sup | +0.562 |
Neg logit contributions | |
hetical | -0.653 |
sequ | -0.641 |
pneum | -0.616 |
helic | -0.591 |
stro | -0.589 |
Token | M |
Token ID | 44 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
ariat | +0.642 |
rium | +0.620 |
Merit | +0.577 |
anity | +0.561 |
sup | +0.542 |
Neg logit contributions | |
hetical | -0.691 |
sequ | -0.677 |
pneum | -0.652 |
helic | -0.627 |
stro | -0.625 |
Token | anners |
Token ID | 15672 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
hetical | +0.753 |
sequ | +0.740 |
pneum | +0.720 |
stro | +0.699 |
helic | +0.699 |
Neg logit contributions | |
ariat | -0.371 |
rium | -0.354 |
Merit | -0.315 |
anity | -0.298 |
sup | -0.288 |
Token | - |
Token ID | 532 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
hetical | +0.761 |
sequ | +0.751 |
pneum | +0.728 |
stro | +0.706 |
helic | +0.706 |
Neg logit contributions | |
ariat | -0.429 |
rium | -0.410 |
Merit | -0.367 |
anity | -0.352 |
sup | -0.337 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ariat | +0.036 |
rium | +0.035 |
Merit | +0.032 |
anity | +0.031 |
sup | +0.030 |
Neg logit contributions | |
hetical | -0.035 |
sequ | -0.035 |
pneum | -0.033 |
stro | -0.032 |
helic | -0.032 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
hetical | +0.857 |
sequ | +0.836 |
pneum | +0.797 |
helic | +0.754 |
stro | +0.752 |
Neg logit contributions | |
ariat | -1.260 |
rium | -1.228 |
Merit | -1.157 |
anity | -1.132 |
sup | -1.099 |
Token | 4 |
Token ID | 604 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
hetical | +3.086 |
sequ | +3.086 |
pneum | +2.957 |
stro | +2.843 |
helic | +2.824 |
Neg logit contributions | |
ariat | -2.406 |
rium | -2.311 |
anity | -2.083 |
Merit | -2.083 |
merce | -2.027 |
Token | of |
Token ID | 286 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
hetical | +0.449 |
sequ | +0.440 |
pneum | +0.420 |
stro | +0.403 |
helic | +0.400 |
Neg logit contributions | |
ariat | -0.483 |
rium | -0.468 |
Merit | -0.434 |
anity | -0.427 |
sup | -0.410 |
Token | 15 |
Token ID | 1315 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
hetical | +0.659 |
sequ | +0.656 |
pneum | +0.633 |
stro | +0.608 |
helic | +0.605 |
Neg logit contributions | |
ariat | -0.513 |
rium | -0.491 |
Merit | -0.448 |
anity | -0.440 |
merce | -0.422 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
ariat | +0.033 |
rium | +0.033 |
Merit | +0.031 |
anity | +0.030 |
sup | +0.030 |
Neg logit contributions | |
hetical | -0.018 |
sequ | -0.017 |
pneum | -0.016 |
stro | -0.015 |
helic | -0.015 |
Token | : |
Token ID | 25 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
hetical | +2.587 |
sequ | +2.585 |
pneum | +2.421 |
stro | +2.310 |
actionDate | +2.289 |
Neg logit contributions | |
ariat | -3.163 |
rium | -3.048 |
Merit | -2.839 |
anity | -2.810 |
merce | -2.774 |
Token | Carly |
Token ID | 35982 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
hetical | +0.848 |
sequ | +0.830 |
pneum | +0.796 |
stro | +0.759 |
helic | +0.759 |
Neg logit contributions | |
ariat | -0.967 |
rium | -0.936 |
Merit | -0.874 |
anity | -0.855 |
sup | -0.827 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
hetical | +0.456 |
sequ | +0.449 |
pneum | +0.434 |
helic | +0.417 |
stro | +0.417 |
Neg logit contributions | |
ariat | -0.347 |
rium | -0.333 |
Merit | -0.306 |
anity | -0.297 |
sup | -0.285 |
Token | 's |
Token ID | 338 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
hetical | +0.458 |
sequ | +0.452 |
pneum | +0.434 |
stro | +0.416 |
helic | +0.415 |
Neg logit contributions | |
ariat | -0.451 |
rium | -0.438 |
Merit | -0.405 |
anity | -0.395 |
sup | -0.379 |
Token | political |
Token ID | 1964 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
hetical | +0.874 |
sequ | +0.863 |
pneum | +0.828 |
stro | +0.790 |
helic | +0.789 |
Neg logit contributions | |
ariat | -1.003 |
rium | -0.972 |
Merit | -0.908 |
anity | -0.885 |
sup | -0.854 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ariat | +0.055 |
rium | +0.053 |
Merit | +0.049 |
anity | +0.048 |
sup | +0.046 |
Neg logit contributions | |
hetical | -0.056 |
sequ | -0.055 |
pneum | -0.053 |
helic | -0.051 |
stro | -0.051 |
Token | state |
Token ID | 1181 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
ariat | +0.177 |
rium | +0.171 |
Merit | +0.160 |
anity | +0.156 |
sup | +0.151 |
Neg logit contributions | |
hetical | -0.158 |
sequ | -0.154 |
pneum | -0.148 |
helic | -0.142 |
stro | -0.141 |
Token | that |
Token ID | 326 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
hetical | +0.350 |
sequ | +0.344 |
pneum | +0.330 |
stro | +0.317 |
helic | +0.316 |
Neg logit contributions | |
ariat | -0.320 |
rium | -0.310 |
Merit | -0.288 |
anity | -0.280 |
sup | -0.269 |
Token | has |
Token ID | 468 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
ariat | +0.177 |
rium | +0.172 |
Merit | +0.161 |
anity | +0.157 |
sup | +0.148 |
Neg logit contributions | |
hetical | -0.174 |
sequ | -0.172 |
pneum | -0.165 |
helic | -0.157 |
stro | -0.157 |
Token | acc |
Token ID | 697 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
hetical | +0.020 |
sequ | +0.020 |
pneum | +0.019 |
helic | +0.019 |
stro | +0.018 |
Neg logit contributions | |
ariat | -0.019 |
rium | -0.019 |
Merit | -0.017 |
anity | -0.017 |
sup | -0.016 |
Token | eded |
Token ID | 15395 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
ariat | +0.416 |
rium | +0.403 |
Merit | +0.378 |
anity | +0.368 |
sup | +0.357 |
Neg logit contributions | |
hetical | -0.374 |
sequ | -0.366 |
pneum | -0.351 |
stro | -0.335 |
helic | -0.335 |
Token | to |
Token ID | 284 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
sequ | +2.585 |
hetical | +2.532 |
pneum | +2.438 |
stro | +2.283 |
helic | +2.260 |
Neg logit contributions | |
ariat | -2.947 |
rium | -2.890 |
Merit | -2.690 |
anity | -2.636 |
sup | -2.454 |
Token | international |
Token ID | 3230 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
ariat | +0.037 |
rium | +0.036 |
Merit | +0.034 |
anity | +0.033 |
sup | +0.032 |
Neg logit contributions | |
hetical | -0.032 |
sequ | -0.032 |
pneum | -0.031 |
stro | -0.029 |
helic | -0.029 |
Token | treaties |
Token ID | 30734 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
hetical | +0.367 |
sequ | +0.362 |
pneum | +0.351 |
stro | +0.335 |
helic | +0.335 |
Neg logit contributions | |
ariat | -0.273 |
rium | -0.265 |
Merit | -0.243 |
anity | -0.236 |
sup | -0.223 |
Token | on |
Token ID | 319 |
Feature activation | +7.50e-04 |
Pos logit contributions | |
hetical | +0.211 |
sequ | +0.208 |
pneum | +0.200 |
stro | +0.191 |
helic | +0.190 |
Neg logit contributions | |
ariat | -0.195 |
rium | -0.189 |
Merit | -0.174 |
anity | -0.170 |
sup | -0.161 |
Token | human |
Token ID | 1692 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ariat | +0.001 |
rium | +0.001 |
Merit | +0.001 |
anity | +0.001 |
sup | +0.000 |
Neg logit contributions | |
hetical | -0.001 |
sequ | -0.001 |
pneum | -0.001 |
helic | -0.000 |
stro | -0.000 |
Token | al |
Token ID | 282 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
hetical | +0.167 |
sequ | +0.164 |
pneum | +0.158 |
stro | +0.152 |
helic | +0.151 |
Neg logit contributions | |
ariat | -0.139 |
rium | -0.134 |
Merit | -0.125 |
anity | -0.120 |
sup | -0.116 |
Token | Bol |
Token ID | 10797 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
hetical | +0.124 |
sequ | +0.121 |
pneum | +0.117 |
stro | +0.112 |
helic | +0.112 |
Neg logit contributions | |
ariat | -0.116 |
rium | -0.112 |
Merit | -0.105 |
anity | -0.102 |
sup | -0.098 |
Token | k |
Token ID | 74 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
hetical | +0.113 |
sequ | +0.110 |
pneum | +0.106 |
stro | +0.102 |
helic | +0.102 |
Neg logit contributions | |
ariat | -0.106 |
rium | -0.102 |
Merit | -0.095 |
anity | -0.093 |
sup | -0.089 |
Token | iah |
Token ID | 9520 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
ariat | +0.368 |
rium | +0.353 |
Merit | +0.324 |
anity | +0.315 |
sup | +0.302 |
Neg logit contributions | |
hetical | -0.484 |
sequ | -0.476 |
pneum | -0.461 |
helic | -0.445 |
stro | -0.443 |
Token | acc |
Token ID | 697 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
ariat | +0.033 |
rium | +0.032 |
Merit | +0.029 |
anity | +0.029 |
sup | +0.027 |
Neg logit contributions | |
hetical | -0.034 |
sequ | -0.034 |
pneum | -0.032 |
stro | -0.031 |
helic | -0.031 |
Token | eding |
Token ID | 8228 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
ariat | +0.626 |
rium | +0.606 |
Merit | +0.560 |
anity | +0.547 |
sup | +0.528 |
Neg logit contributions | |
hetical | -0.661 |
sequ | -0.650 |
pneum | -0.628 |
helic | -0.603 |
stro | -0.598 |
Token | to |
Token ID | 284 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
sequ | +2.562 |
hetical | +2.547 |
pneum | +2.410 |
stro | +2.294 |
helic | +2.287 |
Neg logit contributions | |
ariat | -2.927 |
rium | -2.857 |
Merit | -2.655 |
anity | -2.625 |
sup | -2.484 |
Token | the |
Token ID | 262 |
Feature activation | +2.72e-03 |
Pos logit contributions | |
hetical | +0.171 |
sequ | +0.169 |
pneum | +0.162 |
helic | +0.155 |
stro | +0.155 |
Neg logit contributions | |
ariat | -0.163 |
rium | -0.158 |
Merit | -0.147 |
anity | -0.144 |
sup | -0.137 |
Token | throne |
Token ID | 19262 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
ariat | +0.002 |
rium | +0.002 |
Merit | +0.002 |
anity | +0.002 |
sup | +0.002 |
Neg logit contributions | |
hetical | -0.002 |
sequ | -0.002 |
pneum | -0.002 |
helic | -0.002 |
stro | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
hetical | +0.619 |
sequ | +0.612 |
pneum | +0.584 |
stro | +0.560 |
helic | +0.558 |
Neg logit contributions | |
ariat | -0.632 |
rium | -0.614 |
Merit | -0.571 |
anity | -0.557 |
sup | -0.534 |
Token | The |
Token ID | 383 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ariat | +0.059 |
rium | +0.057 |
Merit | +0.053 |
anity | +0.052 |
sup | +0.050 |
Neg logit contributions | |
hetical | -0.055 |
sequ | -0.054 |
pneum | -0.052 |
stro | -0.050 |
helic | -0.050 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
hetical | +0.371 |
sequ | +0.364 |
pneum | +0.352 |
stro | +0.341 |
helic | +0.339 |
Neg logit contributions | |
ariat | -0.239 |
rium | -0.229 |
Merit | -0.208 |
anity | -0.201 |
sup | -0.191 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
hetical | +1.125 |
sequ | +1.097 |
pneum | +1.046 |
helic | +0.992 |
stro | +0.990 |
Neg logit contributions | |
ariat | -1.628 |
rium | -1.584 |
Merit | -1.493 |
anity | -1.461 |
sup | -1.421 |
Token | 5 |
Token ID | 642 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
sequ | +2.840 |
hetical | +2.832 |
pneum | +2.682 |
actionDate | +2.585 |
stro | +2.576 |
Neg logit contributions | |
ariat | -2.257 |
rium | -2.193 |
Merit | -1.980 |
anity | -1.941 |
merce | -1.901 |
Token | of |
Token ID | 286 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
hetical | +0.684 |
sequ | +0.672 |
pneum | +0.640 |
stro | +0.615 |
helic | +0.605 |
Neg logit contributions | |
ariat | -0.750 |
rium | -0.727 |
Merit | -0.677 |
anity | -0.664 |
sup | -0.636 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
hetical | +0.382 |
sequ | +0.378 |
pneum | +0.362 |
stro | +0.349 |
helic | +0.348 |
Neg logit contributions | |
ariat | -0.310 |
rium | -0.299 |
Merit | -0.275 |
anity | -0.269 |
sup | -0.256 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
hetical | +0.001 |
sequ | +0.001 |
pneum | +0.001 |
stro | +0.001 |
helic | +0.001 |
Neg logit contributions | |
ariat | -0.001 |
rium | -0.001 |
Merit | -0.001 |
anity | -0.001 |
sup | -0.001 |
Token | : |
Token ID | 25 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
hetical | +2.410 |
sequ | +2.393 |
pneum | +2.222 |
stro | +2.172 |
──── | +2.112 |
Neg logit contributions | |
ariat | -3.044 |
rium | -2.947 |
merce | -2.766 |
Merit | -2.736 |
anity | -2.728 |
Token | Carly |
Token ID | 35982 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
hetical | +0.716 |
sequ | +0.702 |
pneum | +0.675 |
stro | +0.649 |
helic | +0.646 |
Neg logit contributions | |
ariat | -0.639 |
rium | -0.619 |
Merit | -0.570 |
anity | -0.557 |
sup | -0.534 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
hetical | +0.299 |
sequ | +0.294 |
pneum | +0.283 |
stro | +0.273 |
helic | +0.271 |
Neg logit contributions | |
ariat | -0.237 |
rium | -0.227 |
Merit | -0.209 |
anity | -0.203 |
sup | -0.194 |
Token | 's |
Token ID | 338 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
hetical | +0.306 |
sequ | +0.300 |
pneum | +0.288 |
stro | +0.275 |
helic | +0.275 |
Neg logit contributions | |
ariat | -0.333 |
rium | -0.323 |
Merit | -0.302 |
anity | -0.294 |
sup | -0.284 |
Token | political |
Token ID | 1964 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
hetical | +0.607 |
sequ | +0.592 |
pneum | +0.568 |
stro | +0.538 |
helic | +0.538 |
Neg logit contributions | |
ariat | -0.796 |
rium | -0.776 |
Merit | -0.728 |
anity | -0.713 |
sup | -0.688 |
Token | er |
Token ID | 263 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
ariat | +0.010 |
rium | +0.010 |
Merit | +0.009 |
anity | +0.009 |
sup | +0.009 |
Neg logit contributions | |
hetical | -0.007 |
sequ | -0.006 |
pneum | -0.006 |
stro | -0.006 |
helic | -0.006 |
Token | magnet |
Token ID | 19972 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
hetical | +0.002 |
sequ | +0.002 |
pneum | +0.002 |
helic | +0.002 |
stro | +0.002 |
Neg logit contributions | |
ariat | -0.003 |
rium | -0.003 |
Merit | -0.003 |
anity | -0.003 |
sup | -0.003 |
Token | ? |
Token ID | 30 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
ariat | +0.834 |
rium | +0.812 |
Merit | +0.769 |
anity | +0.751 |
sup | +0.731 |
Neg logit contributions | |
hetical | -0.538 |
sequ | -0.525 |
pneum | -0.497 |
helic | -0.473 |
stro | -0.468 |
Token |
|
Token ID | 198 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
hetical | +0.588 |
sequ | +0.578 |
pneum | +0.557 |
helic | +0.535 |
stro | +0.532 |
Neg logit contributions | |
ariat | -0.536 |
rium | -0.520 |
Merit | -0.481 |
anity | -0.468 |
sup | -0.450 |
Token |
|
Token ID | 198 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
ariat | +0.114 |
rium | +0.110 |
Merit | +0.102 |
anity | +0.100 |
sup | +0.095 |
Neg logit contributions | |
hetical | -0.124 |
sequ | -0.122 |
pneum | -0.117 |
stro | -0.113 |
helic | -0.111 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
ariat | +0.022 |
rium | +0.022 |
Merit | +0.020 |
anity | +0.020 |
sup | +0.020 |
Neg logit contributions | |
hetical | -0.014 |
sequ | -0.014 |
pneum | -0.013 |
stro | -0.013 |
helic | -0.012 |
Token | : |
Token ID | 25 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
hetical | +2.411 |
sequ | +2.406 |
pneum | +2.228 |
stro | +2.170 |
──── | +2.103 |
Neg logit contributions | |
ariat | -3.048 |
rium | -2.953 |
Merit | -2.741 |
anity | -2.710 |
merce | -2.701 |
Token | hey |
Token ID | 17207 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ariat | +0.550 |
rium | +0.532 |
Merit | +0.497 |
anity | +0.483 |
sup | +0.466 |
Neg logit contributions | |
hetical | -0.543 |
sequ | -0.534 |
pneum | -0.513 |
helic | -0.492 |
stro | -0.490 |
Token | _ |
Token ID | 62 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
hetical | +0.240 |
sequ | +0.236 |
pneum | +0.227 |
stro | +0.219 |
helic | +0.218 |
Neg logit contributions | |
ariat | -0.226 |
rium | -0.217 |
Merit | -0.203 |
anity | -0.196 |
sup | -0.190 |
Token | ler |
Token ID | 1754 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
hetical | +1.006 |
sequ | +0.988 |
pneum | +0.944 |
stro | +0.928 |
helic | +0.907 |
Neg logit contributions | |
ariat | -0.903 |
rium | -0.865 |
Merit | -0.813 |
anity | -0.782 |
sup | -0.761 |
Token | oy |
Token ID | 726 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
ariat | +0.065 |
rium | +0.063 |
Merit | +0.058 |
anity | +0.056 |
sup | +0.054 |
Neg logit contributions | |
hetical | -0.077 |
sequ | -0.076 |
pneum | -0.073 |
stro | -0.071 |
helic | -0.070 |
Token | are |
Token ID | 389 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
hetical | +0.167 |
sequ | +0.165 |
pneum | +0.158 |
helic | +0.149 |
stro | +0.149 |
Neg logit contributions | |
ariat | -0.188 |
rium | -0.181 |
Merit | -0.171 |
anity | -0.166 |
sup | -0.159 |
Token | Here |
Token ID | 3423 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
hetical | +0.110 |
sequ | +0.107 |
pneum | +0.103 |
helic | +0.097 |
stro | +0.097 |
Neg logit contributions | |
ariat | -0.155 |
rium | -0.150 |
Merit | -0.142 |
anity | -0.139 |
sup | -0.135 |
Token | .... |
Token ID | 1106 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ariat | +0.431 |
rium | +0.416 |
Merit | +0.386 |
anity | +0.374 |
sup | +0.361 |
Neg logit contributions | |
hetical | -0.508 |
sequ | -0.499 |
pneum | -0.482 |
helic | -0.462 |
stro | -0.462 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ariat | +1.081 |
rium | +1.041 |
Merit | +0.966 |
anity | +0.940 |
sup | +0.907 |
Neg logit contributions | |
hetical | -1.259 |
sequ | -1.233 |
pneum | -1.189 |
helic | -1.145 |
stro | -1.143 |
Token |
|
Token ID | 198 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
hetical | +0.118 |
sequ | +0.116 |
pneum | +0.111 |
stro | +0.108 |
helic | +0.105 |
Neg logit contributions | |
ariat | -0.112 |
rium | -0.108 |
Merit | -0.100 |
anity | -0.097 |
sup | -0.093 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
hetical | +0.107 |
sequ | +0.104 |
pneum | +0.098 |
stro | +0.095 |
helic | +0.093 |
Neg logit contributions | |
ariat | -0.169 |
rium | -0.163 |
Merit | -0.153 |
anity | -0.151 |
sup | -0.148 |
Token | : |
Token ID | 25 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
hetical | +2.355 |
sequ | +2.348 |
pneum | +2.176 |
stro | +2.117 |
──── | +2.053 |
Neg logit contributions | |
ariat | -2.974 |
rium | -2.884 |
Merit | -2.676 |
anity | -2.643 |
merce | -2.634 |
Token | SAS |
Token ID | 35516 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
ariat | +0.422 |
rium | +0.409 |
Merit | +0.382 |
anity | +0.371 |
sup | +0.357 |
Neg logit contributions | |
hetical | -0.422 |
sequ | -0.415 |
pneum | -0.399 |
helic | -0.383 |
stro | -0.381 |
Token | K |
Token ID | 42 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
hetical | +0.075 |
sequ | +0.074 |
pneum | +0.071 |
stro | +0.069 |
helic | +0.069 |
Neg logit contributions | |
ariat | -0.064 |
rium | -0.062 |
Merit | -0.057 |
anity | -0.055 |
sup | -0.053 |
Token | ATCH |
Token ID | 11417 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
hetical | +0.516 |
sequ | +0.507 |
pneum | +0.489 |
stro | +0.475 |
helic | +0.474 |
Neg logit contributions | |
ariat | -0.388 |
rium | -0.372 |
Merit | -0.341 |
anity | -0.330 |
sup | -0.318 |
Token | EW |
Token ID | 6217 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
hetical | +0.065 |
sequ | +0.064 |
pneum | +0.062 |
stro | +0.060 |
helic | +0.060 |
Neg logit contributions | |
ariat | -0.045 |
rium | -0.044 |
Merit | -0.040 |
anity | -0.039 |
sup | -0.037 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
hetical | +0.336 |
sequ | +0.331 |
pneum | +0.319 |
stro | +0.309 |
helic | +0.307 |
Neg logit contributions | |
ariat | -0.216 |
rium | -0.207 |
Merit | -0.188 |
anity | -0.182 |
sup | -0.173 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
hetical | +1.310 |
sequ | +1.280 |
pneum | +1.214 |
stro | +1.149 |
helic | +1.147 |
Neg logit contributions | |
ariat | -1.948 |
rium | -1.897 |
Merit | -1.789 |
anity | -1.754 |
sup | -1.700 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
hetical | +2.601 |
sequ | +2.554 |
pneum | +2.457 |
stro | +2.350 |
helic | +2.342 |
Neg logit contributions | |
ariat | -2.509 |
rium | -2.421 |
Merit | -2.256 |
anity | -2.196 |
sup | -2.109 |
Token | of |
Token ID | 286 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
hetical | +0.724 |
sequ | +0.712 |
pneum | +0.676 |
stro | +0.651 |
helic | +0.636 |
Neg logit contributions | |
ariat | -0.807 |
rium | -0.782 |
Merit | -0.729 |
anity | -0.717 |
merce | -0.687 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
hetical | +0.395 |
sequ | +0.391 |
pneum | +0.374 |
stro | +0.361 |
helic | +0.359 |
Neg logit contributions | |
ariat | -0.324 |
rium | -0.313 |
Merit | -0.287 |
anity | -0.282 |
sup | -0.267 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
hetical | +0.079 |
sequ | +0.078 |
pneum | +0.073 |
stro | +0.068 |
helic | +0.068 |
Neg logit contributions | |
ariat | -0.154 |
rium | -0.150 |
Merit | -0.142 |
anity | -0.140 |
sup | -0.136 |
Token | : |
Token ID | 25 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
hetical | +2.311 |
sequ | +2.291 |
pneum | +2.128 |
stro | +2.084 |
──── | +2.022 |
Neg logit contributions | |
ariat | -2.916 |
rium | -2.824 |
merce | -2.649 |
Merit | -2.622 |
anity | -2.614 |
Token | Carly |
Token ID | 35982 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
hetical | +0.776 |
sequ | +0.761 |
pneum | +0.732 |
stro | +0.704 |
helic | +0.700 |
Neg logit contributions | |
ariat | -0.691 |
rium | -0.669 |
Merit | -0.617 |
anity | -0.602 |
sup | -0.578 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
hetical | +0.245 |
sequ | +0.240 |
pneum | +0.231 |
stro | +0.223 |
helic | +0.221 |
Neg logit contributions | |
ariat | -0.192 |
rium | -0.185 |
Merit | -0.169 |
anity | -0.165 |
sup | -0.158 |
Token | 's |
Token ID | 338 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
hetical | +0.220 |
sequ | +0.216 |
pneum | +0.206 |
stro | +0.198 |
helic | +0.196 |
Neg logit contributions | |
ariat | -0.246 |
rium | -0.238 |
Merit | -0.223 |
anity | -0.218 |
sup | -0.210 |
Token | political |
Token ID | 1964 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
hetical | +0.589 |
sequ | +0.575 |
pneum | +0.552 |
stro | +0.522 |
helic | +0.520 |
Neg logit contributions | |
ariat | -0.787 |
rium | -0.769 |
Merit | -0.723 |
anity | -0.707 |
sup | -0.680 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
hetical | +0.281 |
sequ | +0.276 |
pneum | +0.266 |
stro | +0.258 |
helic | +0.256 |
Neg logit contributions | |
ariat | -0.175 |
rium | -0.167 |
Merit | -0.151 |
anity | -0.147 |
sup | -0.139 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
hetical | +1.160 |
sequ | +1.133 |
pneum | +1.078 |
helic | +1.019 |
stro | +1.019 |
Neg logit contributions | |
ariat | -1.709 |
rium | -1.664 |
Merit | -1.569 |
anity | -1.537 |
sup | -1.492 |
Token | 12 |
Token ID | 1105 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
hetical | +2.524 |
sequ | +2.492 |
pneum | +2.403 |
stro | +2.298 |
helic | +2.258 |
Neg logit contributions | |
ariat | -2.452 |
rium | -2.352 |
Merit | -2.202 |
anity | -2.172 |
merce | -2.073 |
Token | of |
Token ID | 286 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
hetical | +0.169 |
sequ | +0.166 |
pneum | +0.158 |
stro | +0.152 |
helic | +0.150 |
Neg logit contributions | |
ariat | -0.180 |
rium | -0.175 |
Merit | -0.163 |
anity | -0.159 |
sup | -0.153 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
hetical | +0.348 |
sequ | +0.344 |
pneum | +0.329 |
stro | +0.318 |
helic | +0.316 |
Neg logit contributions | |
ariat | -0.283 |
rium | -0.274 |
Merit | -0.251 |
anity | -0.246 |
sup | -0.234 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
hetical | +0.074 |
sequ | +0.072 |
pneum | +0.067 |
stro | +0.063 |
helic | +0.063 |
Neg logit contributions | |
ariat | -0.142 |
rium | -0.139 |
Merit | -0.131 |
anity | -0.129 |
sup | -0.125 |
Token | : |
Token ID | 25 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
hetical | +2.293 |
sequ | +2.275 |
pneum | +2.111 |
stro | +2.069 |
──── | +2.005 |
Neg logit contributions | |
ariat | -2.923 |
rium | -2.837 |
merce | -2.675 |
Merit | -2.627 |
anity | -2.624 |
Token | Carly |
Token ID | 35982 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
hetical | +0.744 |
sequ | +0.730 |
pneum | +0.703 |
stro | +0.675 |
helic | +0.672 |
Neg logit contributions | |
ariat | -0.660 |
rium | -0.638 |
Merit | -0.588 |
anity | -0.575 |
sup | -0.551 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
hetical | +0.355 |
sequ | +0.349 |
pneum | +0.336 |
stro | +0.324 |
helic | +0.321 |
Neg logit contributions | |
ariat | -0.279 |
rium | -0.269 |
Merit | -0.246 |
anity | -0.240 |
sup | -0.229 |
Token | 's |
Token ID | 338 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
hetical | +0.176 |
sequ | +0.172 |
pneum | +0.165 |
stro | +0.158 |
helic | +0.157 |
Neg logit contributions | |
ariat | -0.195 |
rium | -0.189 |
Merit | -0.176 |
anity | -0.172 |
sup | -0.166 |
Token | political |
Token ID | 1964 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
hetical | +0.564 |
sequ | +0.552 |
pneum | +0.529 |
stro | +0.501 |
helic | +0.500 |
Neg logit contributions | |
ariat | -0.747 |
rium | -0.729 |
Merit | -0.685 |
anity | -0.670 |
sup | -0.645 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ariat | +0.000 |
rium | +0.000 |
Merit | +0.000 |
anity | +0.000 |
sup | +0.000 |
Neg logit contributions | |
hetical | -0.000 |
sequ | -0.000 |
pneum | -0.000 |
stro | -0.000 |
helic | -0.000 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
hetical | +1.205 |
sequ | +1.178 |
pneum | +1.117 |
stro | +1.056 |
helic | +1.053 |
Neg logit contributions | |
ariat | -1.804 |
rium | -1.758 |
Merit | -1.657 |
anity | -1.626 |
sup | -1.575 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
hetical | +2.973 |
sequ | +2.952 |
pneum | +2.844 |
stro | +2.734 |
helic | +2.697 |
Neg logit contributions | |
ariat | -2.045 |
rium | -1.959 |
Merit | -1.767 |
anity | -1.735 |
merce | -1.668 |
Token | of |
Token ID | 286 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
hetical | +0.200 |
sequ | +0.196 |
pneum | +0.187 |
stro | +0.179 |
helic | +0.178 |
Neg logit contributions | |
ariat | -0.212 |
rium | -0.205 |
Merit | -0.191 |
anity | -0.187 |
sup | -0.180 |
Token | 15 |
Token ID | 1315 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
hetical | +0.181 |
sequ | +0.179 |
pneum | +0.172 |
stro | +0.166 |
helic | +0.165 |
Neg logit contributions | |
ariat | -0.144 |
rium | -0.139 |
Merit | -0.128 |
anity | -0.125 |
sup | -0.119 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
hetical | +0.028 |
sequ | +0.027 |
pneum | +0.026 |
stro | +0.024 |
helic | +0.024 |
Neg logit contributions | |
ariat | -0.053 |
rium | -0.052 |
Merit | -0.049 |
anity | -0.048 |
sup | -0.047 |
Token | : |
Token ID | 25 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
hetical | +2.295 |
sequ | +2.278 |
pneum | +2.112 |
stro | +2.071 |
──── | +2.007 |
Neg logit contributions | |
ariat | -2.918 |
rium | -2.831 |
merce | -2.664 |
Merit | -2.623 |
anity | -2.618 |
Token | Carly |
Token ID | 35982 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
hetical | +0.647 |
sequ | +0.634 |
pneum | +0.611 |
stro | +0.587 |
helic | +0.585 |
Neg logit contributions | |
ariat | -0.569 |
rium | -0.550 |
Merit | -0.508 |
anity | -0.495 |
sup | -0.475 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
hetical | +0.215 |
sequ | +0.211 |
pneum | +0.203 |
stro | +0.196 |
helic | +0.195 |
Neg logit contributions | |
ariat | -0.167 |
rium | -0.160 |
Merit | -0.147 |
anity | -0.143 |
sup | -0.137 |
Token | 's |
Token ID | 338 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
hetical | +0.132 |
sequ | +0.130 |
pneum | +0.124 |
stro | +0.119 |
helic | +0.119 |
Neg logit contributions | |
ariat | -0.145 |
rium | -0.140 |
Merit | -0.131 |
anity | -0.128 |
sup | -0.124 |
Token | political |
Token ID | 1964 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
hetical | +0.510 |
sequ | +0.498 |
pneum | +0.478 |
stro | +0.453 |
helic | +0.452 |
Neg logit contributions | |
ariat | -0.671 |
rium | -0.655 |
Merit | -0.615 |
anity | -0.601 |
sup | -0.580 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ariat | +0.079 |
rium | +0.076 |
Merit | +0.069 |
anity | +0.067 |
sup | +0.064 |
Neg logit contributions | |
hetical | -0.113 |
sequ | -0.111 |
pneum | -0.108 |
stro | -0.104 |
helic | -0.103 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
hetical | +1.158 |
sequ | +1.131 |
pneum | +1.074 |
stro | +1.017 |
helic | +1.016 |
Neg logit contributions | |
ariat | -1.711 |
rium | -1.666 |
Merit | -1.571 |
anity | -1.539 |
sup | -1.493 |
Token | 9 |
Token ID | 860 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
sequ | +2.703 |
hetical | +2.693 |
pneum | +2.530 |
Tolkien | +2.464 |
stro | +2.458 |
Neg logit contributions | |
ariat | -2.101 |
rium | -2.060 |
merce | -1.864 |
Merit | -1.862 |
anity | -1.841 |
Token | of |
Token ID | 286 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
hetical | +0.616 |
sequ | +0.605 |
pneum | +0.576 |
stro | +0.553 |
helic | +0.542 |
Neg logit contributions | |
ariat | -0.679 |
rium | -0.658 |
Merit | -0.614 |
anity | -0.602 |
sup | -0.576 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
hetical | +0.285 |
sequ | +0.282 |
pneum | +0.269 |
stro | +0.260 |
helic | +0.258 |
Neg logit contributions | |
ariat | -0.231 |
rium | -0.224 |
Merit | -0.205 |
anity | -0.201 |
sup | -0.191 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
hetical | +0.081 |
sequ | +0.079 |
pneum | +0.074 |
stro | +0.069 |
helic | +0.068 |
Neg logit contributions | |
ariat | -0.157 |
rium | -0.153 |
Merit | -0.145 |
anity | -0.143 |
sup | -0.139 |
Token | : |
Token ID | 25 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
hetical | +2.288 |
sequ | +2.270 |
pneum | +2.107 |
stro | +2.063 |
──── | +2.000 |
Neg logit contributions | |
ariat | -2.892 |
rium | -2.805 |
merce | -2.632 |
Merit | -2.599 |
anity | -2.594 |
Token | Carly |
Token ID | 35982 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
hetical | +0.677 |
sequ | +0.664 |
pneum | +0.639 |
stro | +0.614 |
helic | +0.612 |
Neg logit contributions | |
ariat | -0.597 |
rium | -0.577 |
Merit | -0.533 |
anity | -0.520 |
sup | -0.499 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
hetical | +0.341 |
sequ | +0.336 |
pneum | +0.323 |
stro | +0.311 |
helic | +0.309 |
Neg logit contributions | |
ariat | -0.267 |
rium | -0.257 |
Merit | -0.235 |
anity | -0.229 |
sup | -0.219 |
Token | 's |
Token ID | 338 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
hetical | +0.212 |
sequ | +0.207 |
pneum | +0.198 |
stro | +0.190 |
helic | +0.189 |
Neg logit contributions | |
ariat | -0.232 |
rium | -0.225 |
Merit | -0.210 |
anity | -0.205 |
sup | -0.198 |
Token | political |
Token ID | 1964 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
hetical | +0.549 |
sequ | +0.536 |
pneum | +0.514 |
stro | +0.486 |
helic | +0.485 |
Neg logit contributions | |
ariat | -0.726 |
rium | -0.709 |
Merit | -0.666 |
anity | -0.651 |
sup | -0.627 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
ariat | +0.071 |
rium | +0.068 |
Merit | +0.062 |
anity | +0.060 |
sup | +0.057 |
Neg logit contributions | |
hetical | -0.115 |
sequ | -0.113 |
pneum | -0.109 |
stro | -0.105 |
helic | -0.105 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
hetical | +1.253 |
sequ | +1.223 |
pneum | +1.163 |
helic | +1.101 |
stro | +1.100 |
Neg logit contributions | |
ariat | -1.842 |
rium | -1.792 |
Merit | -1.690 |
anity | -1.656 |
sup | -1.607 |
Token | 8 |
Token ID | 807 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
hetical | +3.080 |
sequ | +3.049 |
pneum | +2.944 |
stro | +2.842 |
actionDate | +2.805 |
Neg logit contributions | |
ariat | -1.999 |
rium | -1.913 |
Merit | -1.725 |
anity | -1.701 |
merce | -1.699 |
Token | of |
Token ID | 286 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
hetical | +0.396 |
sequ | +0.389 |
pneum | +0.371 |
stro | +0.356 |
helic | +0.350 |
Neg logit contributions | |
ariat | -0.431 |
rium | -0.417 |
Merit | -0.389 |
anity | -0.381 |
sup | -0.365 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
hetical | +0.246 |
sequ | +0.243 |
pneum | +0.233 |
stro | +0.225 |
helic | +0.224 |
Neg logit contributions | |
ariat | -0.199 |
rium | -0.192 |
Merit | -0.176 |
anity | -0.173 |
sup | -0.164 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
hetical | +0.088 |
sequ | +0.086 |
pneum | +0.080 |
stro | +0.075 |
helic | +0.074 |
Neg logit contributions | |
ariat | -0.170 |
rium | -0.165 |
Merit | -0.157 |
anity | -0.154 |
sup | -0.150 |
Token | : |
Token ID | 25 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
hetical | +2.291 |
sequ | +2.274 |
pneum | +2.112 |
stro | +2.066 |
──── | +2.003 |
Neg logit contributions | |
ariat | -2.887 |
rium | -2.797 |
merce | -2.622 |
Merit | -2.594 |
anity | -2.588 |
Token | Carly |
Token ID | 35982 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
hetical | +0.628 |
sequ | +0.616 |
pneum | +0.594 |
stro | +0.570 |
helic | +0.569 |
Neg logit contributions | |
ariat | -0.550 |
rium | -0.531 |
Merit | -0.491 |
anity | -0.478 |
sup | -0.459 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
hetical | +0.294 |
sequ | +0.289 |
pneum | +0.278 |
stro | +0.268 |
helic | +0.266 |
Neg logit contributions | |
ariat | -0.230 |
rium | -0.221 |
Merit | -0.203 |
anity | -0.198 |
sup | -0.189 |
Token | 's |
Token ID | 338 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
hetical | +0.230 |
sequ | +0.225 |
pneum | +0.215 |
stro | +0.206 |
helic | +0.205 |
Neg logit contributions | |
ariat | -0.255 |
rium | -0.247 |
Merit | -0.231 |
anity | -0.225 |
sup | -0.217 |
Token | political |
Token ID | 1964 |
Feature activation | +9.97e-02 |
Pos logit contributions | |
hetical | +0.572 |
sequ | +0.558 |
pneum | +0.536 |
stro | +0.507 |
helic | +0.506 |
Neg logit contributions | |
ariat | -0.758 |
rium | -0.740 |
Merit | -0.696 |
anity | -0.680 |
sup | -0.655 |
Token | when |
Token ID | 618 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
hetical | +0.135 |
sequ | +0.133 |
pneum | +0.128 |
helic | +0.122 |
stro | +0.122 |
Neg logit contributions | |
ariat | -0.134 |
rium | -0.130 |
Merit | -0.121 |
anity | -0.117 |
sup | -0.113 |
Token | you |
Token ID | 345 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ariat | +0.524 |
rium | +0.507 |
Merit | +0.472 |
anity | +0.460 |
sup | +0.445 |
Neg logit contributions | |
hetical | -0.522 |
sequ | -0.511 |
pneum | -0.492 |
helic | -0.471 |
stro | -0.470 |
Token | turn |
Token ID | 1210 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ariat | +0.136 |
rium | +0.132 |
Merit | +0.123 |
anity | +0.120 |
sup | +0.116 |
Neg logit contributions | |
hetical | -0.127 |
sequ | -0.124 |
pneum | -0.119 |
helic | -0.114 |
stro | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
hetical | +0.138 |
sequ | +0.137 |
pneum | +0.131 |
helic | +0.126 |
stro | +0.126 |
Neg logit contributions | |
ariat | -0.130 |
rium | -0.127 |
Merit | -0.118 |
anity | -0.115 |
sup | -0.110 |
Token | f |
Token ID | 277 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ariat | +0.071 |
rium | +0.069 |
Merit | +0.065 |
anity | +0.063 |
sup | +0.060 |
Neg logit contributions | |
hetical | -0.069 |
sequ | -0.068 |
pneum | -0.065 |
helic | -0.063 |
stro | -0.062 |
Token | auc |
Token ID | 14272 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
ariat | +0.291 |
rium | +0.283 |
Merit | +0.268 |
anity | +0.262 |
sup | +0.255 |
Neg logit contributions | |
hetical | -0.183 |
sequ | -0.178 |
pneum | -0.169 |
helic | -0.160 |
stro | -0.160 |
Token | et |
Token ID | 316 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
hetical | +2.978 |
sequ | +2.912 |
pneum | +2.844 |
stro | +2.786 |
helic | +2.695 |
Neg logit contributions | |
ariat | -2.037 |
rium | -2.005 |
Merit | -1.943 |
sup | -1.718 |
anity | -1.704 |
Token | on |
Token ID | 319 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
hetical | +0.046 |
sequ | +0.046 |
pneum | +0.044 |
stro | +0.042 |
helic | +0.042 |
Neg logit contributions | |
ariat | -0.047 |
rium | -0.045 |
Merit | -0.042 |
anity | -0.041 |
sup | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
ariat | +0.281 |
rium | +0.271 |
Merit | +0.252 |
anity | +0.245 |
sup | +0.236 |
Neg logit contributions | |
hetical | -0.313 |
sequ | -0.309 |
pneum | -0.297 |
stro | -0.285 |
helic | -0.285 |
Token | the |
Token ID | 262 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
ariat | +0.049 |
rium | +0.047 |
Merit | +0.044 |
anity | +0.042 |
sup | +0.041 |
Neg logit contributions | |
hetical | -0.055 |
sequ | -0.054 |
pneum | -0.052 |
helic | -0.050 |
stro | -0.050 |
Token | water |
Token ID | 1660 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ariat | +0.019 |
rium | +0.018 |
Merit | +0.017 |
anity | +0.016 |
sup | +0.016 |
Neg logit contributions | |
hetical | -0.018 |
sequ | -0.018 |
pneum | -0.017 |
helic | -0.017 |
stro | -0.016 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
hetical | +0.257 |
sequ | +0.253 |
pneum | +0.245 |
stro | +0.237 |
helic | +0.236 |
Neg logit contributions | |
ariat | -0.159 |
rium | -0.152 |
Merit | -0.138 |
anity | -0.134 |
sup | -0.127 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
hetical | +1.159 |
sequ | +1.132 |
pneum | +1.076 |
stro | +1.017 |
helic | +1.016 |
Neg logit contributions | |
ariat | -1.723 |
rium | -1.677 |
Merit | -1.582 |
anity | -1.551 |
sup | -1.503 |
Token | 13 |
Token ID | 1511 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
sequ | +2.659 |
hetical | +2.648 |
pneum | +2.495 |
stro | +2.448 |
helic | +2.389 |
Neg logit contributions | |
ariat | -2.195 |
rium | -2.137 |
Merit | -1.974 |
anity | -1.943 |
merce | -1.870 |
Token | of |
Token ID | 286 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
hetical | +0.295 |
sequ | +0.290 |
pneum | +0.277 |
stro | +0.265 |
helic | +0.262 |
Neg logit contributions | |
ariat | -0.317 |
rium | -0.307 |
Merit | -0.286 |
anity | -0.280 |
sup | -0.269 |
Token | 15 |
Token ID | 1315 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
hetical | +0.282 |
sequ | +0.279 |
pneum | +0.267 |
stro | +0.258 |
helic | +0.256 |
Neg logit contributions | |
ariat | -0.229 |
rium | -0.222 |
Merit | -0.203 |
anity | -0.199 |
sup | -0.189 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
hetical | +0.047 |
sequ | +0.046 |
pneum | +0.043 |
stro | +0.041 |
helic | +0.040 |
Neg logit contributions | |
ariat | -0.092 |
rium | -0.089 |
Merit | -0.084 |
anity | -0.083 |
sup | -0.081 |
Token | : |
Token ID | 25 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
hetical | +2.250 |
sequ | +2.231 |
pneum | +2.074 |
stro | +2.029 |
──── | +1.966 |
Neg logit contributions | |
ariat | -2.854 |
rium | -2.771 |
merce | -2.607 |
Merit | -2.564 |
anity | -2.562 |
Token | Carly |
Token ID | 35982 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
hetical | +0.635 |
sequ | +0.623 |
pneum | +0.600 |
stro | +0.576 |
helic | +0.574 |
Neg logit contributions | |
ariat | -0.558 |
rium | -0.540 |
Merit | -0.498 |
anity | -0.486 |
sup | -0.466 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
hetical | +0.156 |
sequ | +0.154 |
pneum | +0.148 |
stro | +0.143 |
helic | +0.142 |
Neg logit contributions | |
ariat | -0.121 |
rium | -0.117 |
Merit | -0.107 |
anity | -0.104 |
sup | -0.100 |
Token | 's |
Token ID | 338 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
hetical | +0.039 |
sequ | +0.038 |
pneum | +0.037 |
stro | +0.035 |
helic | +0.035 |
Neg logit contributions | |
ariat | -0.043 |
rium | -0.041 |
Merit | -0.039 |
anity | -0.038 |
sup | -0.037 |
Token | political |
Token ID | 1964 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
hetical | +0.449 |
sequ | +0.439 |
pneum | +0.421 |
stro | +0.399 |
helic | +0.399 |
Neg logit contributions | |
ariat | -0.587 |
rium | -0.572 |
Merit | -0.538 |
anity | -0.525 |
sup | -0.507 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
hetical | +0.079 |
sequ | +0.078 |
pneum | +0.075 |
stro | +0.073 |
helic | +0.073 |
Neg logit contributions | |
ariat | -0.051 |
rium | -0.049 |
Merit | -0.045 |
anity | -0.043 |
sup | -0.041 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
hetical | +1.181 |
sequ | +1.154 |
pneum | +1.096 |
stro | +1.037 |
helic | +1.036 |
Neg logit contributions | |
ariat | -1.749 |
rium | -1.703 |
Merit | -1.605 |
anity | -1.573 |
sup | -1.526 |
Token | 11 |
Token ID | 1367 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
hetical | +2.745 |
sequ | +2.714 |
pneum | +2.600 |
helic | +2.497 |
stro | +2.495 |
Neg logit contributions | |
ariat | -2.134 |
rium | -2.056 |
Merit | -1.898 |
anity | -1.844 |
sup | -1.745 |
Token | of |
Token ID | 286 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
hetical | +0.420 |
sequ | +0.412 |
pneum | +0.393 |
stro | +0.377 |
helic | +0.371 |
Neg logit contributions | |
ariat | -0.458 |
rium | -0.444 |
Merit | -0.414 |
anity | -0.405 |
sup | -0.388 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
hetical | +0.298 |
sequ | +0.295 |
pneum | +0.282 |
stro | +0.272 |
helic | +0.271 |
Neg logit contributions | |
ariat | -0.242 |
rium | -0.234 |
Merit | -0.214 |
anity | -0.210 |
sup | -0.199 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
hetical | +0.056 |
sequ | +0.054 |
pneum | +0.051 |
stro | +0.048 |
helic | +0.047 |
Neg logit contributions | |
ariat | -0.108 |
rium | -0.105 |
Merit | -0.099 |
anity | -0.098 |
sup | -0.095 |
Token | : |
Token ID | 25 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
hetical | +2.242 |
sequ | +2.224 |
pneum | +2.066 |
stro | +2.023 |
──── | +1.959 |
Neg logit contributions | |
ariat | -2.838 |
rium | -2.752 |
merce | -2.585 |
Merit | -2.551 |
anity | -2.544 |
Token | Carly |
Token ID | 35982 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
hetical | +0.691 |
sequ | +0.677 |
pneum | +0.652 |
stro | +0.627 |
helic | +0.624 |
Neg logit contributions | |
ariat | -0.610 |
rium | -0.590 |
Merit | -0.544 |
anity | -0.531 |
sup | -0.509 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
hetical | +0.379 |
sequ | +0.373 |
pneum | +0.359 |
stro | +0.346 |
helic | +0.343 |
Neg logit contributions | |
ariat | -0.298 |
rium | -0.286 |
Merit | -0.262 |
anity | -0.256 |
sup | -0.244 |
Token | 's |
Token ID | 338 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
hetical | +0.188 |
sequ | +0.184 |
pneum | +0.176 |
stro | +0.169 |
helic | +0.168 |
Neg logit contributions | |
ariat | -0.206 |
rium | -0.200 |
Merit | -0.187 |
anity | -0.182 |
sup | -0.176 |
Token | political |
Token ID | 1964 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
hetical | +0.581 |
sequ | +0.567 |
pneum | +0.545 |
stro | +0.515 |
helic | +0.514 |
Neg logit contributions | |
ariat | -0.768 |
rium | -0.750 |
Merit | -0.705 |
anity | -0.689 |
sup | -0.663 |
Token | ecosystem |
Token ID | 13187 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
ariat | +0.333 |
rium | +0.323 |
Merit | +0.297 |
anity | +0.293 |
sup | +0.281 |
Neg logit contributions | |
hetical | -0.378 |
sequ | -0.374 |
pneum | -0.357 |
helic | -0.344 |
stro | -0.343 |
Token | to |
Token ID | 284 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
ariat | +0.065 |
rium | +0.063 |
Merit | +0.059 |
anity | +0.058 |
sup | +0.055 |
Neg logit contributions | |
hetical | -0.066 |
sequ | -0.065 |
pneum | -0.062 |
helic | -0.059 |
stro | -0.059 |
Token | handle |
Token ID | 5412 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ariat | +0.300 |
rium | +0.291 |
Merit | +0.273 |
anity | +0.266 |
sup | +0.257 |
Neg logit contributions | |
hetical | -0.259 |
sequ | -0.255 |
pneum | -0.244 |
helic | -0.232 |
stro | -0.232 |
Token | its |
Token ID | 663 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ariat | +1.334 |
rium | +1.288 |
Merit | +1.202 |
anity | +1.166 |
sup | +1.133 |
Neg logit contributions | |
hetical | -1.381 |
sequ | -1.346 |
pneum | -1.299 |
helic | -1.247 |
stro | -1.246 |
Token | current |
Token ID | 1459 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
ariat | +0.242 |
rium | +0.235 |
Merit | +0.220 |
anity | +0.215 |
sup | +0.208 |
Neg logit contributions | |
hetical | -0.199 |
sequ | -0.196 |
pneum | -0.187 |
helic | -0.178 |
stro | -0.178 |
Token | capacity |
Token ID | 5339 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
hetical | +0.251 |
sequ | +0.250 |
pneum | +0.238 |
helic | +0.227 |
stro | +0.227 |
Neg logit contributions | |
ariat | -0.290 |
rium | -0.283 |
Merit | -0.262 |
anity | -0.258 |
sup | -0.247 |
Token | needs |
Token ID | 2476 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ariat | +1.380 |
rium | +1.332 |
Merit | +1.256 |
anity | +1.218 |
sup | +1.193 |
Neg logit contributions | |
hetical | -1.250 |
sequ | -1.213 |
pneum | -1.170 |
helic | -1.122 |
stro | -1.118 |
Token | . |
Token ID | 13 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ariat | +0.379 |
rium | +0.366 |
Merit | +0.340 |
anity | +0.331 |
sup | +0.320 |
Neg logit contributions | |
hetical | -0.415 |
sequ | -0.406 |
pneum | -0.392 |
helic | -0.377 |
stro | -0.376 |
Token | I |
Token ID | 314 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
ariat | +0.441 |
rium | +0.428 |
Merit | +0.398 |
anity | +0.390 |
sup | +0.376 |
Neg logit contributions | |
hetical | -0.406 |
sequ | -0.399 |
pneum | -0.382 |
helic | -0.364 |
stro | -0.364 |
Token | think |
Token ID | 892 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
ariat | +0.363 |
rium | +0.351 |
Merit | +0.329 |
anity | +0.321 |
sup | +0.310 |
Neg logit contributions | |
hetical | -0.337 |
sequ | -0.330 |
pneum | -0.317 |
helic | -0.303 |
stro | -0.303 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
hetical | +0.025 |
sequ | +0.025 |
pneum | +0.024 |
helic | +0.023 |
stro | +0.023 |
Neg logit contributions | |
ariat | -0.024 |
rium | -0.023 |
Merit | -0.022 |
anity | -0.021 |
sup | -0.020 |
Token | on |
Token ID | 319 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ariat | +0.722 |
rium | +0.697 |
Merit | +0.651 |
anity | +0.634 |
sup | +0.615 |
Neg logit contributions | |
hetical | -0.712 |
sequ | -0.696 |
pneum | -0.670 |
helic | -0.642 |
stro | -0.642 |
Token | Youtube |
Token ID | 27431 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
hetical | +0.092 |
sequ | +0.090 |
pneum | +0.086 |
helic | +0.082 |
stro | +0.082 |
Neg logit contributions | |
ariat | -0.118 |
rium | -0.114 |
Merit | -0.108 |
anity | -0.105 |
sup | -0.102 |
Token | ? |
Token ID | 30 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
hetical | +0.322 |
sequ | +0.315 |
pneum | +0.298 |
helic | +0.281 |
stro | +0.281 |
Neg logit contributions | |
ariat | -0.529 |
rium | -0.514 |
Merit | -0.485 |
anity | -0.475 |
sup | -0.460 |
Token | No |
Token ID | 1400 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
hetical | +0.820 |
sequ | +0.803 |
pneum | +0.773 |
stro | +0.734 |
helic | +0.732 |
Neg logit contributions | |
ariat | -0.891 |
rium | -0.869 |
Merit | -0.808 |
anity | -0.792 |
sup | -0.755 |
Token | ? |
Token ID | 30 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
hetical | +0.147 |
sequ | +0.144 |
pneum | +0.137 |
stro | +0.128 |
helic | +0.128 |
Neg logit contributions | |
ariat | -0.237 |
rium | -0.231 |
Merit | -0.218 |
anity | -0.213 |
sup | -0.206 |
Token | Well |
Token ID | 3894 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
hetical | +0.525 |
sequ | +0.512 |
pneum | +0.491 |
helic | +0.467 |
stro | +0.467 |
Neg logit contributions | |
ariat | -0.631 |
rium | -0.613 |
Merit | -0.574 |
anity | -0.561 |
sup | -0.540 |
Token | do |
Token ID | 466 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
ariat | +1.203 |
rium | +1.160 |
Merit | +1.077 |
anity | +1.046 |
sup | +1.006 |
Neg logit contributions | |
hetical | -1.368 |
sequ | -1.344 |
pneum | -1.296 |
helic | -1.246 |
stro | -1.243 |
Token | it |
Token ID | 340 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
ariat | +0.281 |
rium | +0.272 |
Merit | +0.252 |
anity | +0.245 |
sup | +0.236 |
Neg logit contributions | |
hetical | -0.321 |
sequ | -0.315 |
pneum | -0.304 |
helic | -0.292 |
stro | -0.291 |
Token | HERE |
Token ID | 15698 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ariat | +0.241 |
rium | +0.233 |
Merit | +0.216 |
anity | +0.210 |
sup | +0.201 |
Neg logit contributions | |
hetical | -0.268 |
sequ | -0.265 |
pneum | -0.254 |
stro | -0.244 |
helic | -0.244 |
Token | !!! |
Token ID | 10185 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
ariat | +0.312 |
rium | +0.301 |
Merit | +0.279 |
anity | +0.271 |
sup | +0.261 |
Neg logit contributions | |
hetical | -0.351 |
sequ | -0.345 |
pneum | -0.333 |
helic | -0.319 |
stro | -0.319 |
Token |
|
Token ID | 198 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
ariat | +0.366 |
rium | +0.355 |
Merit | +0.330 |
anity | +0.321 |
sup | +0.309 |
Neg logit contributions | |
hetical | -0.380 |
sequ | -0.373 |
pneum | -0.359 |
helic | -0.345 |
stro | -0.344 |
Token |
|
Token ID | 198 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
hetical | +0.008 |
sequ | +0.008 |
pneum | +0.007 |
stro | +0.007 |
helic | +0.007 |
Neg logit contributions | |
ariat | -0.008 |
rium | -0.008 |
Merit | -0.007 |
anity | -0.007 |
sup | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ariat | +0.039 |
rium | +0.038 |
Merit | +0.035 |
anity | +0.034 |
sup | +0.033 |
Neg logit contributions | |
hetical | -0.043 |
sequ | -0.042 |
pneum | -0.041 |
stro | -0.039 |
helic | -0.039 |
Token | Ward |
Token ID | 49021 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
ariat | +0.012 |
rium | +0.012 |
Merit | +0.011 |
anity | +0.011 |
sup | +0.010 |
Neg logit contributions | |
hetical | -0.011 |
sequ | -0.010 |
pneum | -0.010 |
stro | -0.010 |
helic | -0.010 |
Token | Breaker |
Token ID | 44478 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
hetical | +0.062 |
sequ | +0.061 |
pneum | +0.059 |
stro | +0.057 |
helic | +0.057 |
Neg logit contributions | |
ariat | -0.046 |
rium | -0.044 |
Merit | -0.040 |
anity | -0.039 |
sup | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
ariat | +1.178 |
rium | +1.134 |
Merit | +1.043 |
anity | +1.016 |
sup | +0.972 |
Neg logit contributions | |
hetical | -1.462 |
sequ | -1.438 |
pneum | -1.390 |
helic | -1.335 |
stro | -1.335 |
Token | Part |
Token ID | 2142 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ariat | +0.048 |
rium | +0.046 |
Merit | +0.043 |
anity | +0.041 |
sup | +0.039 |
Neg logit contributions | |
hetical | -0.065 |
sequ | -0.064 |
pneum | -0.062 |
helic | -0.060 |
stro | -0.059 |
Token | 2 |
Token ID | 362 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
ariat | +0.987 |
rium | +0.940 |
Merit | +0.843 |
anity | +0.809 |
sup | +0.767 |
Neg logit contributions | |
hetical | -1.935 |
sequ | -1.905 |
pneum | -1.852 |
helic | -1.796 |
stro | -1.792 |
Token |
|
Token ID | 198 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
ariat | +0.292 |
rium | +0.281 |
Merit | +0.261 |
anity | +0.254 |
sup | +0.244 |
Neg logit contributions | |
hetical | -0.330 |
sequ | -0.324 |
pneum | -0.313 |
helic | -0.300 |
stro | -0.299 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ariat | +0.142 |
rium | +0.137 |
Merit | +0.127 |
anity | +0.124 |
sup | +0.119 |
Neg logit contributions | |
hetical | -0.158 |
sequ | -0.156 |
pneum | -0.149 |
stro | -0.144 |
helic | -0.142 |
Token | Res |
Token ID | 4965 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
ariat | +0.116 |
rium | +0.112 |
Merit | +0.104 |
anity | +0.102 |
sup | +0.099 |
Neg logit contributions | |
hetical | -0.116 |
sequ | -0.114 |
pneum | -0.110 |
stro | -0.106 |
helic | -0.105 |
Token | a |
Token ID | 64 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
ariat | +0.356 |
rium | +0.339 |
Merit | +0.305 |
anity | +0.293 |
sup | +0.278 |
Neg logit contributions | |
hetical | -0.687 |
sequ | -0.677 |
pneum | -0.658 |
helic | -0.639 |
stro | -0.636 |
Token | efforts |
Token ID | 4040 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
ariat | +0.150 |
rium | +0.146 |
Merit | +0.136 |
anity | +0.132 |
sup | +0.128 |
Neg logit contributions | |
hetical | -0.148 |
sequ | -0.145 |
pneum | -0.140 |
helic | -0.134 |
stro | -0.134 |
Token | and |
Token ID | 290 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
hetical | +0.326 |
sequ | +0.321 |
pneum | +0.307 |
stro | +0.294 |
helic | +0.294 |
Neg logit contributions | |
ariat | -0.327 |
rium | -0.316 |
Merit | -0.294 |
anity | -0.286 |
sup | -0.276 |
Token | judge |
Token ID | 5052 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
hetical | +0.074 |
sequ | +0.072 |
pneum | +0.069 |
helic | +0.066 |
stro | +0.066 |
Neg logit contributions | |
ariat | -0.077 |
rium | -0.074 |
Merit | -0.069 |
anity | -0.068 |
sup | -0.065 |
Token | for |
Token ID | 329 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
ariat | +0.322 |
rium | +0.311 |
Merit | +0.290 |
anity | +0.281 |
sup | +0.269 |
Neg logit contributions | |
hetical | -0.333 |
sequ | -0.329 |
pneum | -0.316 |
helic | -0.302 |
stro | -0.300 |
Token | yourself |
Token ID | 3511 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
hetical | +0.040 |
sequ | +0.039 |
pneum | +0.037 |
helic | +0.036 |
stro | +0.035 |
Neg logit contributions | |
ariat | -0.054 |
rium | -0.052 |
Merit | -0.049 |
anity | -0.048 |
sup | -0.047 |
Token | ... |
Token ID | 986 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
hetical | +0.126 |
sequ | +0.124 |
pneum | +0.119 |
helic | +0.114 |
stro | +0.114 |
Neg logit contributions | |
ariat | -0.108 |
rium | -0.104 |
Merit | -0.097 |
anity | -0.093 |
sup | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
ariat | +1.199 |
rium | +1.158 |
Merit | +1.074 |
anity | +1.044 |
sup | +1.007 |
Neg logit contributions | |
hetical | -1.351 |
sequ | -1.325 |
pneum | -1.278 |
helic | -1.229 |
stro | -1.226 |
Token |
|
Token ID | 198 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
ariat | +0.050 |
rium | +0.048 |
Merit | +0.045 |
anity | +0.044 |
sup | +0.042 |
Neg logit contributions | |
hetical | -0.054 |
sequ | -0.054 |
pneum | -0.051 |
stro | -0.049 |
helic | -0.049 |
Token | This |
Token ID | 1212 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
ariat | +0.033 |
rium | +0.032 |
Merit | +0.029 |
anity | +0.029 |
sup | +0.028 |
Neg logit contributions | |
hetical | -0.032 |
sequ | -0.032 |
pneum | -0.030 |
stro | -0.029 |
helic | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
hetical | +0.062 |
sequ | +0.061 |
pneum | +0.059 |
helic | +0.056 |
stro | +0.056 |
Neg logit contributions | |
ariat | -0.065 |
rium | -0.063 |
Merit | -0.059 |
anity | -0.057 |
sup | -0.055 |
Token | how |
Token ID | 703 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ariat | +0.610 |
rium | +0.590 |
Merit | +0.548 |
anity | +0.534 |
sup | +0.517 |
Neg logit contributions | |
hetical | -0.632 |
sequ | -0.618 |
pneum | -0.596 |
helic | -0.572 |
stro | -0.570 |
Token | . |
Token ID | 13 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
hetical | +0.033 |
sequ | +0.032 |
pneum | +0.031 |
helic | +0.030 |
stro | +0.030 |
Neg logit contributions | |
ariat | -0.029 |
rium | -0.028 |
Merit | -0.026 |
anity | -0.026 |
sup | -0.025 |
Token | The |
Token ID | 383 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
hetical | +0.070 |
sequ | +0.069 |
pneum | +0.066 |
stro | +0.063 |
helic | +0.063 |
Neg logit contributions | |
ariat | -0.072 |
rium | -0.070 |
Merit | -0.065 |
anity | -0.064 |
sup | -0.061 |
Token | gem |
Token ID | 16840 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
ariat | +0.029 |
rium | +0.028 |
Merit | +0.027 |
anity | +0.027 |
sup | +0.026 |
Neg logit contributions | |
hetical | -0.015 |
sequ | -0.015 |
pneum | -0.014 |
helic | -0.013 |
stro | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ariat | +0.233 |
rium | +0.224 |
Merit | +0.213 |
anity | +0.206 |
sup | +0.198 |
Neg logit contributions | |
hetical | -0.242 |
sequ | -0.239 |
pneum | -0.228 |
stro | -0.221 |
helic | -0.218 |
Token | the |
Token ID | 262 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ariat | +0.315 |
rium | +0.300 |
Merit | +0.284 |
anity | +0.274 |
sup | +0.263 |
Neg logit contributions | |
hetical | -0.348 |
sequ | -0.345 |
pneum | -0.330 |
helic | -0.317 |
stro | -0.316 |
Token | collection |
Token ID | 4947 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ariat | +0.460 |
rium | +0.448 |
Merit | +0.430 |
anity | +0.423 |
sup | +0.412 |
Neg logit contributions | |
hetical | -0.158 |
sequ | -0.155 |
pneum | -0.143 |
helic | -0.130 |
stro | -0.129 |
Token | is |
Token ID | 318 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
ariat | +1.434 |
rium | +1.382 |
Merit | +1.280 |
anity | +1.243 |
sup | +1.195 |
Neg logit contributions | |
hetical | -1.718 |
sequ | -1.687 |
pneum | -1.628 |
helic | -1.566 |
stro | -1.563 |
Token | a |
Token ID | 257 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
hetical | +0.066 |
sequ | +0.065 |
pneum | +0.063 |
helic | +0.060 |
stro | +0.060 |
Neg logit contributions | |
ariat | -0.063 |
rium | -0.061 |
Merit | -0.057 |
anity | -0.055 |
sup | -0.053 |
Token | blue |
Token ID | 4171 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ariat | +0.159 |
rium | +0.154 |
Merit | +0.145 |
anity | +0.141 |
sup | +0.137 |
Neg logit contributions | |
hetical | -0.128 |
sequ | -0.126 |
pneum | -0.120 |
helic | -0.115 |
stro | -0.114 |
Token | five |
Token ID | 1936 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
hetical | +0.429 |
sequ | +0.425 |
pneum | +0.407 |
helic | +0.389 |
stro | +0.388 |
Neg logit contributions | |
ariat | -0.460 |
rium | -0.442 |
Merit | -0.417 |
anity | -0.405 |
sup | -0.389 |
Token | - |
Token ID | 12 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
hetical | +0.149 |
sequ | +0.148 |
pneum | +0.141 |
stro | +0.135 |
helic | +0.135 |
Neg logit contributions | |
ariat | -0.154 |
rium | -0.149 |
Merit | -0.140 |
anity | -0.136 |
sup | -0.131 |
Token | an |
Token ID | 281 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ariat | +0.084 |
rium | +0.081 |
Merit | +0.076 |
anity | +0.073 |
sup | +0.070 |
Neg logit contributions | |
hetical | -0.092 |
sequ | -0.091 |
pneum | -0.088 |
helic | -0.084 |
stro | -0.084 |
Token | official |
Token ID | 1743 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
ariat | +0.145 |
rium | +0.141 |
Merit | +0.132 |
anity | +0.129 |
sup | +0.125 |
Neg logit contributions | |
hetical | -0.125 |
sequ | -0.122 |
pneum | -0.117 |
helic | -0.112 |
stro | -0.112 |
Token | number |
Token ID | 1271 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
hetical | +0.520 |
sequ | +0.513 |
pneum | +0.492 |
helic | +0.472 |
stro | +0.471 |
Neg logit contributions | |
ariat | -0.482 |
rium | -0.465 |
Merit | -0.438 |
anity | -0.422 |
sup | -0.405 |
Token | of |
Token ID | 286 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
hetical | +0.084 |
sequ | +0.083 |
pneum | +0.080 |
stro | +0.076 |
helic | +0.076 |
Neg logit contributions | |
ariat | -0.076 |
rium | -0.074 |
Merit | -0.069 |
anity | -0.066 |
sup | -0.064 |
Token | Honey |
Token ID | 21788 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ariat | +0.287 |
rium | +0.277 |
Merit | +0.261 |
anity | +0.251 |
sup | +0.242 |
Neg logit contributions | |
hetical | -0.290 |
sequ | -0.286 |
pneum | -0.274 |
helic | -0.263 |
stro | -0.261 |
Token | comb |
Token ID | 24011 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ariat | +0.191 |
rium | +0.187 |
Merit | +0.178 |
anity | +0.175 |
sup | +0.171 |
Neg logit contributions | |
hetical | -0.088 |
sequ | -0.085 |
pneum | -0.080 |
helic | -0.075 |
stro | -0.074 |
Token | - |
Token ID | 12 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
ariat | +0.859 |
rium | +0.831 |
Merit | +0.774 |
anity | +0.753 |
sup | +0.727 |
Neg logit contributions | |
hetical | -0.891 |
sequ | -0.874 |
pneum | -0.841 |
helic | -0.807 |
stro | -0.805 |
Token | optim |
Token ID | 40085 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ariat | +0.348 |
rium | +0.336 |
Merit | +0.315 |
anity | +0.307 |
sup | +0.298 |
Neg logit contributions | |
hetical | -0.310 |
sequ | -0.303 |
pneum | -0.290 |
stro | -0.279 |
helic | -0.277 |
Token | ized |
Token ID | 1143 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
ariat | +0.954 |
rium | +0.929 |
Merit | +0.880 |
anity | +0.862 |
sup | +0.840 |
Neg logit contributions | |
hetical | -0.559 |
sequ | -0.543 |
pneum | -0.515 |
helic | -0.486 |
stro | -0.485 |
Token | apps |
Token ID | 6725 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
ariat | +0.627 |
rium | +0.606 |
Merit | +0.568 |
anity | +0.551 |
sup | +0.532 |
Neg logit contributions | |
hetical | -0.619 |
sequ | -0.609 |
pneum | -0.585 |
helic | -0.561 |
stro | -0.559 |
Token | . |
Token ID | 13 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
ariat | +0.358 |
rium | +0.346 |
Merit | +0.321 |
anity | +0.310 |
sup | +0.298 |
Neg logit contributions | |
hetical | -0.414 |
sequ | -0.410 |
pneum | -0.392 |
stro | -0.377 |
helic | -0.376 |
Token | a |
Token ID | 257 |
Feature activation | +9.71e-02 |
Pos logit contributions | |
hetical | +0.207 |
sequ | +0.205 |
pneum | +0.196 |
helic | +0.188 |
stro | +0.187 |
Neg logit contributions | |
ariat | -0.218 |
rium | -0.211 |
Merit | -0.198 |
anity | -0.192 |
sup | -0.184 |
Token | great |
Token ID | 1049 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ariat | +0.078 |
rium | +0.076 |
Merit | +0.071 |
anity | +0.069 |
sup | +0.067 |
Neg logit contributions | |
hetical | -0.068 |
sequ | -0.067 |
pneum | -0.064 |
helic | -0.061 |
stro | -0.061 |
Token | effects |
Token ID | 3048 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
hetical | +0.084 |
sequ | +0.083 |
pneum | +0.079 |
helic | +0.076 |
stro | +0.076 |
Neg logit contributions | |
ariat | -0.097 |
rium | -0.093 |
Merit | -0.087 |
anity | -0.085 |
sup | -0.082 |
Token | tool |
Token ID | 2891 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
ariat | +0.103 |
rium | +0.099 |
Merit | +0.094 |
anity | +0.091 |
sup | +0.088 |
Neg logit contributions | |
hetical | -0.089 |
sequ | -0.088 |
pneum | -0.083 |
helic | -0.080 |
stro | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
hetical | +0.362 |
sequ | +0.357 |
pneum | +0.342 |
stro | +0.329 |
helic | +0.328 |
Neg logit contributions | |
ariat | -0.319 |
rium | -0.309 |
Merit | -0.288 |
anity | -0.278 |
sup | -0.267 |
Token | ( |
Token ID | 357 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
hetical | +0.014 |
sequ | +0.014 |
pneum | +0.014 |
helic | +0.013 |
stro | +0.013 |
Neg logit contributions | |
ariat | -0.015 |
rium | -0.014 |
Merit | -0.013 |
anity | -0.013 |
sup | -0.012 |
Token | Free |
Token ID | 11146 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
hetical | +0.133 |
sequ | +0.130 |
pneum | +0.125 |
stro | +0.120 |
helic | +0.119 |
Neg logit contributions | |
ariat | -0.143 |
rium | -0.138 |
Merit | -0.128 |
anity | -0.126 |
sup | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
ariat | +0.098 |
rium | +0.095 |
Merit | +0.089 |
anity | +0.086 |
sup | +0.084 |
Neg logit contributions | |
hetical | -0.094 |
sequ | -0.092 |
pneum | -0.088 |
helic | -0.084 |
stro | -0.084 |
Token | $ |
Token ID | 720 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
hetical | +0.034 |
sequ | +0.033 |
pneum | +0.032 |
helic | +0.031 |
stro | +0.031 |
Neg logit contributions | |
ariat | -0.030 |
rium | -0.029 |
Merit | -0.027 |
anity | -0.027 |
sup | -0.025 |
Token | 3 |
Token ID | 18 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ariat | +0.303 |
rium | +0.288 |
Merit | +0.257 |
anity | +0.248 |
sup | +0.235 |
Neg logit contributions | |
hetical | -0.576 |
sequ | -0.568 |
pneum | -0.551 |
stro | -0.535 |
helic | -0.533 |
Token | . |
Token ID | 13 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
ariat | +0.381 |
rium | +0.368 |
Merit | +0.341 |
anity | +0.331 |
sup | +0.319 |
Neg logit contributions | |
hetical | -0.444 |
sequ | -0.436 |
pneum | -0.421 |
helic | -0.405 |
stro | -0.404 |
Token | or |
Token ID | 273 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
hetical | +0.112 |
sequ | +0.110 |
pneum | +0.106 |
stro | +0.102 |
helic | +0.101 |
Neg logit contributions | |
ariat | -0.103 |
rium | -0.099 |
Merit | -0.092 |
anity | -0.090 |
sup | -0.087 |
Token | take |
Token ID | 1011 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
hetical | +0.041 |
sequ | +0.040 |
pneum | +0.039 |
helic | +0.037 |
stro | +0.037 |
Neg logit contributions | |
ariat | -0.044 |
rium | -0.043 |
Merit | -0.040 |
anity | -0.039 |
sup | -0.038 |
Token | them |
Token ID | 606 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
ariat | +0.046 |
rium | +0.044 |
Merit | +0.041 |
anity | +0.040 |
sup | +0.039 |
Neg logit contributions | |
hetical | -0.044 |
sequ | -0.043 |
pneum | -0.041 |
helic | -0.040 |
stro | -0.040 |
Token | off |
Token ID | 572 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
hetical | +0.258 |
sequ | +0.252 |
pneum | +0.243 |
helic | +0.233 |
stro | +0.232 |
Neg logit contributions | |
ariat | -0.255 |
rium | -0.247 |
Merit | -0.230 |
anity | -0.224 |
sup | -0.217 |
Token | altogether |
Token ID | 13318 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
hetical | +0.647 |
sequ | +0.636 |
pneum | +0.612 |
helic | +0.587 |
stro | +0.587 |
Neg logit contributions | |
ariat | -0.602 |
rium | -0.581 |
Merit | -0.540 |
anity | -0.526 |
sup | -0.507 |
Token | .) |
Token ID | 2014 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ariat | +0.649 |
rium | +0.628 |
Merit | +0.586 |
anity | +0.571 |
sup | +0.552 |
Neg logit contributions | |
hetical | -0.651 |
sequ | -0.637 |
pneum | -0.613 |
helic | -0.588 |
stro | -0.587 |
Token | If |
Token ID | 1002 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
hetical | +0.166 |
sequ | +0.163 |
pneum | +0.157 |
helic | +0.150 |
stro | +0.150 |
Neg logit contributions | |
ariat | -0.175 |
rium | -0.170 |
Merit | -0.158 |
anity | -0.154 |
sup | -0.149 |
Token | they |
Token ID | 484 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
hetical | +0.341 |
sequ | +0.336 |
pneum | +0.325 |
stro | +0.312 |
helic | +0.311 |
Neg logit contributions | |
ariat | -0.314 |
rium | -0.304 |
Merit | -0.281 |
anity | -0.273 |
sup | -0.263 |
Token | want |
Token ID | 765 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
hetical | +0.020 |
sequ | +0.020 |
pneum | +0.019 |
helic | +0.018 |
stro | +0.018 |
Neg logit contributions | |
ariat | -0.027 |
rium | -0.026 |
Merit | -0.025 |
anity | -0.024 |
sup | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
hetical | +0.134 |
sequ | +0.131 |
pneum | +0.127 |
helic | +0.121 |
stro | +0.121 |
Neg logit contributions | |
ariat | -0.131 |
rium | -0.127 |
Merit | -0.118 |
anity | -0.115 |
sup | -0.111 |
Token | show |
Token ID | 905 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
ariat | +0.237 |
rium | +0.229 |
Merit | +0.214 |
anity | +0.208 |
sup | +0.201 |
Neg logit contributions | |
hetical | -0.236 |
sequ | -0.232 |
pneum | -0.223 |
helic | -0.213 |
stro | -0.213 |
Token | literally |
Token ID | 7360 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
ariat | +0.184 |
rium | +0.179 |
Merit | +0.167 |
anity | +0.162 |
sup | +0.155 |
Neg logit contributions | |
hetical | -0.175 |
sequ | -0.173 |
pneum | -0.165 |
stro | -0.158 |
helic | -0.157 |
Token | terrified |
Token ID | 22144 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ariat | +0.037 |
rium | +0.036 |
Merit | +0.034 |
anity | +0.033 |
sup | +0.031 |
Neg logit contributions | |
hetical | -0.036 |
sequ | -0.035 |
pneum | -0.034 |
stro | -0.032 |
helic | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
ariat | +0.794 |
rium | +0.767 |
Merit | +0.714 |
anity | +0.694 |
sup | +0.670 |
Neg logit contributions | |
hetical | -0.854 |
sequ | -0.838 |
pneum | -0.807 |
helic | -0.775 |
stro | -0.773 |
Token | as |
Token ID | 355 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
ariat | +0.034 |
rium | +0.033 |
Merit | +0.031 |
anity | +0.030 |
sup | +0.029 |
Neg logit contributions | |
hetical | -0.031 |
sequ | -0.031 |
pneum | -0.030 |
helic | -0.028 |
stro | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
hetical | +0.072 |
sequ | +0.070 |
pneum | +0.068 |
stro | +0.065 |
helic | +0.065 |
Neg logit contributions | |
ariat | -0.079 |
rium | -0.076 |
Merit | -0.072 |
anity | -0.069 |
sup | -0.067 |
Token | result |
Token ID | 1255 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
ariat | +0.130 |
rium | +0.126 |
Merit | +0.118 |
anity | +0.115 |
sup | +0.111 |
Neg logit contributions | |
hetical | -0.118 |
sequ | -0.116 |
pneum | -0.112 |
helic | -0.107 |
stro | -0.106 |
Token | cooper |
Token ID | 6788 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ariat | +0.275 |
rium | +0.267 |
Merit | +0.248 |
anity | +0.242 |
sup | +0.232 |
Neg logit contributions | |
hetical | -0.267 |
sequ | -0.262 |
pneum | -0.252 |
stro | -0.241 |
helic | -0.241 |
Token | ated |
Token ID | 515 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
hetical | +0.217 |
sequ | +0.211 |
pneum | +0.202 |
stro | +0.193 |
helic | +0.192 |
Neg logit contributions | |
ariat | -0.254 |
rium | -0.245 |
Merit | -0.233 |
anity | -0.225 |
sup | -0.219 |
Token | with |
Token ID | 351 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ariat | +0.002 |
rium | +0.002 |
Merit | +0.002 |
anity | +0.002 |
sup | +0.002 |
Neg logit contributions | |
hetical | -0.002 |
sequ | -0.002 |
pneum | -0.002 |
helic | -0.002 |
stro | -0.002 |
Token | whatever |
Token ID | 4232 |
Feature activation | -9.56e-03 |
Pos logit contributions | |
hetical | +0.101 |
sequ | +0.100 |
pneum | +0.097 |
helic | +0.093 |
stro | +0.092 |
Neg logit contributions | |
ariat | -0.086 |
rium | -0.082 |
Merit | -0.077 |
anity | -0.074 |
sup | -0.071 |
Token | he |
Token ID | 339 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
hetical | +0.008 |
sequ | +0.007 |
pneum | +0.007 |
helic | +0.007 |
stro | +0.007 |
Neg logit contributions | |
ariat | -0.007 |
rium | -0.006 |
Merit | -0.006 |
anity | -0.006 |
sup | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
ariat | +0.171 |
rium | +0.166 |
Merit | +0.154 |
anity | +0.151 |
sup | +0.145 |
Neg logit contributions | |
hetical | -0.164 |
sequ | -0.161 |
pneum | -0.154 |
helic | -0.148 |
stro | -0.148 |
Token | music |
Token ID | 2647 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
ariat | +0.033 |
rium | +0.031 |
Merit | +0.029 |
anity | +0.028 |
sup | +0.026 |
Neg logit contributions | |
hetical | -0.050 |
sequ | -0.050 |
pneum | -0.048 |
stro | -0.046 |
helic | -0.046 |
Token | box |
Token ID | 3091 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
hetical | +0.628 |
sequ | +0.613 |
pneum | +0.589 |
helic | +0.565 |
stro | +0.564 |
Neg logit contributions | |
ariat | -0.674 |
rium | -0.653 |
Merit | -0.610 |
anity | -0.594 |
sup | -0.577 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e-03 |
Pos logit contributions | |
hetical | +0.107 |
sequ | +0.106 |
pneum | +0.101 |
stro | +0.098 |
helic | +0.096 |
Neg logit contributions | |
ariat | -0.092 |
rium | -0.089 |
Merit | -0.081 |
anity | -0.080 |
merce | -0.077 |
Token | involving |
Token ID | 7411 |
Feature activation | -9.95e-02 |
Pos logit contributions | |
hetical | +0.002 |
sequ | +0.002 |
pneum | +0.002 |
helic | +0.002 |
stro | +0.002 |
Neg logit contributions | |
ariat | -0.002 |
rium | -0.002 |
Merit | -0.002 |
anity | -0.002 |
sup | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
hetical | +0.080 |
sequ | +0.078 |
pneum | +0.075 |
stro | +0.072 |
helic | +0.072 |
Neg logit contributions | |
ariat | -0.069 |
rium | -0.067 |
Merit | -0.062 |
anity | -0.060 |
sup | -0.058 |
Token | entire |
Token ID | 2104 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ariat | +0.025 |
rium | +0.024 |
Merit | +0.022 |
anity | +0.022 |
sup | +0.021 |
Neg logit contributions | |
hetical | -0.023 |
sequ | -0.022 |
pneum | -0.022 |
helic | -0.021 |
stro | -0.021 |
Token | palm |
Token ID | 18057 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ariat | +0.198 |
rium | +0.192 |
Merit | +0.180 |
anity | +0.176 |
sup | +0.172 |
Neg logit contributions | |
hetical | -0.162 |
sequ | -0.158 |
pneum | -0.152 |
helic | -0.145 |
stro | -0.145 |
Token | opl |
Token ID | 20106 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
ariat | +0.042 |
rium | +0.039 |
Merit | +0.032 |
anity | +0.030 |
sup | +0.027 |
Neg logit contributions | |
hetical | -0.168 |
sequ | -0.166 |
pneum | -0.162 |
stro | -0.158 |
helic | -0.158 |
Token | ant |
Token ID | 415 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
hetical | +0.639 |
sequ | +0.630 |
pneum | +0.607 |
stro | +0.590 |
helic | +0.583 |
Neg logit contributions | |
ariat | -0.340 |
rium | -0.327 |
Merit | -0.297 |
anity | -0.281 |
sup | -0.267 |
Token | ar |
Token ID | 283 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
hetical | +0.522 |
sequ | +0.512 |
pneum | +0.493 |
stro | +0.484 |
actionDate | +0.475 |
Neg logit contributions | |
ariat | -0.265 |
rium | -0.256 |
Merit | -0.238 |
anity | -0.225 |
sup | -0.213 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
hetical | +0.078 |
sequ | +0.076 |
pneum | +0.073 |
helic | +0.070 |
stro | +0.070 |
Neg logit contributions | |
ariat | -0.098 |
rium | -0.095 |
Merit | -0.089 |
anity | -0.087 |
sup | -0.084 |
Token | to |
Token ID | 284 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ariat | +0.119 |
rium | +0.115 |
Merit | +0.108 |
anity | +0.105 |
sup | +0.101 |
Neg logit contributions | |
hetical | -0.116 |
sequ | -0.114 |
pneum | -0.109 |
helic | -0.104 |
stro | -0.104 |
Token | be |
Token ID | 307 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
hetical | +0.151 |
sequ | +0.148 |
pneum | +0.142 |
helic | +0.135 |
stro | +0.135 |
Neg logit contributions | |
ariat | -0.173 |
rium | -0.167 |
Merit | -0.157 |
anity | -0.153 |
sup | -0.148 |
Token | said |
Token ID | 531 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
hetical | +0.077 |
sequ | +0.076 |
pneum | +0.072 |
helic | +0.069 |
stro | +0.069 |
Neg logit contributions | |
ariat | -0.094 |
rium | -0.091 |
Merit | -0.085 |
anity | -0.083 |
sup | -0.080 |
Token | too |
Token ID | 1165 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
hetical | +0.343 |
sequ | +0.337 |
pneum | +0.324 |
stro | +0.309 |
helic | +0.308 |
Neg logit contributions | |
ariat | -0.329 |
rium | -0.316 |
Merit | -0.295 |
anity | -0.286 |
sup | -0.276 |
Token | about |
Token ID | 546 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
hetical | +0.596 |
sequ | +0.587 |
pneum | +0.565 |
stro | +0.539 |
helic | +0.539 |
Neg logit contributions | |
ariat | -0.540 |
rium | -0.519 |
Merit | -0.482 |
anity | -0.467 |
sup | -0.450 |
Token | what |
Token ID | 644 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
hetical | +0.422 |
sequ | +0.415 |
pneum | +0.400 |
helic | +0.382 |
stro | +0.381 |
Neg logit contributions | |
ariat | -0.419 |
rium | -0.407 |
Merit | -0.380 |
anity | -0.367 |
sup | -0.354 |
Token | Phil |
Token ID | 4543 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
hetical | +0.166 |
sequ | +0.163 |
pneum | +0.157 |
stro | +0.150 |
helic | +0.150 |
Neg logit contributions | |
ariat | -0.164 |
rium | -0.158 |
Merit | -0.148 |
anity | -0.143 |
sup | -0.138 |
Token | adel |
Token ID | 6959 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
hetical | +0.490 |
sequ | +0.479 |
pneum | +0.461 |
stro | +0.443 |
helic | +0.441 |
Neg logit contributions | |
ariat | -0.492 |
rium | -0.477 |
Merit | -0.444 |
anity | -0.431 |
sup | -0.418 |
Token | ph |
Token ID | 746 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
hetical | +0.230 |
sequ | +0.226 |
pneum | +0.219 |
stro | +0.212 |
helic | +0.209 |
Neg logit contributions | |
ariat | -0.161 |
rium | -0.154 |
Merit | -0.142 |
anity | -0.137 |
sup | -0.132 |
Token | ians |
Token ID | 1547 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
hetical | +0.181 |
sequ | +0.178 |
pneum | +0.174 |
stro | +0.168 |
helic | +0.168 |
Neg logit contributions | |
ariat | -0.090 |
rium | -0.086 |
Merit | -0.077 |
anity | -0.073 |
sup | -0.069 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
hetical | +0.137 |
sequ | +0.136 |
pneum | +0.131 |
stro | +0.128 |
helic | +0.128 |
Neg logit contributions | |
ariat | -0.062 |
rium | -0.058 |
Merit | -0.051 |
anity | -0.049 |
sup | -0.046 |
Token | frame |
Token ID | 5739 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
hetical | +0.102 |
sequ | +0.101 |
pneum | +0.096 |
helic | +0.092 |
stro | +0.091 |
Neg logit contributions | |
ariat | -0.117 |
rium | -0.113 |
Merit | -0.106 |
anity | -0.104 |
sup | -0.100 |
Token | causes |
Token ID | 5640 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
hetical | +1.228 |
sequ | +1.226 |
pneum | +1.160 |
helic | +1.120 |
stro | +1.119 |
Neg logit contributions | |
ariat | -1.211 |
rium | -1.173 |
Merit | -1.093 |
anity | -1.062 |
sup | -0.993 |
Token | huge |
Token ID | 3236 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
hetical | +0.707 |
sequ | +0.694 |
pneum | +0.662 |
helic | +0.641 |
stro | +0.632 |
Neg logit contributions | |
ariat | -0.767 |
rium | -0.740 |
Merit | -0.692 |
anity | -0.672 |
sup | -0.646 |
Token | matchup |
Token ID | 18406 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
ariat | +0.486 |
rium | +0.471 |
Merit | +0.439 |
anity | +0.427 |
sup | +0.410 |
Neg logit contributions | |
hetical | -0.462 |
sequ | -0.455 |
pneum | -0.435 |
helic | -0.419 |
stro | -0.415 |
Token | problems |
Token ID | 2761 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
hetical | +0.062 |
sequ | +0.061 |
pneum | +0.058 |
stro | +0.055 |
helic | +0.055 |
Neg logit contributions | |
ariat | -0.081 |
rium | -0.079 |
Merit | -0.074 |
anity | -0.072 |
sup | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
hetical | +0.614 |
sequ | +0.610 |
pneum | +0.580 |
stro | +0.558 |
helic | +0.557 |
Neg logit contributions | |
ariat | -0.578 |
rium | -0.559 |
Merit | -0.520 |
anity | -0.504 |
sup | -0.481 |
Token | provides |
Token ID | 3769 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
hetical | +0.051 |
sequ | +0.050 |
pneum | +0.048 |
helic | +0.047 |
stro | +0.046 |
Neg logit contributions | |
ariat | -0.051 |
rium | -0.049 |
Merit | -0.046 |
anity | -0.045 |
sup | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
hetical | +0.613 |
sequ | +0.601 |
pneum | +0.575 |
helic | +0.553 |
stro | +0.547 |
Neg logit contributions | |
ariat | -0.690 |
rium | -0.666 |
Merit | -0.624 |
anity | -0.608 |
sup | -0.582 |
Token | red |
Token ID | 2266 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
ariat | +0.088 |
rium | +0.086 |
Merit | +0.081 |
anity | +0.079 |
sup | +0.076 |
Neg logit contributions | |
hetical | -0.069 |
sequ | -0.067 |
pneum | -0.064 |
helic | -0.061 |
stro | -0.061 |
Token | zone |
Token ID | 6516 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
hetical | +0.435 |
sequ | +0.428 |
pneum | +0.411 |
helic | +0.396 |
stro | +0.396 |
Neg logit contributions | |
ariat | -0.351 |
rium | -0.339 |
Merit | -0.314 |
anity | -0.302 |
sup | -0.290 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ariat | +0.333 |
rium | +0.322 |
Merit | +0.299 |
anity | +0.291 |
sup | +0.281 |
Neg logit contributions | |
hetical | -0.359 |
sequ | -0.352 |
pneum | -0.338 |
stro | -0.325 |
helic | -0.325 |
Token |
|
Token ID | 198 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ariat | +0.203 |
rium | +0.196 |
Merit | +0.181 |
anity | +0.177 |
sup | +0.170 |
Neg logit contributions | |
hetical | -0.231 |
sequ | -0.227 |
pneum | -0.218 |
stro | -0.210 |
helic | -0.209 |
Token | So |
Token ID | 2396 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ariat | +0.079 |
rium | +0.076 |
Merit | +0.070 |
anity | +0.069 |
sup | +0.067 |
Neg logit contributions | |
hetical | -0.071 |
sequ | -0.070 |
pneum | -0.067 |
stro | -0.064 |
helic | -0.063 |
Token | why |
Token ID | 1521 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
ariat | +0.089 |
rium | +0.086 |
Merit | +0.080 |
anity | +0.077 |
sup | +0.075 |
Neg logit contributions | |
hetical | -0.095 |
sequ | -0.093 |
pneum | -0.089 |
helic | -0.086 |
stro | -0.086 |
Token | is |
Token ID | 318 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
hetical | +0.301 |
sequ | +0.294 |
pneum | +0.284 |
helic | +0.272 |
stro | +0.271 |
Neg logit contributions | |
ariat | -0.302 |
rium | -0.292 |
Merit | -0.272 |
anity | -0.265 |
sup | -0.257 |
Token | Re |
Token ID | 797 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
ariat | +0.065 |
rium | +0.063 |
Merit | +0.059 |
anity | +0.057 |
sup | +0.055 |
Neg logit contributions | |
hetical | -0.062 |
sequ | -0.061 |
pneum | -0.059 |
helic | -0.056 |
stro | -0.056 |
Token | es |
Token ID | 274 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
hetical | +0.733 |
sequ | +0.717 |
pneum | +0.685 |
stro | +0.660 |
helic | +0.657 |
Neg logit contributions | |
ariat | -0.708 |
rium | -0.693 |
Merit | -0.639 |
anity | -0.618 |
sup | -0.606 |
Token | - |
Token ID | 12 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
hetical | +0.745 |
sequ | +0.733 |
pneum | +0.701 |
stro | +0.676 |
helic | +0.672 |
Neg logit contributions | |
ariat | -0.770 |
rium | -0.745 |
Merit | -0.690 |
anity | -0.672 |
sup | -0.653 |
Token | Jones |
Token ID | 25784 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
hetical | +0.179 |
sequ | +0.175 |
pneum | +0.169 |
helic | +0.163 |
stro | +0.163 |
Neg logit contributions | |
ariat | -0.142 |
rium | -0.137 |
Merit | -0.127 |
anity | -0.123 |
sup | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ariat | +0.273 |
rium | +0.265 |
Merit | +0.248 |
anity | +0.241 |
sup | +0.234 |
Neg logit contributions | |
hetical | -0.255 |
sequ | -0.249 |
pneum | -0.240 |
helic | -0.229 |
stro | -0.229 |
Token | who |
Token ID | 508 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ariat | +0.251 |
rium | +0.243 |
Merit | +0.226 |
anity | +0.220 |
sup | +0.213 |
Neg logit contributions | |
hetical | -0.260 |
sequ | -0.255 |
pneum | -0.246 |
helic | -0.236 |
stro | -0.235 |
Token | aren |
Token ID | 3588 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ariat | +0.254 |
rium | +0.246 |
Merit | +0.230 |
anity | +0.224 |
sup | +0.217 |
Neg logit contributions | |
hetical | -0.223 |
sequ | -0.219 |
pneum | -0.209 |
helic | -0.200 |
stro | -0.200 |
Token | 't |
Token ID | 470 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
hetical | +0.162 |
sequ | +0.159 |
pneum | +0.152 |
stro | +0.146 |
helic | +0.144 |
Neg logit contributions | |
ariat | -0.179 |
rium | -0.174 |
Merit | -0.162 |
anity | -0.159 |
sup | -0.153 |
Token | completely |
Token ID | 3190 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ariat | +0.196 |
rium | +0.190 |
Merit | +0.177 |
anity | +0.173 |
sup | +0.166 |
Neg logit contributions | |
hetical | -0.187 |
sequ | -0.183 |
pneum | -0.176 |
helic | -0.168 |
stro | -0.168 |
Token | off |
Token ID | 572 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
hetical | +0.239 |
sequ | +0.236 |
pneum | +0.227 |
stro | +0.216 |
helic | +0.216 |
Neg logit contributions | |
ariat | -0.242 |
rium | -0.237 |
Merit | -0.220 |
anity | -0.214 |
sup | -0.204 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
hetical | +0.073 |
sequ | +0.072 |
pneum | +0.069 |
stro | +0.066 |
helic | +0.066 |
Neg logit contributions | |
ariat | -0.064 |
rium | -0.062 |
Merit | -0.058 |
anity | -0.057 |
sup | -0.054 |
Token | radar |
Token ID | 13428 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
hetical | +0.087 |
sequ | +0.085 |
pneum | +0.081 |
helic | +0.078 |
stro | +0.078 |
Neg logit contributions | |
ariat | -0.097 |
rium | -0.094 |
Merit | -0.088 |
anity | -0.086 |
sup | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
hetical | +0.454 |
sequ | +0.450 |
pneum | +0.431 |
stro | +0.415 |
helic | +0.414 |
Neg logit contributions | |
ariat | -0.412 |
rium | -0.400 |
Merit | -0.376 |
anity | -0.364 |
sup | -0.346 |
Token |
|
Token ID | 198 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
ariat | +0.094 |
rium | +0.091 |
Merit | +0.085 |
anity | +0.083 |
sup | +0.080 |
Neg logit contributions | |
hetical | -0.096 |
sequ | -0.094 |
pneum | -0.090 |
stro | -0.086 |
helic | -0.086 |
Token |
|
Token ID | 198 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
ariat | +0.049 |
rium | +0.047 |
Merit | +0.043 |
anity | +0.042 |
sup | +0.041 |
Neg logit contributions | |
hetical | -0.054 |
sequ | -0.053 |
pneum | -0.051 |
stro | -0.049 |
helic | -0.048 |
Token | In |
Token ID | 818 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
hetical | +0.003 |
sequ | +0.003 |
pneum | +0.003 |
stro | +0.003 |
helic | +0.003 |
Neg logit contributions | |
ariat | -0.004 |
rium | -0.004 |
Merit | -0.003 |
anity | -0.003 |
sup | -0.003 |
Token | May |
Token ID | 1737 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
ariat | +0.252 |
rium | +0.243 |
Merit | +0.227 |
anity | +0.220 |
sup | +0.212 |
Neg logit contributions | |
hetical | -0.265 |
sequ | -0.260 |
pneum | -0.250 |
stro | -0.240 |
helic | -0.240 |
Token | real |
Token ID | 1103 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ariat | +0.163 |
rium | +0.159 |
Merit | +0.149 |
anity | +0.145 |
sup | +0.142 |
Neg logit contributions | |
hetical | -0.136 |
sequ | -0.132 |
pneum | -0.127 |
helic | -0.121 |
stro | -0.121 |
Token | - |
Token ID | 12 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ariat | +0.154 |
rium | +0.149 |
Merit | +0.139 |
anity | +0.135 |
sup | +0.131 |
Neg logit contributions | |
hetical | -0.146 |
sequ | -0.142 |
pneum | -0.137 |
helic | -0.131 |
stro | -0.131 |
Token | time |
Token ID | 2435 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
ariat | +0.089 |
rium | +0.086 |
Merit | +0.080 |
anity | +0.077 |
sup | +0.075 |
Neg logit contributions | |
hetical | -0.104 |
sequ | -0.103 |
pneum | -0.099 |
stro | -0.095 |
helic | -0.095 |
Token | / |
Token ID | 1220 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
ariat | +0.303 |
rium | +0.294 |
Merit | +0.275 |
anity | +0.269 |
sup | +0.261 |
Neg logit contributions | |
hetical | -0.257 |
sequ | -0.250 |
pneum | -0.240 |
helic | -0.230 |
stro | -0.229 |
Token | streaming |
Token ID | 11305 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
ariat | +0.402 |
rium | +0.389 |
Merit | +0.365 |
anity | +0.356 |
sup | +0.345 |
Neg logit contributions | |
hetical | -0.346 |
sequ | -0.339 |
pneum | -0.324 |
helic | -0.310 |
stro | -0.309 |
Token | analytics |
Token ID | 23696 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
hetical | +0.033 |
sequ | +0.032 |
pneum | +0.031 |
helic | +0.029 |
stro | +0.029 |
Neg logit contributions | |
ariat | -0.037 |
rium | -0.036 |
Merit | -0.034 |
anity | -0.033 |
sup | -0.032 |
Token | version |
Token ID | 2196 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
hetical | +0.445 |
sequ | +0.438 |
pneum | +0.418 |
helic | +0.399 |
stro | +0.398 |
Neg logit contributions | |
ariat | -0.497 |
rium | -0.481 |
Merit | -0.454 |
anity | -0.440 |
sup | -0.424 |
Token | . |
Token ID | 13 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
ariat | +0.018 |
rium | +0.017 |
Merit | +0.016 |
anity | +0.016 |
sup | +0.015 |
Neg logit contributions | |
hetical | -0.018 |
sequ | -0.017 |
pneum | -0.017 |
stro | -0.016 |
helic | -0.016 |
Token | It |
Token ID | 632 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
ariat | +0.273 |
rium | +0.264 |
Merit | +0.247 |
anity | +0.241 |
sup | +0.233 |
Neg logit contributions | |
hetical | -0.255 |
sequ | -0.250 |
pneum | -0.240 |
helic | -0.230 |
stro | -0.230 |
Token | � |
Token ID | 447 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
hetical | +0.041 |
sequ | +0.041 |
pneum | +0.039 |
stro | +0.037 |
helic | +0.037 |
Neg logit contributions | |
ariat | -0.037 |
rium | -0.036 |
Merit | -0.034 |
anity | -0.033 |
sup | -0.031 |
Token | � |
Token ID | 247 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ariat | +0.152 |
rium | +0.147 |
Merit | +0.139 |
anity | +0.136 |
sup | +0.132 |
Neg logit contributions | |
hetical | -0.101 |
sequ | -0.098 |
pneum | -0.093 |
helic | -0.088 |
stro | -0.088 |
Token | The |
Token ID | 383 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ariat | +0.260 |
rium | +0.252 |
Merit | +0.235 |
anity | +0.230 |
sup | +0.221 |
Neg logit contributions | |
hetical | -0.236 |
sequ | -0.231 |
pneum | -0.221 |
stro | -0.212 |
helic | -0.210 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
ariat | +0.445 |
rium | +0.434 |
Merit | +0.412 |
anity | +0.404 |
sup | +0.395 |
Neg logit contributions | |
hetical | -0.233 |
sequ | -0.225 |
pneum | -0.214 |
helic | -0.202 |
stro | -0.200 |
Token | 8 |
Token ID | 807 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
hetical | +0.739 |
sequ | +0.730 |
pneum | +0.711 |
stro | +0.687 |
actionDate | +0.674 |
Neg logit contributions | |
ariat | -0.445 |
rium | -0.428 |
Merit | -0.382 |
anity | -0.372 |
merce | -0.353 |
Token | of |
Token ID | 286 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ariat | +0.412 |
rium | +0.399 |
Merit | +0.372 |
anity | +0.362 |
sup | +0.351 |
Neg logit contributions | |
hetical | -0.406 |
sequ | -0.398 |
pneum | -0.383 |
helic | -0.367 |
stro | -0.366 |
Token | 15 |
Token ID | 1315 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ariat | +0.226 |
rium | +0.219 |
Merit | +0.201 |
anity | +0.196 |
sup | +0.187 |
Neg logit contributions | |
hetical | -0.290 |
sequ | -0.285 |
pneum | -0.275 |
stro | -0.265 |
helic | -0.264 |
Token | Photo |
Token ID | 5555 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
ariat | +0.531 |
rium | +0.514 |
Merit | +0.477 |
anity | +0.465 |
sup | +0.448 |
Neg logit contributions | |
hetical | -0.554 |
sequ | -0.544 |
pneum | -0.523 |
helic | -0.501 |
stro | -0.501 |
Token | : |
Token ID | 25 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
hetical | +1.852 |
sequ | +1.836 |
pneum | +1.726 |
stro | +1.678 |
──── | +1.633 |
Neg logit contributions | |
ariat | -2.188 |
rium | -2.116 |
Merit | -1.971 |
anity | -1.951 |
merce | -1.900 |
Token | Le |
Token ID | 1004 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
ariat | +0.460 |
rium | +0.445 |
Merit | +0.416 |
anity | +0.405 |
sup | +0.391 |
Neg logit contributions | |
hetical | -0.444 |
sequ | -0.435 |
pneum | -0.418 |
helic | -0.401 |
stro | -0.400 |
Token | a |
Token ID | 64 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
ariat | +0.198 |
rium | +0.189 |
Merit | +0.170 |
anity | +0.163 |
sup | +0.155 |
Neg logit contributions | |
hetical | -0.370 |
sequ | -0.364 |
pneum | -0.353 |
stro | -0.342 |
helic | -0.341 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
ariat | +0.081 |
rium | +0.079 |
Merit | +0.075 |
anity | +0.074 |
sup | +0.072 |
Neg logit contributions | |
hetical | -0.047 |
sequ | -0.046 |
pneum | -0.043 |
helic | -0.041 |
stro | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ariat | +0.531 |
rium | +0.512 |
Merit | +0.469 |
anity | +0.457 |
sup | +0.437 |
Neg logit contributions | |
hetical | -0.670 |
sequ | -0.660 |
pneum | -0.635 |
stro | -0.612 |
helic | -0.609 |
Token | Hide |
Token ID | 10415 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
hetical | +0.257 |
sequ | +0.253 |
pneum | +0.245 |
stro | +0.237 |
helic | +0.236 |
Neg logit contributions | |
ariat | -0.159 |
rium | -0.152 |
Merit | -0.138 |
anity | -0.134 |
sup | -0.127 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
hetical | +1.159 |
sequ | +1.132 |
pneum | +1.076 |
stro | +1.017 |
helic | +1.016 |
Neg logit contributions | |
ariat | -1.723 |
rium | -1.677 |
Merit | -1.582 |
anity | -1.551 |
sup | -1.503 |
Token | 13 |
Token ID | 1511 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
sequ | +2.659 |
hetical | +2.648 |
pneum | +2.495 |
stro | +2.448 |
helic | +2.389 |
Neg logit contributions | |
ariat | -2.195 |
rium | -2.137 |
Merit | -1.974 |
anity | -1.943 |
merce | -1.870 |
Token | of |
Token ID | 286 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
hetical | +0.295 |
sequ | +0.290 |
pneum | +0.277 |
stro | +0.265 |
helic | +0.262 |
Neg logit contributions | |
ariat | -0.317 |
rium | -0.307 |
Merit | -0.286 |
anity | -0.280 |
sup | -0.269 |
Token | 15 |
Token ID | 1315 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
hetical | +0.282 |
sequ | +0.279 |
pneum | +0.267 |
stro | +0.258 |
helic | +0.256 |
Neg logit contributions | |
ariat | -0.229 |
rium | -0.222 |
Merit | -0.203 |
anity | -0.199 |
sup | -0.189 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
hetical | +0.047 |
sequ | +0.046 |
pneum | +0.043 |
stro | +0.041 |
helic | +0.040 |
Neg logit contributions | |
ariat | -0.092 |
rium | -0.089 |
Merit | -0.084 |
anity | -0.083 |
sup | -0.081 |
Token | : |
Token ID | 25 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
hetical | +2.250 |
sequ | +2.231 |
pneum | +2.074 |
stro | +2.029 |
──── | +1.966 |
Neg logit contributions | |
ariat | -2.854 |
rium | -2.771 |
merce | -2.607 |
Merit | -2.564 |
anity | -2.562 |
Token | Carly |
Token ID | 35982 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
hetical | +0.635 |
sequ | +0.623 |
pneum | +0.600 |
stro | +0.576 |
helic | +0.574 |
Neg logit contributions | |
ariat | -0.558 |
rium | -0.540 |
Merit | -0.498 |
anity | -0.486 |
sup | -0.466 |
Token | Fiorina |
Token ID | 49028 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
hetical | +0.156 |
sequ | +0.154 |
pneum | +0.148 |
stro | +0.143 |
helic | +0.142 |
Neg logit contributions | |
ariat | -0.121 |
rium | -0.117 |
Merit | -0.107 |
anity | -0.104 |
sup | -0.100 |
Token | 's |
Token ID | 338 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
hetical | +0.039 |
sequ | +0.038 |
pneum | +0.037 |
stro | +0.035 |
helic | +0.035 |
Neg logit contributions | |
ariat | -0.043 |
rium | -0.041 |
Merit | -0.039 |
anity | -0.038 |
sup | -0.037 |
Token | political |
Token ID | 1964 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
hetical | +0.449 |
sequ | +0.439 |
pneum | +0.421 |
stro | +0.399 |
helic | +0.399 |
Neg logit contributions | |
ariat | -0.587 |
rium | -0.572 |
Merit | -0.538 |
anity | -0.525 |
sup | -0.507 |
Token | ." |
Token ID | 526 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
hetical | +0.266 |
sequ | +0.259 |
pneum | +0.249 |
helic | +0.238 |
stro | +0.237 |
Neg logit contributions | |
ariat | -0.318 |
rium | -0.308 |
Merit | -0.290 |
anity | -0.282 |
sup | -0.274 |
Token |
|
Token ID | 198 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
hetical | +0.146 |
sequ | +0.144 |
pneum | +0.138 |
helic | +0.133 |
stro | +0.133 |
Neg logit contributions | |
ariat | -0.136 |
rium | -0.132 |
Merit | -0.122 |
anity | -0.119 |
sup | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
hetical | +0.056 |
sequ | +0.055 |
pneum | +0.053 |
stro | +0.051 |
helic | +0.051 |
Neg logit contributions | |
ariat | -0.050 |
rium | -0.048 |
Merit | -0.045 |
anity | -0.044 |
sup | -0.042 |
Token | For |
Token ID | 1890 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
hetical | +0.136 |
sequ | +0.133 |
pneum | +0.127 |
stro | +0.123 |
helic | +0.121 |
Neg logit contributions | |
ariat | -0.151 |
rium | -0.146 |
Merit | -0.135 |
anity | -0.133 |
sup | -0.129 |
Token | some |
Token ID | 617 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
hetical | +0.346 |
sequ | +0.340 |
pneum | +0.327 |
stro | +0.313 |
helic | +0.313 |
Neg logit contributions | |
ariat | -0.348 |
rium | -0.336 |
Merit | -0.314 |
anity | -0.305 |
sup | -0.294 |
Token | actors |
Token ID | 10544 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
hetical | +0.517 |
sequ | +0.509 |
pneum | +0.490 |
helic | +0.473 |
stro | +0.473 |
Neg logit contributions | |
ariat | -0.426 |
rium | -0.414 |
Merit | -0.381 |
anity | -0.365 |
sup | -0.352 |
Token | , |
Token ID | 11 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
hetical | +1.999 |
sequ | +1.971 |
pneum | +1.882 |
stro | +1.811 |
helic | +1.806 |
Neg logit contributions | |
ariat | -1.817 |
rium | -1.775 |
Merit | -1.629 |
anity | -1.568 |
sup | -1.512 |
Token | like |
Token ID | 588 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
hetical | +0.255 |
sequ | +0.251 |
pneum | +0.241 |
helic | +0.232 |
stro | +0.231 |
Neg logit contributions | |
ariat | -0.240 |
rium | -0.232 |
Merit | -0.216 |
anity | -0.209 |
sup | -0.202 |
Token | Ford |
Token ID | 8092 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
hetical | +0.325 |
sequ | +0.321 |
pneum | +0.307 |
helic | +0.295 |
stro | +0.293 |
Neg logit contributions | |
ariat | -0.334 |
rium | -0.323 |
Merit | -0.302 |
anity | -0.293 |
sup | -0.283 |
Token | and |
Token ID | 290 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
hetical | +0.838 |
sequ | +0.820 |
pneum | +0.786 |
stro | +0.759 |
helic | +0.754 |
Neg logit contributions | |
ariat | -0.775 |
rium | -0.747 |
Merit | -0.688 |
anity | -0.663 |
sup | -0.649 |
Token | Fisher |
Token ID | 14388 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
hetical | +0.040 |
sequ | +0.039 |
pneum | +0.038 |
helic | +0.036 |
stro | +0.036 |
Neg logit contributions | |
ariat | -0.042 |
rium | -0.040 |
Merit | -0.038 |
anity | -0.037 |
sup | -0.035 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
hetical | +0.440 |
sequ | +0.439 |
pneum | +0.424 |
stro | +0.400 |
helic | +0.398 |
Neg logit contributions | |
ariat | -0.371 |
rium | -0.355 |
Merit | -0.324 |
anity | -0.316 |
merce | -0.307 |
Token | boys |
Token ID | 13202 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
hetical | +0.326 |
sequ | +0.323 |
stro | +0.311 |
pneum | +0.308 |
helic | +0.299 |
Neg logit contributions | |
ariat | -0.132 |
rium | -0.121 |
Merit | -0.104 |
anity | -0.100 |
sup | -0.097 |
Token | beware |
Token ID | 40600 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
ariat | +0.158 |
rium | +0.151 |
Merit | +0.139 |
anity | +0.133 |
sup | +0.129 |
Neg logit contributions | |
hetical | -0.195 |
sequ | -0.190 |
pneum | -0.185 |
helic | -0.176 |
stro | -0.176 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
hetical | +0.647 |
sequ | +0.639 |
pneum | +0.615 |
helic | +0.588 |
stro | +0.588 |
Neg logit contributions | |
ariat | -0.598 |
rium | -0.577 |
Merit | -0.534 |
anity | -0.518 |
sup | -0.500 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ariat | +0.152 |
rium | +0.147 |
Merit | +0.136 |
anity | +0.133 |
sup | +0.127 |
Neg logit contributions | |
hetical | -0.163 |
sequ | -0.161 |
pneum | -0.154 |
stro | -0.149 |
helic | -0.146 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
ariat | +0.182 |
rium | +0.176 |
Merit | +0.165 |
anity | +0.162 |
sup | +0.159 |
Neg logit contributions | |
hetical | -0.117 |
sequ | -0.113 |
pneum | -0.107 |
stro | -0.104 |
helic | -0.101 |
Token | : |
Token ID | 25 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
sequ | +2.729 |
hetical | +2.726 |
pneum | +2.506 |
stro | +2.458 |
──── | +2.375 |
Neg logit contributions | |
ariat | -3.575 |
rium | -3.457 |
Merit | -3.217 |
merce | -3.201 |
anity | -3.175 |
Token | j |
Token ID | 474 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ariat | +0.837 |
rium | +0.811 |
Merit | +0.757 |
anity | +0.737 |
sup | +0.712 |
Neg logit contributions | |
hetical | -0.814 |
sequ | -0.798 |
pneum | -0.767 |
helic | -0.735 |
stro | -0.733 |
Token | wt |
Token ID | 46569 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
hetical | +0.423 |
sequ | +0.416 |
pneum | +0.400 |
stro | +0.389 |
helic | +0.383 |
Neg logit contributions | |
ariat | -0.382 |
rium | -0.369 |
Merit | -0.346 |
anity | -0.331 |
sup | -0.323 |
Token | 0001 |
Token ID | 18005 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ariat | +0.312 |
rium | +0.300 |
Merit | +0.279 |
anity | +0.269 |
sup | +0.259 |
Neg logit contributions | |
hetical | -0.380 |
sequ | -0.373 |
pneum | -0.360 |
stro | -0.348 |
helic | -0.346 |
Token | - |
Token ID | 532 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ariat | +0.141 |
rium | +0.133 |
Merit | +0.119 |
anity | +0.113 |
sup | +0.107 |
Neg logit contributions | |
hetical | -0.301 |
sequ | -0.297 |
pneum | -0.289 |
helic | -0.281 |
stro | -0.280 |
Token | Wikimedia |
Token ID | 44877 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
hetical | +0.393 |
sequ | +0.387 |
pneum | +0.372 |
helic | +0.357 |
stro | +0.356 |
Neg logit contributions | |
ariat | -0.396 |
rium | -0.383 |
Merit | -0.358 |
anity | -0.348 |
sup | -0.335 |
Token | Commons |
Token ID | 13815 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
hetical | +1.313 |
sequ | +1.309 |
pneum | +1.252 |
helic | +1.209 |
stro | +1.205 |
Neg logit contributions | |
ariat | -1.007 |
rium | -0.973 |
Merit | -0.893 |
anity | -0.858 |
sup | -0.825 |
Token | . |
Token ID | 13 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
hetical | +0.338 |
sequ | +0.333 |
pneum | +0.320 |
helic | +0.307 |
stro | +0.307 |
Neg logit contributions | |
ariat | -0.313 |
rium | -0.303 |
Merit | -0.281 |
anity | -0.272 |
sup | -0.263 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
hetical | +0.430 |
sequ | +0.422 |
pneum | +0.407 |
stro | +0.390 |
helic | +0.390 |
Neg logit contributions | |
ariat | -0.414 |
rium | -0.400 |
Merit | -0.373 |
anity | -0.362 |
sup | -0.349 |
Token | T |
Token ID | 51 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
hetical | +0.409 |
sequ | +0.400 |
pneum | +0.382 |
stro | +0.371 |
helic | +0.363 |
Neg logit contributions | |
ariat | -0.429 |
rium | -0.414 |
Merit | -0.381 |
anity | -0.376 |
sup | -0.366 |
Token | ucker |
Token ID | 12603 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
hetical | +0.330 |
sequ | +0.323 |
pneum | +0.310 |
stro | +0.298 |
helic | +0.297 |
Neg logit contributions | |
ariat | -0.319 |
rium | -0.308 |
Merit | -0.290 |
anity | -0.279 |
sup | -0.271 |
Token | Carlson |
Token ID | 33059 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
hetical | +1.628 |
sequ | +1.616 |
pneum | +1.563 |
helic | +1.484 |
stro | +1.477 |
Neg logit contributions | |
ariat | -2.073 |
rium | -2.037 |
Merit | -1.876 |
anity | -1.836 |
merce | -1.770 |
Token | laid |
Token ID | 8104 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
hetical | +0.399 |
sequ | +0.396 |
pneum | +0.377 |
helic | +0.363 |
stro | +0.363 |
Neg logit contributions | |
ariat | -0.386 |
rium | -0.379 |
Merit | -0.347 |
anity | -0.337 |
sup | -0.325 |
Token | out |
Token ID | 503 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
hetical | +0.564 |
sequ | +0.555 |
pneum | +0.536 |
stro | +0.518 |
helic | +0.515 |
Neg logit contributions | |
ariat | -0.425 |
rium | -0.410 |
Merit | -0.379 |
anity | -0.366 |
sup | -0.349 |
Token | a |
Token ID | 257 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
hetical | +0.141 |
sequ | +0.139 |
pneum | +0.133 |
stro | +0.128 |
helic | +0.128 |
Neg logit contributions | |
ariat | -0.145 |
rium | -0.141 |
Merit | -0.131 |
anity | -0.128 |
sup | -0.123 |
Token | number |
Token ID | 1271 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
hetical | +0.568 |
sequ | +0.561 |
pneum | +0.535 |
stro | +0.512 |
helic | +0.512 |
Neg logit contributions | |
ariat | -0.651 |
rium | -0.632 |
Merit | -0.592 |
anity | -0.576 |
sup | -0.555 |