Token | ally |
Token ID | 12525 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
thur | +0.502 |
andise | +0.485 |
gee | +0.470 |
boa | +0.457 |
Merchants | +0.425 |
Neg logit contributions | |
ta | -0.424 |
Else | -0.418 |
Defendants | -0.418 |
core | -0.416 |
cial | -0.407 |
Token | in |
Token ID | 287 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
ta | +0.027 |
Else | +0.027 |
core | +0.027 |
Defendants | +0.027 |
cial | +0.026 |
Neg logit contributions | |
thur | -0.034 |
andise | -0.033 |
gee | -0.032 |
boa | -0.031 |
Merchants | -0.029 |
Token | charge |
Token ID | 3877 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
Else | +0.486 |
ta | +0.480 |
core | +0.477 |
Defendants | +0.477 |
cial | +0.468 |
Neg logit contributions | |
thur | -0.519 |
andise | -0.498 |
gee | -0.485 |
boa | -0.472 |
Merchants | -0.439 |
Token | of |
Token ID | 286 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
Else | +0.348 |
ta | +0.348 |
core | +0.344 |
Defendants | +0.344 |
cial | +0.336 |
Neg logit contributions | |
thur | -0.450 |
andise | -0.435 |
gee | -0.427 |
boa | -0.413 |
Merchants | -0.386 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
Else | +0.347 |
ta | +0.345 |
Defendants | +0.342 |
core | +0.341 |
cial | +0.335 |
Neg logit contributions | |
thur | -0.373 |
andise | -0.359 |
gee | -0.352 |
boa | -0.340 |
Merchants | -0.313 |
Token | probe |
Token ID | 12774 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Else | +0.402 |
ta | +0.400 |
core | +0.399 |
Defendants | +0.394 |
cial | +0.390 |
Neg logit contributions | |
thur | -0.466 |
andise | -0.449 |
gee | -0.443 |
boa | -0.427 |
Merchants | -0.400 |
Token | : |
Token ID | 25 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ta | +1.206 |
Else | +1.205 |
core | +1.189 |
Defendants | +1.155 |
yang | +1.152 |
Neg logit contributions | |
thur | -1.915 |
gee | -1.832 |
andise | -1.826 |
boa | -1.749 |
Merchants | -1.659 |
Token | report |
Token ID | 989 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Else | +0.791 |
ta | +0.788 |
core | +0.783 |
Defendants | +0.778 |
cial | +0.776 |
Neg logit contributions | |
thur | -0.622 |
andise | -0.598 |
gee | -0.582 |
boa | -0.562 |
Merchants | -0.515 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ta | +0.737 |
Else | +0.735 |
core | +0.716 |
cial | +0.704 |
Defendants | +0.703 |
Neg logit contributions | |
thur | -1.378 |
andise | -1.333 |
gee | -1.313 |
boa | -1.276 |
Merchants | -1.223 |
Token | airline |
Token ID | 18091 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
thur | +0.172 |
andise | +0.166 |
gee | +0.162 |
boa | +0.158 |
Merchants | +0.146 |
Neg logit contributions | |
ta | -0.140 |
Else | -0.139 |
core | -0.138 |
Defendants | -0.138 |
cial | -0.136 |
Token | takes |
Token ID | 2753 |
Feature activation | +3.12e-03 |
Pos logit contributions | |
Else | +0.504 |
ta | +0.501 |
Defendants | +0.497 |
core | +0.496 |
cial | +0.490 |
Neg logit contributions | |
thur | -0.651 |
andise | -0.625 |
gee | -0.616 |
boa | -0.599 |
Merchants | -0.558 |
Token | th |
Token ID | 400 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
thur | +0.316 |
andise | +0.306 |
gee | +0.299 |
boa | +0.290 |
Merchants | +0.269 |
Neg logit contributions | |
ta | -0.270 |
Else | -0.268 |
core | -0.266 |
Defendants | -0.265 |
cial | -0.261 |
Token | anniversary |
Token ID | 11162 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ta | +0.068 |
Else | +0.068 |
core | +0.068 |
Defendants | +0.067 |
cial | +0.066 |
Neg logit contributions | |
thur | -0.079 |
andise | -0.076 |
gee | -0.075 |
boa | -0.072 |
Merchants | -0.067 |
Token | of |
Token ID | 286 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
ta | +0.141 |
Else | +0.141 |
Defendants | +0.140 |
core | +0.139 |
cial | +0.137 |
Neg logit contributions | |
thur | -0.177 |
andise | -0.171 |
gee | -0.167 |
boa | -0.162 |
Merchants | -0.151 |
Token | the |
Token ID | 262 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
thur | +0.018 |
andise | +0.018 |
gee | +0.017 |
boa | +0.017 |
Merchants | +0.016 |
Neg logit contributions | |
ta | -0.015 |
Else | -0.015 |
core | -0.014 |
Defendants | -0.014 |
cial | -0.014 |
Token | D |
Token ID | 360 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
thur | +0.306 |
andise | +0.295 |
gee | +0.288 |
boa | +0.279 |
Merchants | +0.258 |
Neg logit contributions | |
ta | -0.268 |
Else | -0.265 |
core | -0.263 |
Defendants | -0.263 |
cial | -0.258 |
Token | - |
Token ID | 12 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
ta | +0.546 |
Else | +0.546 |
core | +0.540 |
Defendants | +0.539 |
cial | +0.527 |
Neg logit contributions | |
thur | -0.607 |
andise | -0.588 |
gee | -0.573 |
boa | -0.556 |
Merchants | -0.514 |
Token | Day |
Token ID | 12393 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
Defendants | +1.341 |
Else | +1.336 |
ta | +1.329 |
core | +1.318 |
Secondary | +1.285 |
Neg logit contributions | |
thur | -1.699 |
andise | -1.655 |
gee | -1.641 |
boa | -1.574 |
Merchants | -1.469 |
Token | land |
Token ID | 1956 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
Else | +0.310 |
ta | +0.310 |
Defendants | +0.307 |
core | +0.306 |
cial | +0.301 |
Neg logit contributions | |
thur | -0.303 |
andise | -0.292 |
gee | -0.284 |
boa | -0.275 |
Merchants | -0.253 |
Token | ings |
Token ID | 654 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
thur | +0.023 |
andise | +0.022 |
gee | +0.022 |
boa | +0.021 |
Merchants | +0.020 |
Neg logit contributions | |
ta | -0.010 |
Else | -0.010 |
core | -0.010 |
Defendants | -0.010 |
cial | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -3.10e-03 |
Pos logit contributions | |
Else | +0.261 |
ta | +0.261 |
Defendants | +0.258 |
core | +0.257 |
cial | +0.252 |
Neg logit contributions | |
thur | -0.312 |
andise | -0.302 |
gee | -0.294 |
boa | -0.286 |
Merchants | -0.265 |
Token |
|
Token ID | 198 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
thur | +0.002 |
andise | +0.002 |
gee | +0.002 |
boa | +0.002 |
Merchants | +0.002 |
Neg logit contributions | |
ta | -0.002 |
Else | -0.002 |
core | -0.002 |
Defendants | -0.002 |
cial | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
ta | +0.041 |
Else | +0.041 |
core | +0.041 |
Defendants | +0.041 |
cial | +0.040 |
Neg logit contributions | |
thur | -0.055 |
andise | -0.054 |
gee | -0.052 |
boa | -0.051 |
Merchants | -0.048 |
Token | one |
Token ID | 530 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
ta | +0.116 |
Else | +0.116 |
core | +0.115 |
Defendants | +0.115 |
cial | +0.113 |
Neg logit contributions | |
thur | -0.151 |
andise | -0.146 |
gee | -0.143 |
boa | -0.139 |
Merchants | -0.130 |
Token | source |
Token ID | 2723 |
Feature activation | +9.64e-02 |
Pos logit contributions | |
thur | +0.054 |
andise | +0.052 |
gee | +0.051 |
boa | +0.050 |
Merchants | +0.046 |
Neg logit contributions | |
ta | -0.044 |
Else | -0.044 |
core | -0.043 |
Defendants | -0.043 |
cial | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ta | +0.057 |
Else | +0.057 |
core | +0.056 |
Defendants | +0.056 |
cial | +0.055 |
Neg logit contributions | |
thur | -0.072 |
andise | -0.070 |
gee | -0.068 |
boa | -0.066 |
Merchants | -0.062 |
Token | Penguins |
Token ID | 29755 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ta | +0.140 |
Else | +0.140 |
core | +0.138 |
Defendants | +0.138 |
cial | +0.136 |
Neg logit contributions | |
thur | -0.143 |
andise | -0.138 |
gee | -0.134 |
boa | -0.130 |
Merchants | -0.120 |
Token | GM |
Token ID | 6951 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ta | +0.094 |
Else | +0.094 |
core | +0.093 |
Defendants | +0.093 |
cial | +0.091 |
Neg logit contributions | |
thur | -0.100 |
andise | -0.096 |
gee | -0.094 |
boa | -0.091 |
Merchants | -0.084 |
Token | Jim |
Token ID | 5395 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Else | +1.412 |
ta | +1.379 |
Defendants | +1.363 |
core | +1.352 |
cial | +1.341 |
Neg logit contributions | |
thur | -1.616 |
andise | -1.565 |
gee | -1.500 |
boa | -1.465 |
Merchants | -1.368 |
Token | Rutherford |
Token ID | 49767 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Else | +0.943 |
ta | +0.932 |
core | +0.926 |
cial | +0.917 |
Defendants | +0.917 |
Neg logit contributions | |
thur | -0.810 |
andise | -0.774 |
gee | -0.750 |
boa | -0.731 |
heed | -0.667 |
Token | approached |
Token ID | 10448 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
ta | +0.174 |
Else | +0.174 |
Defendants | +0.171 |
core | +0.171 |
cial | +0.168 |
Neg logit contributions | |
thur | -0.244 |
andise | -0.236 |
gee | -0.231 |
boa | -0.225 |
Merchants | -0.210 |
Token | Fle |
Token ID | 12005 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
ta | +0.176 |
Else | +0.176 |
core | +0.174 |
Defendants | +0.174 |
cial | +0.171 |
Neg logit contributions | |
thur | -0.173 |
andise | -0.167 |
gee | -0.162 |
boa | -0.157 |
Merchants | -0.145 |
Token | ury |
Token ID | 1601 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
ta | +0.150 |
Else | +0.150 |
Defendants | +0.147 |
core | +0.147 |
cial | +0.143 |
Neg logit contributions | |
thur | -0.357 |
andise | -0.347 |
gee | -0.341 |
boa | -0.333 |
Merchants | -0.315 |
Token | ally |
Token ID | 12525 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
thur | +0.474 |
andise | +0.458 |
gee | +0.445 |
boa | +0.433 |
Merchants | +0.404 |
Neg logit contributions | |
ta | -0.371 |
Else | -0.366 |
Defendants | -0.365 |
core | -0.364 |
cial | -0.356 |
Token | in |
Token ID | 287 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
thur | +0.092 |
andise | +0.089 |
gee | +0.087 |
boa | +0.085 |
Merchants | +0.079 |
Neg logit contributions | |
ta | -0.071 |
Else | -0.071 |
core | -0.070 |
Defendants | -0.070 |
cial | -0.069 |
Token | charge |
Token ID | 3877 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Else | +0.452 |
ta | +0.448 |
core | +0.445 |
Defendants | +0.445 |
cial | +0.437 |
Neg logit contributions | |
thur | -0.414 |
andise | -0.396 |
gee | -0.385 |
boa | -0.373 |
Merchants | -0.344 |
Token | of |
Token ID | 286 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
ta | +0.208 |
Else | +0.207 |
core | +0.205 |
Defendants | +0.205 |
cial | +0.200 |
Neg logit contributions | |
thur | -0.276 |
andise | -0.267 |
gee | -0.262 |
boa | -0.254 |
Merchants | -0.237 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Else | +0.219 |
ta | +0.219 |
core | +0.216 |
Defendants | +0.216 |
cial | +0.212 |
Neg logit contributions | |
thur | -0.274 |
andise | -0.265 |
gee | -0.259 |
boa | -0.251 |
Merchants | -0.233 |
Token | probe |
Token ID | 12774 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Else | +0.420 |
ta | +0.419 |
core | +0.419 |
Defendants | +0.412 |
cial | +0.409 |
Neg logit contributions | |
thur | -0.472 |
andise | -0.454 |
gee | -0.448 |
boa | -0.432 |
Merchants | -0.404 |
Token | : |
Token ID | 25 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
Else | +1.344 |
ta | +1.341 |
core | +1.330 |
Defendants | +1.293 |
yang | +1.292 |
Neg logit contributions | |
thur | -1.592 |
andise | -1.509 |
gee | -1.508 |
boa | -1.437 |
Merchants | -1.348 |
Token | report |
Token ID | 989 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Else | +0.537 |
ta | +0.537 |
core | +0.533 |
Defendants | +0.531 |
cial | +0.526 |
Neg logit contributions | |
thur | -0.433 |
andise | -0.415 |
gee | -0.405 |
boa | -0.390 |
Merchants | -0.357 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Else | +0.699 |
ta | +0.699 |
core | +0.683 |
cial | +0.667 |
Defendants | +0.667 |
Neg logit contributions | |
thur | -1.280 |
andise | -1.238 |
gee | -1.216 |
boa | -1.182 |
Merchants | -1.131 |
Token | airline |
Token ID | 18091 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
thur | +0.076 |
andise | +0.073 |
gee | +0.072 |
boa | +0.070 |
Merchants | +0.065 |
Neg logit contributions | |
ta | -0.059 |
Else | -0.059 |
core | -0.058 |
Defendants | -0.058 |
cial | -0.057 |
Token | takes |
Token ID | 2753 |
Feature activation | -6.97e-03 |
Pos logit contributions | |
Else | +0.496 |
ta | +0.494 |
Defendants | +0.489 |
core | +0.488 |
cial | +0.481 |
Neg logit contributions | |
thur | -0.640 |
andise | -0.615 |
gee | -0.607 |
boa | -0.590 |
Merchants | -0.550 |
Token | rate |
Token ID | 2494 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
thur | +0.549 |
andise | +0.533 |
gee | +0.516 |
boa | +0.503 |
Merchants | +0.471 |
Neg logit contributions | |
ta | -0.429 |
core | -0.423 |
Else | -0.422 |
Defendants | -0.419 |
cial | -0.410 |
Token | , |
Token ID | 11 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
Else | +0.647 |
ta | +0.646 |
Defendants | +0.636 |
core | +0.635 |
cial | +0.630 |
Neg logit contributions | |
thur | -0.712 |
andise | -0.688 |
gee | -0.671 |
boa | -0.657 |
Merchants | -0.606 |
Token | America |
Token ID | 2253 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
thur | +0.348 |
andise | +0.337 |
gee | +0.328 |
boa | +0.317 |
Merchants | +0.296 |
Neg logit contributions | |
ta | -0.289 |
Else | -0.286 |
core | -0.284 |
Defendants | -0.284 |
cial | -0.277 |
Token | needs |
Token ID | 2476 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
thur | +0.588 |
andise | +0.569 |
gee | +0.547 |
boa | +0.535 |
Merchants | +0.497 |
Neg logit contributions | |
ta | -0.538 |
Else | -0.536 |
core | -0.533 |
Defendants | -0.530 |
cial | -0.522 |
Token | future |
Token ID | 2003 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
thur | +0.027 |
andise | +0.026 |
gee | +0.025 |
boa | +0.025 |
Merchants | +0.023 |
Neg logit contributions | |
ta | -0.020 |
Else | -0.020 |
core | -0.020 |
Defendants | -0.020 |
cial | -0.019 |
Token | migrants |
Token ID | 12783 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
ta | +0.369 |
Else | +0.368 |
core | +0.365 |
Defendants | +0.363 |
cial | +0.359 |
Neg logit contributions | |
thur | -0.465 |
andise | -0.450 |
gee | -0.440 |
boa | -0.427 |
Merchants | -0.398 |
Token | 4 |
Token ID | 604 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
Else | +1.393 |
ta | +1.390 |
cial | +1.365 |
Defendants | +1.364 |
core | +1.354 |
Neg logit contributions | |
andise | -1.463 |
thur | -1.449 |
gee | -1.416 |
boa | -1.326 |
Merchants | -1.272 |
Token | ways |
Token ID | 2842 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
thur | +0.449 |
andise | +0.433 |
gee | +0.418 |
boa | +0.407 |
Merchants | +0.376 |
Neg logit contributions | |
ta | -0.449 |
Else | -0.447 |
core | -0.446 |
Defendants | -0.442 |
cial | -0.435 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ta | +0.029 |
Else | +0.029 |
core | +0.028 |
Defendants | +0.028 |
cial | +0.028 |
Neg logit contributions | |
thur | -0.039 |
andise | -0.037 |
gee | -0.037 |
boa | -0.036 |
Merchants | -0.033 |
Token | looms |
Token ID | 46234 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
thur | +0.878 |
andise | +0.839 |
gee | +0.819 |
boa | +0.799 |
Merchants | +0.745 |
Neg logit contributions | |
ta | -0.661 |
Else | -0.656 |
core | -0.654 |
Defendants | -0.649 |
cial | -0.632 |
Token | over |
Token ID | 625 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Else | +0.510 |
ta | +0.506 |
core | +0.503 |
Defendants | +0.502 |
cial | +0.497 |
Neg logit contributions | |
thur | -0.607 |
andise | -0.587 |
gee | -0.575 |
boa | -0.558 |
Merchants | -0.523 |
Token | comedian |
Token ID | 23139 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
thur | +0.081 |
andise | +0.079 |
gee | +0.077 |
boa | +0.075 |
Merchants | +0.070 |
Neg logit contributions | |
ta | -0.062 |
Else | -0.061 |
core | -0.061 |
Defendants | -0.061 |
cial | -0.060 |
Token | / |
Token ID | 14 |
Feature activation | -4.48e-03 |
Pos logit contributions | |
ta | +0.016 |
Else | +0.016 |
core | +0.016 |
Defendants | +0.016 |
cial | +0.016 |
Neg logit contributions | |
thur | -0.023 |
andise | -0.022 |
gee | -0.021 |
boa | -0.021 |
Merchants | -0.019 |
Token | author |
Token ID | 9800 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
thur | +0.003 |
andise | +0.003 |
gee | +0.003 |
boa | +0.003 |
Merchants | +0.003 |
Neg logit contributions | |
ta | -0.003 |
Else | -0.003 |
core | -0.003 |
Defendants | -0.003 |
cial | -0.003 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ta | +0.095 |
Else | +0.095 |
core | +0.094 |
Defendants | +0.094 |
cial | +0.092 |
Neg logit contributions | |
thur | -0.125 |
andise | -0.121 |
gee | -0.118 |
boa | -0.115 |
Merchants | -0.107 |
Token | Ben |
Token ID | 3932 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
ta | +0.092 |
Else | +0.092 |
core | +0.091 |
Defendants | +0.091 |
cial | +0.090 |
Neg logit contributions | |
thur | -0.106 |
andise | -0.102 |
gee | -0.100 |
boa | -0.097 |
Merchants | -0.090 |
Token | inc |
Token ID | 1939 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
thur | +0.379 |
andise | +0.368 |
gee | +0.358 |
boa | +0.348 |
Merchants | +0.325 |
Neg logit contributions | |
ta | -0.290 |
Else | -0.288 |
core | -0.287 |
Defendants | -0.286 |
cial | -0.280 |
Token | asa |
Token ID | 15462 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
Else | +1.282 |
ta | +1.257 |
Defendants | +1.256 |
core | +1.236 |
Secondary | +1.209 |
Neg logit contributions | |
thur | -1.575 |
andise | -1.517 |
gee | -1.487 |
boa | -1.441 |
endi | -1.340 |
Token | ), |
Token ID | 828 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
ta | +0.057 |
Else | +0.057 |
core | +0.056 |
Defendants | +0.056 |
cial | +0.055 |
Neg logit contributions | |
thur | -0.069 |
andise | -0.067 |
gee | -0.065 |
boa | -0.063 |
Merchants | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
ta | +0.012 |
Else | +0.012 |
core | +0.012 |
Defendants | +0.012 |
cial | +0.012 |
Neg logit contributions | |
thur | -0.017 |
andise | -0.016 |
gee | -0.016 |
boa | -0.015 |
Merchants | -0.014 |
Token | strangely |
Token ID | 29381 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
thur | +0.056 |
andise | +0.054 |
gee | +0.053 |
boa | +0.051 |
Merchants | +0.048 |
Neg logit contributions | |
ta | -0.041 |
Else | -0.040 |
core | -0.040 |
Defendants | -0.040 |
cial | -0.039 |
Token | judged |
Token ID | 19589 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
thur | +0.417 |
andise | +0.404 |
gee | +0.394 |
boa | +0.383 |
Merchants | +0.358 |
Neg logit contributions | |
ta | -0.321 |
Else | -0.318 |
core | -0.316 |
Defendants | -0.315 |
cial | -0.309 |
Token | sidelines |
Token ID | 29394 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
ta | +0.234 |
Else | +0.234 |
core | +0.232 |
Defendants | +0.231 |
cial | +0.227 |
Neg logit contributions | |
thur | -0.255 |
andise | -0.246 |
gee | -0.240 |
boa | -0.233 |
Merchants | -0.215 |
Token | of |
Token ID | 286 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ta | +0.418 |
Else | +0.418 |
Defendants | +0.413 |
core | +0.412 |
cial | +0.405 |
Neg logit contributions | |
thur | -0.509 |
andise | -0.493 |
gee | -0.482 |
boa | -0.467 |
Merchants | -0.436 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Else | +0.704 |
ta | +0.699 |
Defendants | +0.692 |
core | +0.691 |
cial | +0.680 |
Neg logit contributions | |
thur | -0.867 |
andise | -0.842 |
gee | -0.824 |
boa | -0.793 |
Merchants | -0.744 |
Token | - |
Token ID | 12 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ta | +0.157 |
Else | +0.156 |
core | +0.155 |
Defendants | +0.155 |
cial | +0.152 |
Neg logit contributions | |
thur | -0.179 |
andise | -0.173 |
gee | -0.169 |
boa | -0.164 |
Merchants | -0.152 |
Token | Kim |
Token ID | 26374 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ta | +1.080 |
Defendants | +1.077 |
Else | +1.066 |
core | +1.057 |
Secondary | +1.048 |
Neg logit contributions | |
thur | -0.942 |
andise | -0.917 |
gee | -0.902 |
boa | -0.863 |
Merchants | -0.785 |
Token | summit |
Token ID | 14237 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Else | +0.600 |
ta | +0.596 |
Defendants | +0.593 |
core | +0.590 |
cial | +0.581 |
Neg logit contributions | |
thur | -0.780 |
andise | -0.751 |
gee | -0.741 |
boa | -0.719 |
Merchants | -0.670 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Else | +1.009 |
ta | +1.007 |
core | +0.981 |
cial | +0.954 |
Defendants | +0.953 |
Neg logit contributions | |
thur | -1.804 |
andise | -1.739 |
gee | -1.738 |
boa | -1.673 |
Merchants | -1.610 |
Token | 's |
Token ID | 338 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
thur | +0.098 |
andise | +0.094 |
gee | +0.092 |
boa | +0.089 |
Merchants | +0.083 |
Neg logit contributions | |
ta | -0.088 |
Else | -0.087 |
core | -0.086 |
Defendants | -0.086 |
cial | -0.085 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
thur | +0.554 |
andise | +0.537 |
gee | +0.524 |
boa | +0.511 |
Merchants | +0.473 |
Neg logit contributions | |
ta | -0.427 |
Else | -0.424 |
Defendants | -0.421 |
core | -0.420 |
cial | -0.411 |
Token | say |
Token ID | 910 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
thur | +0.052 |
andise | +0.050 |
gee | +0.049 |
boa | +0.048 |
Merchants | +0.045 |
Neg logit contributions | |
ta | -0.038 |
Else | -0.038 |
core | -0.037 |
Defendants | -0.037 |
cial | -0.036 |
Token | he |
Token ID | 339 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ta | +0.366 |
Else | +0.366 |
core | +0.364 |
Defendants | +0.361 |
cial | +0.357 |
Neg logit contributions | |
thur | -0.486 |
andise | -0.469 |
gee | -0.459 |
boa | -0.447 |
Merchants | -0.418 |
Token | the |
Token ID | 262 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ta | +0.156 |
Else | +0.156 |
core | +0.154 |
Defendants | +0.154 |
cial | +0.151 |
Neg logit contributions | |
thur | -0.200 |
andise | -0.193 |
gee | -0.189 |
boa | -0.184 |
Merchants | -0.171 |
Token | risks |
Token ID | 7476 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ta | +0.176 |
Else | +0.176 |
core | +0.174 |
Defendants | +0.173 |
cial | +0.170 |
Neg logit contributions | |
thur | -0.270 |
andise | -0.261 |
gee | -0.256 |
boa | -0.249 |
Merchants | -0.234 |
Token | of |
Token ID | 286 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Else | +0.205 |
ta | +0.205 |
core | +0.203 |
Defendants | +0.203 |
cial | +0.199 |
Neg logit contributions | |
thur | -0.260 |
andise | -0.252 |
gee | -0.246 |
boa | -0.239 |
Merchants | -0.223 |
Token | a |
Token ID | 257 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ta | +0.114 |
Else | +0.114 |
core | +0.113 |
Defendants | +0.113 |
cial | +0.111 |
Neg logit contributions | |
thur | -0.148 |
andise | -0.143 |
gee | -0.140 |
boa | -0.136 |
Merchants | -0.127 |
Token | Deep |
Token ID | 10766 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
ta | +0.007 |
Else | +0.007 |
core | +0.006 |
Defendants | +0.006 |
cial | +0.006 |
Neg logit contributions | |
thur | -0.007 |
andise | -0.007 |
gee | -0.007 |
boa | -0.007 |
Merchants | -0.006 |
Token | water |
Token ID | 7050 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Else | +0.232 |
ta | +0.232 |
Defendants | +0.226 |
core | +0.222 |
cial | +0.217 |
Neg logit contributions | |
thur | -0.946 |
andise | -0.923 |
gee | -0.912 |
boa | -0.894 |
Merchants | -0.852 |
Token | Horizon |
Token ID | 22776 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Else | +1.249 |
ta | +1.239 |
cial | +1.225 |
Defendants | +1.225 |
core | +1.211 |
Neg logit contributions | |
thur | -1.540 |
andise | -1.484 |
gee | -1.463 |
boa | -1.424 |
Merchants | -1.331 |
Token | - |
Token ID | 12 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
ta | +0.131 |
Else | +0.131 |
Defendants | +0.129 |
core | +0.129 |
cial | +0.127 |
Neg logit contributions | |
thur | -0.182 |
andise | -0.177 |
gee | -0.173 |
boa | -0.168 |
Merchants | -0.157 |
Token | style |
Token ID | 7635 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
thur | +0.040 |
andise | +0.038 |
gee | +0.037 |
boa | +0.036 |
Merchants | +0.033 |
Neg logit contributions | |
ta | -0.043 |
Else | -0.043 |
core | -0.043 |
Defendants | -0.043 |
cial | -0.042 |
Token | blow |
Token ID | 6611 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
Else | +0.209 |
ta | +0.209 |
Defendants | +0.207 |
core | +0.207 |
cial | +0.202 |
Neg logit contributions | |
thur | -0.317 |
andise | -0.307 |
gee | -0.301 |
boa | -0.293 |
Merchants | -0.274 |
Token | out |
Token ID | 448 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
thur | +0.347 |
andise | +0.335 |
gee | +0.326 |
boa | +0.317 |
Merchants | +0.294 |
Neg logit contributions | |
ta | -0.311 |
Else | -0.309 |
core | -0.308 |
Defendants | -0.306 |
cial | -0.300 |
Token | sidelines |
Token ID | 29394 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
Else | +0.304 |
ta | +0.304 |
core | +0.301 |
Defendants | +0.300 |
cial | +0.296 |
Neg logit contributions | |
thur | -0.331 |
andise | -0.319 |
gee | -0.310 |
boa | -0.301 |
Merchants | -0.279 |
Token | of |
Token ID | 286 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ta | +0.462 |
Else | +0.461 |
Defendants | +0.456 |
core | +0.455 |
cial | +0.447 |
Neg logit contributions | |
thur | -0.561 |
andise | -0.544 |
gee | -0.532 |
boa | -0.515 |
Merchants | -0.481 |
Token | Trump |
Token ID | 1301 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
Else | +0.715 |
ta | +0.707 |
Defendants | +0.699 |
core | +0.699 |
cial | +0.687 |
Neg logit contributions | |
thur | -0.938 |
andise | -0.912 |
gee | -0.892 |
boa | -0.860 |
Merchants | -0.809 |
Token | - |
Token ID | 12 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ta | +0.204 |
Else | +0.203 |
core | +0.201 |
Defendants | +0.201 |
cial | +0.198 |
Neg logit contributions | |
thur | -0.230 |
andise | -0.222 |
gee | -0.217 |
boa | -0.210 |
Merchants | -0.195 |
Token | Kim |
Token ID | 26374 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
ta | +1.093 |
Defendants | +1.089 |
Else | +1.077 |
core | +1.070 |
Secondary | +1.061 |
Neg logit contributions | |
thur | -0.936 |
andise | -0.912 |
gee | -0.895 |
boa | -0.858 |
Merchants | -0.782 |
Token | summit |
Token ID | 14237 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Else | +0.560 |
ta | +0.558 |
Defendants | +0.554 |
core | +0.552 |
cial | +0.543 |
Neg logit contributions | |
thur | -0.730 |
andise | -0.704 |
gee | -0.693 |
boa | -0.673 |
Merchants | -0.628 |
Token | Manafort |
Token ID | 26351 |
Feature activation | +5.13e-03 |
Pos logit contributions | |
ta | +1.055 |
Else | +1.052 |
core | +1.026 |
Defendants | +1.000 |
cial | +0.999 |
Neg logit contributions | |
thur | -1.709 |
andise | -1.646 |
gee | -1.641 |
boa | -1.580 |
Merchants | -1.520 |
Token | 's |
Token ID | 338 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
ta | +0.003 |
Else | +0.003 |
core | +0.003 |
Defendants | +0.003 |
cial | +0.003 |
Neg logit contributions | |
thur | -0.004 |
andise | -0.004 |
gee | -0.003 |
boa | -0.003 |
Merchants | -0.003 |
Token | attorneys |
Token ID | 14449 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
thur | +0.478 |
andise | +0.464 |
gee | +0.453 |
boa | +0.442 |
Merchants | +0.411 |
Neg logit contributions | |
ta | -0.346 |
Else | -0.343 |
Defendants | -0.341 |
core | -0.340 |
cial | -0.333 |
Token | say |
Token ID | 910 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
ta | +0.075 |
Else | +0.075 |
core | +0.074 |
Defendants | +0.074 |
cial | +0.073 |
Neg logit contributions | |
thur | -0.115 |
andise | -0.112 |
gee | -0.109 |
boa | -0.106 |
Merchants | -0.099 |
Token | he |
Token ID | 339 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ta | +0.318 |
Else | +0.317 |
core | +0.315 |
Defendants | +0.313 |
cial | +0.309 |
Neg logit contributions | |
thur | -0.426 |
andise | -0.411 |
gee | -0.403 |
boa | -0.393 |
Merchants | -0.366 |
Token | destruction |
Token ID | 8166 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ta | +0.148 |
Else | +0.148 |
core | +0.147 |
Defendants | +0.146 |
cial | +0.144 |
Neg logit contributions | |
thur | -0.174 |
andise | -0.168 |
gee | -0.164 |
boa | -0.159 |
Merchants | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ta | +0.197 |
Else | +0.197 |
core | +0.195 |
Defendants | +0.195 |
cial | +0.191 |
Neg logit contributions | |
thur | -0.232 |
andise | -0.224 |
gee | -0.219 |
boa | -0.212 |
Merchants | -0.197 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
thur | +0.210 |
andise | +0.202 |
gee | +0.197 |
boa | +0.192 |
Merchants | +0.177 |
Neg logit contributions | |
ta | -0.187 |
Else | -0.186 |
Defendants | -0.185 |
core | -0.185 |
cial | -0.181 |
Token | Now |
Token ID | 3844 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
thur | +0.011 |
andise | +0.011 |
gee | +0.011 |
boa | +0.010 |
Merchants | +0.010 |
Neg logit contributions | |
ta | -0.009 |
Else | -0.009 |
core | -0.009 |
Defendants | -0.009 |
cial | -0.009 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
thur | +0.084 |
andise | +0.082 |
gee | +0.080 |
boa | +0.077 |
Merchants | +0.072 |
Neg logit contributions | |
ta | -0.069 |
Else | -0.068 |
core | -0.068 |
Defendants | -0.068 |
cial | -0.066 |
Token | : |
Token ID | 25 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
ta | +1.008 |
Else | +1.003 |
Defendants | +0.991 |
core | +0.988 |
cial | +0.979 |
Neg logit contributions | |
thur | -0.998 |
andise | -0.971 |
gee | -0.942 |
boa | -0.917 |
Merchants | -0.848 |
Token | Watch |
Token ID | 6305 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ta | +1.457 |
Else | +1.455 |
Defendants | +1.420 |
cial | +1.417 |
core | +1.415 |
Neg logit contributions | |
thur | -1.287 |
andise | -1.239 |
gee | -1.221 |
boa | -1.171 |
Merchants | -1.092 |
Token | this |
Token ID | 428 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ta | +0.076 |
Else | +0.076 |
core | +0.075 |
Defendants | +0.075 |
cial | +0.074 |
Neg logit contributions | |
thur | -0.097 |
andise | -0.094 |
gee | -0.092 |
boa | -0.089 |
Merchants | -0.083 |
Token | : |
Token ID | 25 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Else | +0.328 |
ta | +0.328 |
Defendants | +0.324 |
core | +0.324 |
cial | +0.318 |
Neg logit contributions | |
thur | -0.346 |
andise | -0.334 |
gee | -0.326 |
boa | -0.316 |
Merchants | -0.292 |
Token | US |
Token ID | 1294 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
ta | +0.124 |
Else | +0.124 |
core | +0.123 |
Defendants | +0.122 |
cial | +0.120 |
Neg logit contributions | |
thur | -0.154 |
andise | -0.149 |
gee | -0.146 |
boa | -0.142 |
Merchants | -0.132 |
Token | Army |
Token ID | 5407 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ta | +0.224 |
Else | +0.224 |
core | +0.221 |
Defendants | +0.221 |
cial | +0.217 |
Neg logit contributions | |
thur | -0.295 |
andise | -0.286 |
gee | -0.279 |
boa | -0.271 |
Merchants | -0.253 |
Token | L |
Token ID | 406 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
thur | +0.018 |
andise | +0.017 |
gee | +0.017 |
boa | +0.016 |
Merchants | +0.015 |
Neg logit contributions | |
ta | -0.020 |
Else | -0.020 |
core | -0.020 |
Defendants | -0.020 |
cial | -0.019 |
Token | add |
Token ID | 2860 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
ta | +0.067 |
Else | +0.066 |
Defendants | +0.066 |
core | +0.066 |
cial | +0.064 |
Neg logit contributions | |
thur | -0.087 |
andise | -0.084 |
gee | -0.082 |
boa | -0.080 |
Merchants | -0.074 |
Token | tips |
Token ID | 9040 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
ta | +0.152 |
Else | +0.152 |
Defendants | +0.150 |
core | +0.150 |
cial | +0.147 |
Neg logit contributions | |
thur | -0.195 |
andise | -0.189 |
gee | -0.184 |
boa | -0.179 |
Merchants | -0.167 |
Token | in |
Token ID | 287 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ta | +0.004 |
Else | +0.004 |
core | +0.004 |
Defendants | +0.004 |
cial | +0.004 |
Neg logit contributions | |
thur | -0.007 |
andise | -0.007 |
gee | -0.007 |
boa | -0.006 |
Merchants | -0.006 |
Token | By |
Token ID | 2750 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
thur | +0.229 |
andise | +0.222 |
gee | +0.217 |
boa | +0.210 |
Merchants | +0.196 |
Neg logit contributions | |
ta | -0.178 |
Else | -0.177 |
core | -0.176 |
Defendants | -0.175 |
cial | -0.172 |
Token | f |
Token ID | 69 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Else | +0.520 |
ta | +0.520 |
Defendants | +0.514 |
core | +0.510 |
cial | +0.502 |
Neg logit contributions | |
thur | -0.693 |
andise | -0.671 |
gee | -0.654 |
boa | -0.638 |
Merchants | -0.596 |
Token | ug |
Token ID | 1018 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ta | +0.574 |
Else | +0.567 |
Defendants | +0.562 |
core | +0.543 |
cial | +0.535 |
Neg logit contributions | |
thur | -2.154 |
andise | -2.099 |
gee | -2.059 |
boa | -2.027 |
Merchants | -1.936 |
Token | l |
Token ID | 75 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Else | +0.232 |
ta | +0.232 |
Defendants | +0.229 |
core | +0.229 |
cial | +0.224 |
Neg logit contributions | |
thur | -0.296 |
andise | -0.286 |
gee | -0.279 |
boa | -0.271 |
Merchants | -0.252 |
Token | ien |
Token ID | 2013 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
thur | +0.667 |
andise | +0.635 |
gee | +0.622 |
boa | +0.599 |
Merchants | +0.551 |
Neg logit contributions | |
ta | -0.772 |
Else | -0.766 |
core | -0.766 |
Defendants | -0.762 |
cial | -0.757 |
Token | 's |
Token ID | 338 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
ta | +0.055 |
Else | +0.055 |
core | +0.054 |
Defendants | +0.054 |
cial | +0.053 |
Neg logit contributions | |
thur | -0.065 |
andise | -0.063 |
gee | -0.061 |
boa | -0.059 |
Merchants | -0.055 |
Token | shot |
Token ID | 2823 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
thur | +0.039 |
andise | +0.038 |
gee | +0.037 |
boa | +0.036 |
Merchants | +0.033 |
Neg logit contributions | |
ta | -0.031 |
Else | -0.031 |
core | -0.030 |
Defendants | -0.030 |
cial | -0.030 |
Token | ally |
Token ID | 12525 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
thur | +0.619 |
andise | +0.597 |
gee | +0.579 |
boa | +0.563 |
Merchants | +0.527 |
Neg logit contributions | |
ta | -0.487 |
Else | -0.478 |
Defendants | -0.478 |
core | -0.477 |
cial | -0.467 |
Token | in |
Token ID | 287 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ta | +0.069 |
Else | +0.069 |
core | +0.068 |
Defendants | +0.068 |
cial | +0.067 |
Neg logit contributions | |
thur | -0.092 |
andise | -0.090 |
gee | -0.088 |
boa | -0.085 |
Merchants | -0.079 |
Token | charge |
Token ID | 3877 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Else | +0.382 |
ta | +0.379 |
Defendants | +0.376 |
core | +0.376 |
cial | +0.368 |
Neg logit contributions | |
thur | -0.414 |
andise | -0.399 |
gee | -0.388 |
boa | -0.378 |
Merchants | -0.350 |
Token | of |
Token ID | 286 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ta | +0.217 |
Else | +0.217 |
core | +0.215 |
Defendants | +0.215 |
cial | +0.210 |
Neg logit contributions | |
thur | -0.274 |
andise | -0.264 |
gee | -0.259 |
boa | -0.251 |
Merchants | -0.234 |
Token | Cohen |
Token ID | 17154 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
Else | +0.214 |
ta | +0.213 |
core | +0.210 |
Defendants | +0.210 |
cial | +0.206 |
Neg logit contributions | |
thur | -0.259 |
andise | -0.251 |
gee | -0.246 |
boa | -0.238 |
Merchants | -0.221 |
Token | probe |
Token ID | 12774 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Else | +0.395 |
ta | +0.394 |
core | +0.393 |
Defendants | +0.388 |
cial | +0.384 |
Neg logit contributions | |
thur | -0.448 |
andise | -0.432 |
gee | -0.425 |
boa | -0.410 |
Merchants | -0.384 |
Token | : |
Token ID | 25 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Else | +1.242 |
ta | +1.236 |
core | +1.220 |
Defendants | +1.191 |
yang | +1.185 |
Neg logit contributions | |
thur | -1.474 |
andise | -1.402 |
gee | -1.394 |
boa | -1.338 |
Merchants | -1.245 |
Token | report |
Token ID | 989 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ta | +0.315 |
Else | +0.315 |
core | +0.312 |
Defendants | +0.311 |
cial | +0.308 |
Neg logit contributions | |
thur | -0.265 |
andise | -0.255 |
gee | -0.247 |
boa | -0.239 |
Merchants | -0.219 |
Token | Vietnamese |
Token ID | 23618 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ta | +0.856 |
Else | +0.852 |
core | +0.834 |
cial | +0.814 |
Defendants | +0.813 |
Neg logit contributions | |
thur | -1.545 |
andise | -1.497 |
gee | -1.471 |
boa | -1.430 |
Merchants | -1.369 |
Token | airline |
Token ID | 18091 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
thur | +0.146 |
andise | +0.142 |
gee | +0.138 |
boa | +0.135 |
Merchants | +0.126 |
Neg logit contributions | |
ta | -0.105 |
Else | -0.104 |
core | -0.103 |
Defendants | -0.103 |
cial | -0.101 |
Token | takes |
Token ID | 2753 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
Else | +0.480 |
ta | +0.478 |
Defendants | +0.472 |
core | +0.472 |
cial | +0.465 |
Neg logit contributions | |
thur | -0.608 |
andise | -0.585 |
gee | -0.576 |
boa | -0.561 |
Merchants | -0.522 |
Token | fact |
Token ID | 1109 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
thur | +0.016 |
andise | +0.016 |
gee | +0.015 |
boa | +0.015 |
Merchants | +0.014 |
Neg logit contributions | |
ta | -0.012 |
Else | -0.012 |
core | -0.012 |
Defendants | -0.012 |
cial | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
thur | +0.084 |
andise | +0.081 |
gee | +0.079 |
boa | +0.077 |
Merchants | +0.072 |
Neg logit contributions | |
ta | -0.071 |
Else | -0.071 |
core | -0.070 |
Defendants | -0.070 |
cial | -0.069 |
Token | this |
Token ID | 428 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
thur | +0.160 |
andise | +0.155 |
gee | +0.151 |
boa | +0.147 |
Merchants | +0.137 |
Neg logit contributions | |
ta | -0.121 |
Else | -0.121 |
core | -0.120 |
Defendants | -0.119 |
cial | -0.117 |
Token | week |
Token ID | 1285 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
thur | +0.017 |
andise | +0.017 |
gee | +0.016 |
boa | +0.016 |
Merchants | +0.015 |
Neg logit contributions | |
ta | -0.014 |
Else | -0.014 |
core | -0.014 |
Defendants | -0.014 |
cial | -0.014 |
Token | Kirk |
Token ID | 13855 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
thur | +0.157 |
andise | +0.152 |
gee | +0.148 |
boa | +0.144 |
Merchants | +0.134 |
Neg logit contributions | |
ta | -0.126 |
Else | -0.126 |
core | -0.125 |
Defendants | -0.125 |
cial | -0.122 |
Token | Herb |
Token ID | 34858 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
ta | +0.154 |
Else | +0.154 |
core | +0.152 |
Defendants | +0.152 |
cial | +0.149 |
Neg logit contributions | |
thur | -0.197 |
andise | -0.190 |
gee | -0.186 |
boa | -0.181 |
Merchants | -0.168 |
Token | stre |
Token ID | 22853 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Else | +1.397 |
ta | +1.380 |
Defendants | +1.378 |
cial | +1.348 |
yang | +1.335 |
Neg logit contributions | |
thur | -1.303 |
andise | -1.249 |
gee | -1.217 |
boa | -1.159 |
endi | -1.089 |
Token | it |
Token ID | 270 |
Feature activation | +4.49e-03 |
Pos logit contributions | |
Else | +0.938 |
ta | +0.928 |
Defendants | +0.920 |
core | +0.908 |
yang | +0.898 |
Neg logit contributions | |
thur | -1.136 |
andise | -1.104 |
gee | -1.079 |
boa | -1.037 |
heed | -0.964 |
Token | , |
Token ID | 11 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ta | +0.003 |
Else | +0.003 |
core | +0.003 |
Defendants | +0.003 |
cial | +0.003 |
Neg logit contributions | |
thur | -0.003 |
andise | -0.003 |
gee | -0.003 |
boa | -0.003 |
Merchants | -0.003 |
Token | Lee |
Token ID | 5741 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ta | +0.134 |
Else | +0.134 |
core | +0.132 |
Defendants | +0.132 |
cial | +0.130 |
Neg logit contributions | |
thur | -0.180 |
andise | -0.174 |
gee | -0.170 |
boa | -0.166 |
Merchants | -0.154 |
Token | Cor |
Token ID | 2744 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
ta | +0.238 |
Else | +0.237 |
core | +0.235 |
Defendants | +0.235 |
cial | +0.231 |
Neg logit contributions | |
thur | -0.254 |
andise | -0.245 |
gee | -0.239 |
boa | -0.231 |
Merchants | -0.215 |
Token | a |
Token ID | 257 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ta | +0.148 |
Else | +0.148 |
core | +0.146 |
Defendants | +0.146 |
cial | +0.143 |
Neg logit contributions | |
thur | -0.210 |
andise | -0.203 |
gee | -0.199 |
boa | -0.193 |
Merchants | -0.181 |
Token | former |
Token ID | 1966 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ta | +0.067 |
Else | +0.067 |
core | +0.066 |
Defendants | +0.066 |
cial | +0.065 |
Neg logit contributions | |
thur | -0.091 |
andise | -0.088 |
gee | -0.086 |
boa | -0.084 |
Merchants | -0.078 |
Token | executive |
Token ID | 4640 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ta | +0.180 |
Else | +0.180 |
core | +0.178 |
Defendants | +0.178 |
cial | +0.174 |
Neg logit contributions | |
thur | -0.286 |
andise | -0.277 |
gee | -0.272 |
boa | -0.265 |
Merchants | -0.249 |
Token | at |
Token ID | 379 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ta | +0.135 |
Else | +0.135 |
Defendants | +0.134 |
core | +0.134 |
cial | +0.131 |
Neg logit contributions | |
thur | -0.180 |
andise | -0.174 |
gee | -0.170 |
boa | -0.166 |
Merchants | -0.155 |
Token | Bear |
Token ID | 14732 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ta | +0.161 |
Else | +0.161 |
core | +0.159 |
Defendants | +0.159 |
cial | +0.156 |
Neg logit contributions | |
thur | -0.214 |
andise | -0.207 |
gee | -0.202 |
boa | -0.197 |
Merchants | -0.184 |
Token | St |
Token ID | 520 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
ta | +1.076 |
Else | +1.069 |
core | +1.042 |
yang | +1.039 |
Defendants | +1.037 |
Neg logit contributions | |
thur | -1.356 |
andise | -1.293 |
gee | -1.267 |
boa | -1.219 |
Merchants | -1.164 |
Token | ear |
Token ID | 451 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
ta | +0.665 |
Else | +0.657 |
Defendants | +0.646 |
Secondary | +0.620 |
yang | +0.619 |
Neg logit contributions | |
thur | -1.980 |
andise | -1.943 |
gee | -1.881 |
boa | -1.877 |
endi | -1.762 |
Token | ns |
Token ID | 5907 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
ta | +0.625 |
Else | +0.625 |
core | +0.618 |
Defendants | +0.618 |
cial | +0.609 |
Neg logit contributions | |
thur | -0.353 |
andise | -0.332 |
gee | -0.321 |
boa | -0.306 |
Merchants | -0.272 |
Token | , |
Token ID | 11 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
ta | +0.048 |
Else | +0.048 |
core | +0.048 |
Defendants | +0.048 |
cial | +0.047 |
Neg logit contributions | |
thur | -0.061 |
andise | -0.059 |
gee | -0.058 |
boa | -0.056 |
Merchants | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
ta | +0.056 |
Else | +0.056 |
core | +0.055 |
Defendants | +0.055 |
cial | +0.054 |
Neg logit contributions | |
thur | -0.075 |
andise | -0.073 |
gee | -0.071 |
boa | -0.069 |
Merchants | -0.064 |
Token | Goldman |
Token ID | 18740 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
ta | +0.124 |
Else | +0.124 |
core | +0.122 |
Defendants | +0.122 |
cial | +0.120 |
Neg logit contributions | |
thur | -0.161 |
andise | -0.156 |
gee | -0.152 |
boa | -0.148 |
Merchants | -0.138 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ta | +0.166 |
Else | +0.166 |
core | +0.164 |
Defendants | +0.164 |
cial | +0.161 |
Neg logit contributions | |
thur | -0.155 |
andise | -0.149 |
gee | -0.145 |
boa | -0.140 |
Merchants | -0.129 |
Token |
|
Token ID | 198 |
Feature activation | +9.98e-02 |
Pos logit contributions | |
ta | +0.152 |
Else | +0.152 |
core | +0.150 |
Defendants | +0.150 |
cial | +0.147 |
Neg logit contributions | |
thur | -0.166 |
andise | -0.160 |
gee | -0.156 |
boa | -0.151 |
Merchants | -0.140 |
Token |
|
Token ID | 198 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ta | +0.064 |
Else | +0.064 |
core | +0.063 |
Defendants | +0.063 |
cial | +0.062 |
Neg logit contributions | |
thur | -0.070 |
andise | -0.068 |
gee | -0.066 |
boa | -0.064 |
Merchants | -0.059 |
Token | Follow |
Token ID | 7155 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
ta | +0.109 |
Else | +0.109 |
Defendants | +0.108 |
core | +0.108 |
cial | +0.105 |
Neg logit contributions | |
thur | -0.124 |
andise | -0.120 |
gee | -0.117 |
boa | -0.113 |
Merchants | -0.105 |
Token | Dan |
Token ID | 6035 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ta | +0.028 |
Else | +0.028 |
core | +0.028 |
Defendants | +0.028 |
cial | +0.027 |
Neg logit contributions | |
thur | -0.037 |
andise | -0.036 |
gee | -0.035 |
boa | -0.034 |
Merchants | -0.032 |
Token | Han |
Token ID | 9530 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ta | +0.355 |
Else | +0.354 |
core | +0.351 |
Defendants | +0.350 |
cial | +0.345 |
Neg logit contributions | |
thur | -0.464 |
andise | -0.449 |
gee | -0.441 |
boa | -0.426 |
Merchants | -0.400 |
Token | z |
Token ID | 89 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Else | +1.040 |
ta | +1.017 |
Defendants | +1.012 |
Secondary | +0.992 |
core | +0.992 |
Neg logit contributions | |
thur | -1.628 |
andise | -1.547 |
gee | -1.526 |
boa | -1.493 |
Merchants | -1.400 |
Token | us |
Token ID | 385 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Else | +0.699 |
ta | +0.689 |
Defendants | +0.686 |
core | +0.673 |
Secondary | +0.661 |
Neg logit contributions | |
thur | -1.013 |
andise | -0.985 |
gee | -0.964 |
boa | -0.934 |
heed | -0.871 |
Token | on |
Token ID | 319 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
thur | +0.129 |
andise | +0.125 |
gee | +0.122 |
boa | +0.118 |
Merchants | +0.110 |
Neg logit contributions | |
ta | -0.107 |
Else | -0.106 |
core | -0.105 |
Defendants | -0.105 |
cial | -0.103 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
thur | +0.418 |
andise | +0.402 |
gee | +0.391 |
boa | +0.379 |
Merchants | +0.349 |
Neg logit contributions | |
ta | -0.428 |
Else | -0.425 |
core | -0.422 |
Defendants | -0.421 |
cial | -0.414 |
Token | @ |
Token ID | 2488 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
thur | +0.384 |
andise | +0.371 |
gee | +0.362 |
boa | +0.353 |
Merchants | +0.328 |
Neg logit contributions | |
ta | -0.306 |
Else | -0.304 |
core | -0.302 |
Defendants | -0.301 |
cial | -0.296 |
Token |
|
Token ID | 198 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ta | +0.035 |
Else | +0.035 |
core | +0.034 |
Defendants | +0.034 |
cial | +0.034 |
Neg logit contributions | |
thur | -0.038 |
andise | -0.037 |
gee | -0.036 |
boa | -0.035 |
Merchants | -0.032 |
Token | Mod |
Token ID | 5841 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
thur | +0.104 |
andise | +0.100 |
gee | +0.098 |
boa | +0.095 |
Merchants | +0.088 |
Neg logit contributions | |
ta | -0.088 |
Else | -0.088 |
core | -0.087 |
Defendants | -0.087 |
cial | -0.086 |
Token | er |
Token ID | 263 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
ta | +0.219 |
Else | +0.218 |
Defendants | +0.216 |
core | +0.216 |
cial | +0.212 |
Neg logit contributions | |
thur | -0.243 |
andise | -0.235 |
gee | -0.229 |
boa | -0.222 |
Merchants | -0.205 |
Token | ator |
Token ID | 1352 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ta | +0.275 |
Else | +0.275 |
core | +0.272 |
Defendants | +0.272 |
cial | +0.266 |
Neg logit contributions | |
thur | -0.335 |
andise | -0.324 |
gee | -0.317 |
boa | -0.307 |
Merchants | -0.285 |
Token | Elaine |
Token ID | 41463 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Else | +0.205 |
ta | +0.205 |
Defendants | +0.203 |
core | +0.203 |
cial | +0.199 |
Neg logit contributions | |
thur | -0.237 |
andise | -0.229 |
gee | -0.224 |
boa | -0.217 |
Merchants | -0.202 |
Token | Qu |
Token ID | 2264 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Else | +0.444 |
ta | +0.443 |
core | +0.440 |
Defendants | +0.439 |
cial | +0.434 |
Neg logit contributions | |
thur | -0.358 |
andise | -0.343 |
gee | -0.334 |
boa | -0.321 |
Merchants | -0.296 |
Token | ij |
Token ID | 2926 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
Else | +0.632 |
ta | +0.616 |
Defendants | +0.603 |
core | +0.582 |
Secondary | +0.570 |
Neg logit contributions | |
thur | -2.026 |
andise | -1.986 |
gee | -1.942 |
boa | -1.896 |
endi | -1.814 |
Token | ano |
Token ID | 5733 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Else | +0.687 |
ta | +0.680 |
Defendants | +0.672 |
core | +0.672 |
Secondary | +0.657 |
Neg logit contributions | |
thur | -0.637 |
andise | -0.615 |
gee | -0.598 |
boa | -0.583 |
Merchants | -0.526 |
Token | of |
Token ID | 286 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
thur | +0.125 |
andise | +0.121 |
gee | +0.119 |
boa | +0.115 |
Merchants | +0.107 |
Neg logit contributions | |
ta | -0.096 |
Else | -0.096 |
core | -0.095 |
Defendants | -0.095 |
cial | -0.093 |
Token | CBS |
Token ID | 11133 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
thur | +0.140 |
andise | +0.136 |
gee | +0.133 |
boa | +0.130 |
Merchants | +0.121 |
Neg logit contributions | |
ta | -0.095 |
Else | -0.095 |
core | -0.094 |
Defendants | -0.094 |
cial | -0.092 |
Token | let |
Token ID | 1309 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
thur | +0.577 |
andise | +0.560 |
gee | +0.545 |
boa | +0.528 |
Merchants | +0.490 |
Neg logit contributions | |
ta | -0.495 |
Else | -0.493 |
core | -0.490 |
Defendants | -0.487 |
cial | -0.480 |
Token | with |
Token ID | 351 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Else | +1.092 |
ta | +1.087 |
cial | +1.074 |
core | +1.064 |
Defendants | +1.061 |
Neg logit contributions | |
thur | -1.236 |
andise | -1.197 |
gee | -1.192 |
boa | -1.132 |
Merchants | -1.068 |
Token | ' |
Token ID | 705 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Else | +0.636 |
ta | +0.628 |
core | +0.619 |
Defendants | +0.617 |
cial | +0.602 |
Neg logit contributions | |
thur | -1.009 |
andise | -0.971 |
gee | -0.967 |
boa | -0.937 |
Merchants | -0.879 |
Token | 44 |
Token ID | 2598 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
ta | +0.205 |
Else | +0.204 |
Defendants | +0.202 |
core | +0.201 |
cial | +0.198 |
Neg logit contributions | |
thur | -0.231 |
andise | -0.223 |
gee | -0.219 |
boa | -0.212 |
Merchants | -0.196 |
Token | ' |
Token ID | 6 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
thur | +0.043 |
andise | +0.042 |
gee | +0.041 |
boa | +0.040 |
Merchants | +0.037 |
Neg logit contributions | |
ta | -0.036 |
Else | -0.036 |
core | -0.035 |
Defendants | -0.035 |
cial | -0.035 |
Token | on |
Token ID | 319 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
Else | +0.500 |
ta | +0.493 |
core | +0.491 |
Defendants | +0.487 |
cial | +0.482 |
Neg logit contributions | |
thur | -0.574 |
andise | -0.557 |
gee | -0.546 |
boa | -0.527 |
Merchants | -0.491 |
Token | sleeve |
Token ID | 23179 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Else | +0.478 |
ta | +0.473 |
Defendants | +0.473 |
core | +0.469 |
cial | +0.462 |
Neg logit contributions | |
thur | -0.538 |
andise | -0.525 |
gee | -0.515 |
boa | -0.496 |
Merchants | -0.459 |
Token | at |
Token ID | 379 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
Else | +0.954 |
cial | +0.951 |
ta | +0.950 |
core | +0.933 |
Defendants | +0.926 |
Neg logit contributions | |
thur | -1.639 |
andise | -1.600 |
gee | -1.597 |
boa | -1.534 |
Merchants | -1.476 |
Token | basketball |
Token ID | 9669 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
Else | +0.341 |
ta | +0.341 |
Defendants | +0.337 |
core | +0.335 |
cial | +0.331 |
Neg logit contributions | |
thur | -0.612 |
andise | -0.593 |
gee | -0.586 |
boa | -0.569 |
Merchants | -0.537 |
Token | game |
Token ID | 983 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ta | +0.475 |
Else | +0.472 |
Defendants | +0.470 |
core | +0.469 |
cial | +0.459 |
Neg logit contributions | |
thur | -0.501 |
andise | -0.481 |
gee | -0.470 |
boa | -0.453 |
Merchants | -0.420 |
Token | MORE |
Token ID | 12011 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
Else | +0.766 |
ta | +0.766 |
core | +0.746 |
Defendants | +0.743 |
cial | +0.738 |
Neg logit contributions | |
thur | -1.166 |
andise | -1.130 |
gee | -1.114 |
boa | -1.070 |
Merchants | -1.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ta | +0.045 |
Else | +0.045 |
core | +0.044 |
Defendants | +0.044 |
cial | +0.043 |
Neg logit contributions | |
thur | -0.053 |
andise | -0.051 |
gee | -0.050 |
boa | -0.048 |
Merchants | -0.045 |
Token | summoned |
Token ID | 20056 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
thur | +0.025 |
andise | +0.024 |
gee | +0.023 |
boa | +0.022 |
Merchants | +0.021 |
Neg logit contributions | |
ta | -0.020 |
Else | -0.020 |
core | -0.020 |
Defendants | -0.020 |
cial | -0.019 |
Token | another |
Token ID | 1194 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
thur | +0.209 |
andise | +0.202 |
gee | +0.197 |
boa | +0.192 |
Merchants | +0.178 |
Neg logit contributions | |
ta | -0.166 |
Else | -0.165 |
core | -0.164 |
Defendants | -0.163 |
cial | -0.160 |
Token | attacker |
Token ID | 15250 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ta | +0.013 |
Else | +0.013 |
core | +0.013 |
Defendants | +0.013 |
cial | +0.013 |
Neg logit contributions | |
thur | -0.016 |
andise | -0.016 |
gee | -0.015 |
boa | -0.015 |
Merchants | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
thur | +0.163 |
andise | +0.158 |
gee | +0.154 |
boa | +0.150 |
Merchants | +0.139 |
Neg logit contributions | |
ta | -0.129 |
Else | -0.128 |
core | -0.127 |
Defendants | -0.127 |
cial | -0.125 |
Token | Memphis |
Token ID | 20522 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
thur | +0.010 |
andise | +0.009 |
gee | +0.009 |
boa | +0.009 |
Merchants | +0.008 |
Neg logit contributions | |
ta | -0.008 |
Else | -0.008 |
core | -0.007 |
Defendants | -0.007 |
cial | -0.007 |
Token | Dep |
Token ID | 2129 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
thur | +0.491 |
andise | +0.471 |
gee | +0.458 |
boa | +0.443 |
Merchants | +0.410 |
Neg logit contributions | |
ta | -0.454 |
Else | -0.449 |
core | -0.448 |
Defendants | -0.447 |
cial | -0.439 |
Token | ay |
Token ID | 323 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ta | +0.423 |
Defendants | +0.423 |
Else | +0.423 |
core | +0.409 |
cial | +0.387 |
Neg logit contributions | |
thur | -2.165 |
andise | -2.130 |
gee | -2.083 |
boa | -2.078 |
endi | -1.975 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
thur | +0.177 |
andise | +0.172 |
gee | +0.167 |
boa | +0.163 |
Merchants | +0.151 |
Neg logit contributions | |
ta | -0.149 |
Else | -0.148 |
core | -0.147 |
Defendants | -0.147 |
cial | -0.144 |
Token | with |
Token ID | 351 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
ta | +0.012 |
Else | +0.012 |
core | +0.012 |
Defendants | +0.012 |
cial | +0.012 |
Neg logit contributions | |
thur | -0.016 |
andise | -0.016 |
gee | -0.015 |
boa | -0.015 |
Merchants | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
thur | +0.072 |
andise | +0.069 |
gee | +0.068 |
boa | +0.066 |
Merchants | +0.061 |
Neg logit contributions | |
ta | -0.057 |
Else | -0.056 |
core | -0.056 |
Defendants | -0.056 |
cial | -0.055 |
Token | right |
Token ID | 826 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ta | +0.227 |
Else | +0.227 |
core | +0.225 |
Defendants | +0.224 |
cial | +0.220 |
Neg logit contributions | |
thur | -0.282 |
andise | -0.273 |
gee | -0.267 |
boa | -0.260 |
Merchants | -0.242 |
Token | go |
Token ID | 467 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
thur | +0.142 |
andise | +0.137 |
gee | +0.134 |
boa | +0.130 |
Merchants | +0.120 |
Neg logit contributions | |
ta | -0.136 |
Else | -0.136 |
core | -0.135 |
Defendants | -0.135 |
cial | -0.132 |
Token | to |
Token ID | 284 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
thur | +0.143 |
andise | +0.138 |
gee | +0.135 |
boa | +0.132 |
Merchants | +0.123 |
Neg logit contributions | |
ta | -0.109 |
Else | -0.108 |
core | -0.107 |
Defendants | -0.107 |
cial | -0.105 |
Token | MLS |
Token ID | 13981 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
thur | +0.254 |
andise | +0.246 |
gee | +0.240 |
boa | +0.233 |
Merchants | +0.217 |
Neg logit contributions | |
ta | -0.198 |
Else | -0.197 |
core | -0.196 |
Defendants | -0.195 |
cial | -0.191 |
Token | because |
Token ID | 780 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
thur | +0.103 |
andise | +0.099 |
gee | +0.097 |
boa | +0.094 |
Merchants | +0.088 |
Neg logit contributions | |
ta | -0.083 |
Else | -0.083 |
core | -0.082 |
Defendants | -0.082 |
cial | -0.081 |
Token | Ben |
Token ID | 3932 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
thur | +0.113 |
andise | +0.109 |
gee | +0.107 |
boa | +0.104 |
Merchants | +0.096 |
Neg logit contributions | |
ta | -0.094 |
Else | -0.093 |
core | -0.092 |
Defendants | -0.092 |
cial | -0.090 |
Token | f |
Token ID | 69 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ta | +0.245 |
Else | +0.244 |
Defendants | +0.241 |
core | +0.241 |
cial | +0.236 |
Neg logit contributions | |
thur | -0.310 |
andise | -0.300 |
gee | -0.293 |
boa | -0.285 |
Merchants | -0.265 |
Token | ica |
Token ID | 3970 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Else | +0.775 |
ta | +0.768 |
Defendants | +0.767 |
core | +0.743 |
cial | +0.728 |
Neg logit contributions | |
thur | -1.765 |
andise | -1.721 |
gee | -1.680 |
boa | -1.653 |
endi | -1.559 |
Token | still |
Token ID | 991 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
thur | +0.116 |
andise | +0.112 |
gee | +0.109 |
boa | +0.106 |
Merchants | +0.099 |
Neg logit contributions | |
ta | -0.093 |
Else | -0.093 |
core | -0.092 |
Defendants | -0.092 |
cial | -0.090 |
Token | owns |
Token ID | 12216 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
thur | +0.065 |
andise | +0.063 |
gee | +0.061 |
boa | +0.060 |
Merchants | +0.055 |
Neg logit contributions | |
ta | -0.053 |
Else | -0.052 |
core | -0.052 |
Defendants | -0.052 |
cial | -0.051 |
Token | my |
Token ID | 616 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
thur | +0.200 |
andise | +0.193 |
gee | +0.189 |
boa | +0.183 |
Merchants | +0.170 |
Neg logit contributions | |
ta | -0.158 |
Else | -0.157 |
core | -0.156 |
Defendants | -0.156 |
cial | -0.153 |
Token | contract |
Token ID | 2775 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Else | +0.206 |
ta | +0.206 |
Defendants | +0.204 |
core | +0.203 |
cial | +0.200 |
Neg logit contributions | |
thur | -0.265 |
andise | -0.257 |
gee | -0.250 |
boa | -0.244 |
Merchants | -0.227 |
Token | the |
Token ID | 262 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
thur | +0.075 |
andise | +0.072 |
gee | +0.071 |
boa | +0.069 |
Merchants | +0.064 |
Neg logit contributions | |
ta | -0.056 |
Else | -0.056 |
core | -0.055 |
Defendants | -0.055 |
cial | -0.054 |
Token | start |
Token ID | 923 |
Feature activation | -5.79e-03 |
Pos logit contributions | |
ta | +0.038 |
Else | +0.038 |
core | +0.037 |
Defendants | +0.037 |
cial | +0.036 |
Neg logit contributions | |
thur | -0.046 |
andise | -0.044 |
gee | -0.043 |
boa | -0.042 |
Merchants | -0.039 |
Token | opposite |
Token ID | 6697 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
thur | +0.004 |
andise | +0.004 |
gee | +0.004 |
boa | +0.004 |
Merchants | +0.004 |
Neg logit contributions | |
ta | -0.003 |
Else | -0.003 |
core | -0.003 |
Defendants | -0.003 |
cial | -0.003 |
Token | Dar |
Token ID | 7491 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
thur | +0.060 |
andise | +0.058 |
gee | +0.057 |
boa | +0.055 |
Merchants | +0.052 |
Neg logit contributions | |
ta | -0.047 |
Else | -0.047 |
core | -0.047 |
Defendants | -0.047 |
cial | -0.046 |
Token | rel |
Token ID | 2411 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
thur | +0.053 |
andise | +0.051 |
gee | +0.050 |
boa | +0.048 |
Merchants | +0.045 |
Neg logit contributions | |
ta | -0.049 |
Else | -0.049 |
core | -0.048 |
Defendants | -0.048 |
cial | -0.047 |
Token | le |
Token ID | 293 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Else | +0.648 |
ta | +0.647 |
Defendants | +0.643 |
core | +0.641 |
cial | +0.632 |
Neg logit contributions | |
thur | -0.751 |
andise | -0.728 |
gee | -0.720 |
boa | -0.687 |
Merchants | -0.643 |
Token | Revis |
Token ID | 46146 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Else | +1.024 |
ta | +1.019 |
Defendants | +1.018 |
cial | +0.996 |
core | +0.994 |
Neg logit contributions | |
thur | -1.495 |
andise | -1.457 |
gee | -1.441 |
boa | -1.386 |
Merchants | -1.299 |
Token | , |
Token ID | 11 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
ta | +0.195 |
Else | +0.195 |
Defendants | +0.193 |
core | +0.192 |
cial | +0.189 |
Neg logit contributions | |
thur | -0.228 |
andise | -0.220 |
gee | -0.215 |
boa | -0.209 |
Merchants | -0.193 |
Token | collected |
Token ID | 7723 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
thur | +0.059 |
andise | +0.057 |
gee | +0.056 |
boa | +0.054 |
Merchants | +0.051 |
Neg logit contributions | |
ta | -0.044 |
Else | -0.044 |
core | -0.043 |
Defendants | -0.043 |
cial | -0.043 |
Token | seven |
Token ID | 3598 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
thur | +0.274 |
andise | +0.265 |
gee | +0.259 |
boa | +0.251 |
Merchants | +0.234 |
Neg logit contributions | |
ta | -0.220 |
Else | -0.218 |
core | -0.217 |
Defendants | -0.216 |
cial | -0.212 |
Token | more |
Token ID | 517 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
thur | +0.237 |
andise | +0.228 |
gee | +0.222 |
boa | +0.215 |
Merchants | +0.199 |
Neg logit contributions | |
ta | -0.225 |
Else | -0.224 |
core | -0.222 |
Defendants | -0.222 |
cial | -0.218 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ta | +0.014 |
Else | +0.014 |
core | +0.014 |
Defendants | +0.014 |
cial | +0.014 |
Neg logit contributions | |
thur | -0.018 |
andise | -0.018 |
gee | -0.017 |
boa | -0.017 |
Merchants | -0.016 |
Token | mix |
Token ID | 5022 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
thur | +0.111 |
andise | +0.108 |
gee | +0.105 |
boa | +0.102 |
Merchants | +0.095 |
Neg logit contributions | |
ta | -0.088 |
Else | -0.087 |
core | -0.087 |
Defendants | -0.087 |
cial | -0.085 |
Token | for |
Token ID | 329 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
thur | +0.303 |
andise | +0.293 |
gee | +0.286 |
boa | +0.278 |
Merchants | +0.259 |
Neg logit contributions | |
ta | -0.240 |
Else | -0.238 |
core | -0.237 |
Defendants | -0.236 |
cial | -0.232 |
Token | Ad |
Token ID | 1215 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
thur | +0.273 |
andise | +0.265 |
gee | +0.258 |
boa | +0.251 |
Merchants | +0.234 |
Neg logit contributions | |
ta | -0.216 |
Else | -0.214 |
core | -0.213 |
Defendants | -0.212 |
cial | -0.208 |
Token | ew |
Token ID | 413 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
thur | +0.279 |
andise | +0.269 |
gee | +0.262 |
boa | +0.255 |
Merchants | +0.237 |
Neg logit contributions | |
ta | -0.239 |
Else | -0.238 |
core | -0.237 |
Defendants | -0.236 |
cial | -0.232 |
Token | ale |
Token ID | 1000 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Else | +0.552 |
ta | +0.552 |
Defendants | +0.548 |
core | +0.543 |
cial | +0.537 |
Neg logit contributions | |
thur | -0.544 |
andise | -0.525 |
gee | -0.511 |
boa | -0.491 |
Merchants | -0.454 |
Token | Om |
Token ID | 16543 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
thur | +2.029 |
andise | +1.964 |
boa | +1.874 |
gee | +1.867 |
heed | +1.751 |
Neg logit contributions | |
ta | -1.197 |
core | -1.182 |
Defendants | -1.149 |
Else | -1.144 |
Secondary | -1.131 |
Token | ot |
Token ID | 313 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
thur | +0.567 |
andise | +0.550 |
gee | +0.535 |
boa | +0.523 |
Merchants | +0.490 |
Neg logit contributions | |
ta | -0.417 |
Else | -0.411 |
core | -0.411 |
Defendants | -0.407 |
cial | -0.403 |
Token | osh |
Token ID | 3768 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
thur | +1.242 |
andise | +1.196 |
gee | +1.154 |
boa | +1.119 |
Merchants | +1.075 |
Neg logit contributions | |
ta | -0.957 |
core | -0.942 |
Else | -0.933 |
cial | -0.927 |
Defendants | -0.926 |
Token | o |
Token ID | 78 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
thur | +0.015 |
andise | +0.015 |
gee | +0.014 |
boa | +0.014 |
Merchants | +0.013 |
Neg logit contributions | |
ta | -0.013 |
Else | -0.013 |
core | -0.013 |
Defendants | -0.013 |
cial | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
thur | +0.273 |
andise | +0.264 |
gee | +0.257 |
boa | +0.250 |
Merchants | +0.233 |
Neg logit contributions | |
ta | -0.227 |
Else | -0.226 |
core | -0.224 |
Defendants | -0.224 |
cial | -0.220 |
Token | . |
Token ID | 13 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
ta | +0.057 |
Else | +0.057 |
core | +0.057 |
Defendants | +0.057 |
cial | +0.056 |
Neg logit contributions | |
thur | -0.064 |
andise | -0.062 |
gee | -0.060 |
boa | -0.058 |
Merchants | -0.054 |
Token | NOR |
Token ID | 25273 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
ta | +0.024 |
Else | +0.024 |
core | +0.024 |
Defendants | +0.024 |
cial | +0.023 |
Neg logit contributions | |
thur | -0.029 |
andise | -0.028 |
gee | -0.027 |
boa | -0.027 |
Merchants | -0.025 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ta | +0.162 |
Else | +0.162 |
core | +0.160 |
Defendants | +0.160 |
cial | +0.156 |
Neg logit contributions | |
thur | -0.215 |
andise | -0.208 |
gee | -0.203 |
boa | -0.197 |
Merchants | -0.184 |
Token | Ed |
Token ID | 1717 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
thur | +0.217 |
andise | +0.210 |
gee | +0.205 |
boa | +0.199 |
Merchants | +0.185 |
Neg logit contributions | |
ta | -0.168 |
Else | -0.168 |
Defendants | -0.166 |
core | -0.166 |
cial | -0.163 |
Token | v |
Token ID | 85 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
thur | +0.244 |
andise | +0.236 |
gee | +0.231 |
boa | +0.225 |
Merchants | +0.210 |
Neg logit contributions | |
ta | -0.167 |
Else | -0.167 |
core | -0.166 |
Defendants | -0.165 |
cial | -0.162 |
Token | ald |
Token ID | 1940 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Else | +0.103 |
ta | +0.102 |
Defendants | +0.099 |
core | +0.099 |
cial | +0.094 |
Neg logit contributions | |
thur | -0.456 |
andise | -0.446 |
gee | -0.439 |
boa | -0.431 |
Merchants | -0.410 |
Token | Bo |
Token ID | 3248 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
thur | +2.148 |
andise | +2.090 |
gee | +2.036 |
boa | +1.996 |
heed | +1.867 |
Neg logit contributions | |
ta | -1.019 |
Defendants | -0.981 |
Else | -0.969 |
core | -0.961 |
Secondary | -0.945 |
Token | ass |
Token ID | 562 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
ta | +0.014 |
Else | +0.014 |
core | +0.013 |
Defendants | +0.013 |
cial | +0.013 |
Neg logit contributions | |
thur | -0.046 |
andise | -0.045 |
gee | -0.045 |
boa | -0.044 |
Merchants | -0.042 |
Token | on |
Token ID | 261 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
thur | +0.360 |
andise | +0.350 |
gee | +0.343 |
boa | +0.333 |
Merchants | +0.313 |
Neg logit contributions | |
ta | -0.231 |
Else | -0.230 |
core | -0.228 |
Defendants | -0.227 |
cial | -0.223 |
Token | H |
Token ID | 367 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Else | +0.265 |
ta | +0.264 |
core | +0.261 |
Defendants | +0.261 |
cial | +0.256 |
Neg logit contributions | |
thur | -0.330 |
andise | -0.321 |
gee | -0.312 |
boa | -0.304 |
Merchants | -0.283 |
Token | agen |
Token ID | 11286 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
thur | +0.326 |
andise | +0.317 |
gee | +0.310 |
boa | +0.304 |
Merchants | +0.285 |
Neg logit contributions | |
ta | -0.179 |
Else | -0.178 |
core | -0.176 |
Defendants | -0.176 |
cial | -0.171 |
Token | . |
Token ID | 13 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
ta | +0.017 |
Else | +0.017 |
core | +0.017 |
Defendants | +0.017 |
cial | +0.016 |
Neg logit contributions | |
thur | -0.020 |
andise | -0.019 |
gee | -0.019 |
boa | -0.018 |
Merchants | -0.017 |
Token | Oh |
Token ID | 3966 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
thur | +0.052 |
andise | +0.051 |
gee | +0.049 |
boa | +0.048 |
Merchants | +0.045 |
Neg logit contributions | |
ta | -0.044 |
Else | -0.044 |
core | -0.044 |
Defendants | -0.044 |
cial | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +5.96e-03 |
Pos logit contributions | |
ta | +0.061 |
Else | +0.061 |
core | +0.060 |
Defendants | +0.060 |
cial | +0.059 |
Neg logit contributions | |
thur | -0.069 |
andise | -0.066 |
gee | -0.065 |
boa | -0.063 |
Merchants | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ta | +0.004 |
Else | +0.004 |
core | +0.004 |
Defendants | +0.004 |
cial | +0.004 |
Neg logit contributions | |
thur | -0.004 |
andise | -0.004 |
gee | -0.004 |
boa | -0.004 |
Merchants | -0.004 |
Token | Hamp |
Token ID | 13039 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
thur | +0.096 |
andise | +0.093 |
gee | +0.091 |
boa | +0.088 |
Merchants | +0.082 |
Neg logit contributions | |
ta | -0.074 |
Else | -0.074 |
core | -0.073 |
Defendants | -0.073 |
cial | -0.072 |
Token | us |
Token ID | 385 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ta | +0.313 |
Else | +0.313 |
Defendants | +0.307 |
core | +0.307 |
cial | +0.301 |
Neg logit contributions | |
thur | -0.476 |
andise | -0.461 |
gee | -0.451 |
boa | -0.439 |
Merchants | -0.412 |
Token | Lind |
Token ID | 9329 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
thur | +1.989 |
gee | +1.896 |
andise | +1.895 |
boa | +1.850 |
Merchants | +1.721 |
Neg logit contributions | |
ta | -1.068 |
core | -1.061 |
Else | -1.053 |
Defendants | -1.040 |
Secondary | -1.024 |
Token | holm |
Token ID | 22981 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
thur | +0.375 |
andise | +0.355 |
gee | +0.342 |
boa | +0.329 |
Merchants | +0.292 |
Neg logit contributions | |
ta | -0.636 |
Else | -0.633 |
core | -0.631 |
Defendants | -0.628 |
cial | -0.620 |
Token | of |
Token ID | 286 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
thur | +0.132 |
andise | +0.128 |
gee | +0.125 |
boa | +0.121 |
Merchants | +0.113 |
Neg logit contributions | |
ta | -0.105 |
Else | -0.105 |
core | -0.104 |
Defendants | -0.103 |
cial | -0.101 |
Token | the |
Token ID | 262 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ta | +0.098 |
Else | +0.098 |
core | +0.097 |
Defendants | +0.097 |
cial | +0.095 |
Neg logit contributions | |
thur | -0.124 |
andise | -0.120 |
gee | -0.117 |
boa | -0.114 |
Merchants | -0.106 |
Token | Anaheim |
Token ID | 31100 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
ta | +0.130 |
Else | +0.130 |
core | +0.128 |
Defendants | +0.128 |
cial | +0.126 |
Neg logit contributions | |
thur | -0.189 |
andise | -0.183 |
gee | -0.179 |
boa | -0.174 |
Merchants | -0.163 |
Token | right |
Token ID | 826 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ta | +0.227 |
Else | +0.227 |
core | +0.225 |
Defendants | +0.224 |
cial | +0.220 |
Neg logit contributions | |
thur | -0.282 |
andise | -0.273 |
gee | -0.267 |
boa | -0.260 |
Merchants | -0.242 |
Token | wing |
Token ID | 8539 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ta | +0.102 |
Else | +0.102 |
core | +0.101 |
Defendants | +0.101 |
cial | +0.099 |
Neg logit contributions | |
thur | -0.137 |
andise | -0.133 |
gee | -0.130 |
boa | -0.127 |
Merchants | -0.118 |
Token | - |
Token ID | 12 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Else | +0.205 |
ta | +0.205 |
Defendants | +0.202 |
core | +0.202 |
cial | +0.198 |
Neg logit contributions | |
thur | -0.269 |
andise | -0.260 |
gee | -0.254 |
boa | -0.248 |
Merchants | -0.231 |
Token | back |
Token ID | 1891 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ta | +0.115 |
Else | +0.115 |
Defendants | +0.114 |
core | +0.113 |
cial | +0.111 |
Neg logit contributions | |
thur | -0.170 |
andise | -0.164 |
gee | -0.161 |
boa | -0.157 |
Merchants | -0.146 |
Token | Paul |
Token ID | 3362 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
ta | +0.161 |
Else | +0.161 |
Defendants | +0.159 |
core | +0.159 |
cial | +0.156 |
Neg logit contributions | |
thur | -0.212 |
andise | -0.205 |
gee | -0.201 |
boa | -0.195 |
Merchants | -0.182 |
Token | Ver |
Token ID | 4643 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
ta | +0.017 |
Else | +0.017 |
core | +0.017 |
Defendants | +0.017 |
cial | +0.016 |
Neg logit contributions | |
thur | -0.015 |
andise | -0.015 |
gee | -0.014 |
boa | -0.014 |
Merchants | -0.013 |
Token | ha |
Token ID | 3099 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
thur | +1.833 |
andise | +1.782 |
gee | +1.727 |
boa | +1.680 |
Merchants | +1.617 |
Neg logit contributions | |
core | -1.165 |
ta | -1.157 |
Defendants | -1.134 |
cial | -1.133 |
Else | -1.115 |
Token | e |
Token ID | 68 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Else | +0.839 |
ta | +0.839 |
Defendants | +0.836 |
core | +0.831 |
cial | +0.822 |
Neg logit contributions | |
thur | -0.460 |
andise | -0.433 |
gee | -0.419 |
boa | -0.391 |
endi | -0.350 |
Token | gh |
Token ID | 456 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
ta | +1.221 |
Defendants | +1.219 |
Else | +1.216 |
core | +1.183 |
Secondary | +1.181 |
Neg logit contributions | |
thur | -1.297 |
gee | -1.237 |
andise | -1.232 |
boa | -1.191 |
Merchants | -1.088 |
Token | sacrificed |
Token ID | 27445 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ta | +0.040 |
Else | +0.040 |
core | +0.040 |
Defendants | +0.040 |
cial | +0.039 |
Neg logit contributions | |
thur | -0.053 |
andise | -0.051 |
gee | -0.050 |
boa | -0.049 |
Merchants | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
thur | +0.099 |
andise | +0.096 |
gee | +0.093 |
boa | +0.091 |
Merchants | +0.084 |
Neg logit contributions | |
ta | -0.077 |
Else | -0.077 |
core | -0.076 |
Defendants | -0.076 |
cial | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
thur | +0.049 |
andise | +0.048 |
gee | +0.047 |
boa | +0.045 |
Merchants | +0.042 |
Neg logit contributions | |
ta | -0.038 |
Else | -0.037 |
core | -0.037 |
Defendants | -0.037 |
cial | -0.036 |
Token | Americans |
Token ID | 3399 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
thur | +0.277 |
andise | +0.269 |
gee | +0.263 |
boa | +0.255 |
Merchants | +0.238 |
Neg logit contributions | |
ta | -0.202 |
Else | -0.200 |
core | -0.199 |
Defendants | -0.198 |
cial | -0.194 |
Token | ." |
Token ID | 526 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Else | +0.159 |
ta | +0.159 |
Defendants | +0.157 |
core | +0.157 |
cial | +0.154 |
Neg logit contributions | |
thur | -0.203 |
andise | -0.197 |
gee | -0.192 |
boa | -0.187 |
Merchants | -0.174 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
thur | +0.083 |
andise | +0.080 |
gee | +0.078 |
boa | +0.075 |
Merchants | +0.070 |
Neg logit contributions | |
ta | -0.077 |
Else | -0.077 |
core | -0.076 |
Defendants | -0.076 |
cial | -0.075 |
Token | GL |
Token ID | 8763 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ta | +0.007 |
Else | +0.007 |
core | +0.007 |
Defendants | +0.007 |
cial | +0.007 |
Neg logit contributions | |
thur | -0.008 |
andise | -0.008 |
gee | -0.008 |
boa | -0.007 |
Merchants | -0.007 |
Token | AS |
Token ID | 1921 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ta | +0.130 |
Else | +0.130 |
core | +0.128 |
Defendants | +0.128 |
cial | +0.125 |
Neg logit contributions | |
thur | -0.226 |
andise | -0.220 |
gee | -0.215 |
boa | -0.210 |
Merchants | -0.198 |
Token | G |
Token ID | 38 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
thur | +1.411 |
andise | +1.356 |
gee | +1.316 |
boa | +1.265 |
endi | +1.163 |
Neg logit contributions | |
core | -1.546 |
ta | -1.542 |
Else | -1.533 |
Defendants | -1.520 |
cial | -1.503 |
Token | OW |
Token ID | 3913 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
thur | +1.060 |
andise | +1.039 |
gee | +1.020 |
boa | +0.994 |
Merchants | +0.939 |
Neg logit contributions | |
ta | -0.415 |
Else | -0.411 |
Defendants | -0.407 |
core | -0.405 |
Secondary | -0.392 |
Token | - |
Token ID | 532 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
thur | +0.196 |
andise | +0.190 |
gee | +0.185 |
boa | +0.180 |
Merchants | +0.167 |
Neg logit contributions | |
ta | -0.167 |
Else | -0.166 |
core | -0.165 |
Defendants | -0.165 |
cial | -0.161 |
Token | Although |
Token ID | 4900 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ta | +0.034 |
Else | +0.034 |
core | +0.033 |
Defendants | +0.033 |
cial | +0.033 |
Neg logit contributions | |
thur | -0.038 |
andise | -0.037 |
gee | -0.036 |
boa | -0.035 |
Merchants | -0.032 |
Token | he |
Token ID | 339 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
ta | +0.143 |
Else | +0.143 |
core | +0.142 |
Defendants | +0.141 |
cial | +0.139 |
Neg logit contributions | |
thur | -0.188 |
andise | -0.182 |
gee | -0.178 |
boa | -0.173 |
Merchants | -0.161 |
Token | Your |
Token ID | 3406 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
thur | +0.339 |
andise | +0.329 |
gee | +0.321 |
boa | +0.313 |
heed | +0.290 |
Neg logit contributions | |
ta | -0.259 |
Else | -0.256 |
Defendants | -0.255 |
core | -0.255 |
cial | -0.249 |
Token | Name |
Token ID | 6530 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
thur | +0.541 |
andise | +0.525 |
gee | +0.514 |
boa | +0.505 |
Merchants | +0.473 |
Neg logit contributions | |
ta | -0.267 |
Else | -0.264 |
Defendants | -0.262 |
core | -0.262 |
cial | -0.254 |
Token | Add |
Token ID | 3060 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
thur | +0.530 |
andise | +0.513 |
gee | +0.498 |
boa | +0.485 |
heed | +0.447 |
Neg logit contributions | |
ta | -0.505 |
Else | -0.500 |
Defendants | -0.499 |
core | -0.498 |
cial | -0.487 |
Token | a |
Token ID | 257 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
thur | +1.017 |
andise | +0.979 |
gee | +0.972 |
boa | +0.941 |
Merchants | +0.874 |
Neg logit contributions | |
ta | -0.724 |
Else | -0.703 |
core | -0.701 |
Defendants | -0.699 |
Secondary | -0.687 |
Token | comment |
Token ID | 2912 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
thur | +0.789 |
andise | +0.763 |
gee | +0.748 |
boa | +0.722 |
Merchants | +0.663 |
Neg logit contributions | |
ta | -0.721 |
Else | -0.701 |
core | -0.701 |
Defendants | -0.700 |
cial | -0.693 |
Token | here |
Token ID | 994 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
thur | +0.540 |
andise | +0.525 |
gee | +0.510 |
boa | +0.499 |
Merchants | +0.459 |
Neg logit contributions | |
ta | -0.466 |
core | -0.459 |
Else | -0.459 |
Defendants | -0.458 |
cial | -0.448 |
Token | Ver |
Token ID | 4643 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
thur | +0.914 |
andise | +0.892 |
gee | +0.840 |
boa | +0.813 |
heed | +0.699 |
Neg logit contributions | |
ta | -2.049 |
core | -1.999 |
Defendants | -1.993 |
Secondary | -1.980 |
Else | -1.967 |
Token | ification |
Token ID | 2649 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
thur | +1.023 |
andise | +0.984 |
gee | +0.954 |
boa | +0.929 |
heed | +0.873 |
Neg logit contributions | |
ta | -0.730 |
core | -0.722 |
Else | -0.717 |
Defendants | -0.714 |
cial | -0.706 |
Token | Send |
Token ID | 16290 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
thur | +0.390 |
andise | +0.375 |
gee | +0.365 |
boa | +0.355 |
Merchants | +0.327 |
Neg logit contributions | |
ta | -0.343 |
Else | -0.341 |
core | -0.339 |
Defendants | -0.338 |
cial | -0.331 |
Token | Email |
Token ID | 9570 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
thur | +0.067 |
andise | +0.065 |
gee | +0.063 |
boa | +0.061 |
Merchants | +0.057 |
Neg logit contributions | |
ta | -0.060 |
Else | -0.060 |
core | -0.059 |
Defendants | -0.059 |
cial | -0.058 |
Token | Cancel |
Token ID | 27910 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
thur | +0.494 |
andise | +0.480 |
gee | +0.470 |
boa | +0.459 |
Merchants | +0.431 |
Neg logit contributions | |
ta | -0.282 |
Else | -0.277 |
core | -0.276 |
Defendants | -0.275 |
Secondary | -0.266 |
Token | told |
Token ID | 1297 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
thur | +0.080 |
andise | +0.077 |
gee | +0.075 |
boa | +0.073 |
Merchants | +0.068 |
Neg logit contributions | |
ta | -0.059 |
Else | -0.059 |
core | -0.058 |
Defendants | -0.058 |
cial | -0.057 |
Token | Fox |
Token ID | 5426 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
thur | +0.336 |
andise | +0.325 |
gee | +0.317 |
boa | +0.308 |
Merchants | +0.286 |
Neg logit contributions | |
ta | -0.263 |
Else | -0.261 |
core | -0.259 |
Defendants | -0.259 |
cial | -0.253 |
Token | News |
Token ID | 3000 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
thur | +0.462 |
andise | +0.447 |
gee | +0.435 |
boa | +0.423 |
Merchants | +0.391 |
Neg logit contributions | |
ta | -0.407 |
Else | -0.404 |
core | -0.403 |
Defendants | -0.402 |
cial | -0.394 |
Token | host |
Token ID | 2583 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
thur | +0.460 |
andise | +0.445 |
gee | +0.434 |
boa | +0.421 |
Merchants | +0.391 |
Neg logit contributions | |
ta | -0.382 |
Else | -0.379 |
core | -0.378 |
Defendants | -0.376 |
cial | -0.369 |
Token | Laura |
Token ID | 16753 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
thur | +0.514 |
andise | +0.497 |
gee | +0.483 |
boa | +0.469 |
heed | +0.434 |
Neg logit contributions | |
ta | -0.449 |
Else | -0.444 |
core | -0.443 |
Defendants | -0.442 |
cial | -0.432 |
Token | Ing |
Token ID | 17589 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
thur | +0.811 |
andise | +0.780 |
gee | +0.758 |
boa | +0.742 |
heed | +0.692 |
Neg logit contributions | |
ta | -0.603 |
Defendants | -0.594 |
core | -0.591 |
Else | -0.591 |
cial | -0.578 |
Token | raham |
Token ID | 13220 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
thur | +0.735 |
andise | +0.706 |
gee | +0.652 |
boa | +0.626 |
Merchants | +0.527 |
Neg logit contributions | |
core | -2.131 |
ta | -2.129 |
Else | -2.109 |
cial | -2.088 |
Defendants | -2.085 |
Token | that |
Token ID | 326 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
thur | +0.269 |
andise | +0.261 |
gee | +0.255 |
boa | +0.248 |
Merchants | +0.230 |
Neg logit contributions | |
ta | -0.209 |
Else | -0.208 |
core | -0.206 |
Defendants | -0.206 |
cial | -0.201 |
Token | initial |
Token ID | 4238 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
ta | +0.055 |
Else | +0.055 |
core | +0.054 |
Defendants | +0.054 |
cial | +0.053 |
Neg logit contributions | |
thur | -0.068 |
andise | -0.066 |
gee | -0.064 |
boa | -0.062 |
Merchants | -0.058 |
Token | funding |
Token ID | 4918 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
thur | +0.013 |
andise | +0.012 |
gee | +0.012 |
boa | +0.012 |
Merchants | +0.011 |
Neg logit contributions | |
ta | -0.009 |
Else | -0.009 |
core | -0.009 |
Defendants | -0.009 |
cial | -0.008 |
Token | for |
Token ID | 329 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
ta | +0.118 |
Else | +0.118 |
core | +0.116 |
Defendants | +0.116 |
cial | +0.114 |
Neg logit contributions | |
thur | -0.147 |
andise | -0.142 |
gee | -0.139 |
boa | -0.135 |
Merchants | -0.125 |
Token | go |
Token ID | 467 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
thur | +0.129 |
andise | +0.124 |
gee | +0.120 |
boa | +0.116 |
Merchants | +0.106 |
Neg logit contributions | |
ta | -0.150 |
Else | -0.149 |
core | -0.148 |
Defendants | -0.148 |
cial | -0.146 |
Token | to |
Token ID | 284 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
ta | +0.114 |
Else | +0.113 |
Defendants | +0.112 |
core | +0.112 |
cial | +0.110 |
Neg logit contributions | |
thur | -0.151 |
andise | -0.146 |
gee | -0.143 |
boa | -0.139 |
Merchants | -0.130 |
Token | book |
Token ID | 1492 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
thur | +0.046 |
andise | +0.045 |
gee | +0.044 |
boa | +0.043 |
Merchants | +0.040 |
Neg logit contributions | |
ta | -0.033 |
Else | -0.033 |
core | -0.033 |
Defendants | -0.033 |
cial | -0.032 |
Token | shop |
Token ID | 24643 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
thur | +0.145 |
andise | +0.134 |
gee | +0.126 |
boa | +0.118 |
Merchants | +0.096 |
Neg logit contributions | |
ta | -0.451 |
Else | -0.449 |
core | -0.448 |
Defendants | -0.446 |
cial | -0.442 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
thur | +0.470 |
andise | +0.453 |
gee | +0.442 |
boa | +0.431 |
Merchants | +0.399 |
Neg logit contributions | |
ta | -0.409 |
Else | -0.406 |
core | -0.405 |
Defendants | -0.402 |
cial | -0.395 |
Token | the |
Token ID | 1169 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
thur | +0.835 |
andise | +0.808 |
gee | +0.785 |
boa | +0.762 |
Merchants | +0.706 |
Neg logit contributions | |
ta | -0.779 |
Else | -0.777 |
core | -0.777 |
Defendants | -0.770 |
cial | -0.753 |
Token | guard |
Token ID | 14864 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
thur | +1.248 |
andise | +1.197 |
gee | +1.171 |
boa | +1.120 |
Merchants | +1.046 |
Neg logit contributions | |
ta | -1.507 |
core | -1.503 |
Else | -1.479 |
Defendants | -1.471 |
Secondary | -1.444 |
Token | ian |
Token ID | 666 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
Else | +0.322 |
ta | +0.322 |
Defendants | +0.319 |
core | +0.319 |
cial | +0.314 |
Neg logit contributions | |
thur | -0.234 |
andise | -0.225 |
gee | -0.217 |
boa | -0.209 |
Merchants | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
thur | +0.294 |
andise | +0.284 |
gee | +0.277 |
boa | +0.269 |
Merchants | +0.249 |
Neg logit contributions | |
ta | -0.260 |
Else | -0.259 |
core | -0.257 |
Defendants | -0.256 |
cial | -0.252 |
Token | com |
Token ID | 785 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
thur | +0.576 |
andise | +0.562 |
gee | +0.547 |
boa | +0.537 |
Merchants | +0.505 |
Neg logit contributions | |
ta | -0.310 |
Else | -0.307 |
core | -0.306 |
Defendants | -0.303 |
cial | -0.296 |
Token | or |
Token ID | 393 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
thur | +0.354 |
andise | +0.340 |
gee | +0.333 |
boa | +0.322 |
Merchants | +0.297 |
Neg logit contributions | |
ta | -0.335 |
Else | -0.333 |
core | -0.331 |
Defendants | -0.330 |
cial | -0.324 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
thur | +0.760 |
andise | +0.737 |
gee | +0.722 |
boa | +0.704 |
heed | +0.650 |
Neg logit contributions | |
ta | -0.591 |
Else | -0.581 |
Defendants | -0.577 |
core | -0.574 |
cial | -0.560 |
Token | ). |
Token ID | 737 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
thur | +0.528 |
andise | +0.509 |
gee | +0.496 |
boa | +0.481 |
Merchants | +0.446 |
Neg logit contributions | |
ta | -0.466 |
Else | -0.464 |
core | -0.462 |
Defendants | -0.460 |
cial | -0.450 |
Token |
|
Token ID | 198 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
thur | +0.620 |
andise | +0.598 |
gee | +0.581 |
boa | +0.569 |
heed | +0.526 |
Neg logit contributions | |
ta | -0.534 |
Else | -0.532 |
core | -0.528 |
Defendants | -0.528 |
cial | -0.519 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
thur | +0.199 |
andise | +0.192 |
gee | +0.187 |
boa | +0.182 |
Merchants | +0.169 |
Neg logit contributions | |
ta | -0.178 |
Else | -0.177 |
core | -0.176 |
Defendants | -0.175 |
cial | -0.172 |
Token | You |
Token ID | 1639 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
thur | +0.728 |
andise | +0.693 |
gee | +0.673 |
boa | +0.661 |
Merchants | +0.613 |
Neg logit contributions | |
Else | -0.679 |
ta | -0.670 |
core | -0.668 |
Defendants | -0.660 |
cial | -0.654 |
Token | can |
Token ID | 460 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
thur | +0.195 |
andise | +0.188 |
gee | +0.184 |
boa | +0.179 |
Merchants | +0.167 |
Neg logit contributions | |
ta | -0.144 |
Else | -0.144 |
core | -0.143 |
Defendants | -0.142 |
cial | -0.139 |
Token | buy |
Token ID | 2822 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
thur | +1.686 |
andise | +1.598 |
gee | +1.576 |
boa | +1.533 |
heed | +1.443 |
Neg logit contributions | |
ta | -1.118 |
core | -1.100 |
Defendants | -1.082 |
Else | -1.075 |
Secondary | -1.058 |
Token | An |
Token ID | 1052 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
thur | +0.945 |
andise | +0.900 |
gee | +0.882 |
boa | +0.859 |
endi | +0.787 |
Neg logit contributions | |
Else | -0.951 |
Defendants | -0.948 |
ta | -0.948 |
core | -0.947 |
Secondary | -0.918 |
Token | Enemy |
Token ID | 21785 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
thur | +0.191 |
andise | +0.184 |
gee | +0.178 |
boa | +0.172 |
Merchants | +0.157 |
Neg logit contributions | |
ta | -0.234 |
Else | -0.234 |
core | -0.232 |
Defendants | -0.232 |
cial | -0.228 |
Token | of |
Token ID | 286 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
thur | +0.200 |
andise | +0.193 |
gee | +0.189 |
boa | +0.184 |
Merchants | +0.170 |
Neg logit contributions | |
ta | -0.156 |
Else | -0.155 |
core | -0.154 |
Defendants | -0.154 |
cial | -0.151 |
Token | the |
Token ID | 262 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
ta | +0.659 |
Else | +0.656 |
core | +0.653 |
Defendants | +0.650 |
cial | +0.636 |
Neg logit contributions | |
thur | -0.774 |
andise | -0.749 |
gee | -0.733 |
boa | -0.705 |
Merchants | -0.669 |
Token |
|
Token ID | 198 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
thur | +0.090 |
andise | +0.087 |
gee | +0.085 |
boa | +0.083 |
Merchants | +0.076 |
Neg logit contributions | |
ta | -0.081 |
Else | -0.081 |
core | -0.081 |
Defendants | -0.080 |
cial | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
ta | +0.040 |
Else | +0.039 |
core | +0.039 |
Defendants | +0.039 |
cial | +0.038 |
Neg logit contributions | |
thur | -0.043 |
andise | -0.042 |
gee | -0.041 |
boa | -0.040 |
Merchants | -0.037 |
Token | Travel |
Token ID | 33074 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
ta | +0.143 |
Else | +0.143 |
Defendants | +0.142 |
core | +0.141 |
cial | +0.139 |
Neg logit contributions | |
thur | -0.136 |
andise | -0.131 |
gee | -0.128 |
boa | -0.124 |
Merchants | -0.114 |
Token | With |
Token ID | 2080 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
thur | +0.022 |
andise | +0.021 |
gee | +0.021 |
boa | +0.020 |
Merchants | +0.019 |
Neg logit contributions | |
ta | -0.020 |
Else | -0.020 |
core | -0.019 |
Defendants | -0.019 |
cial | -0.019 |
Token | The |
Token ID | 383 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
thur | +0.056 |
andise | +0.054 |
gee | +0.053 |
boa | +0.051 |
Merchants | +0.047 |
Neg logit contributions | |
ta | -0.062 |
Else | -0.062 |
core | -0.061 |
Defendants | -0.061 |
cial | -0.060 |
Token | Nation |
Token ID | 8741 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
ta | +0.298 |
Else | +0.297 |
core | +0.294 |
Defendants | +0.294 |
cial | +0.290 |
Neg logit contributions | |
thur | -0.290 |
andise | -0.279 |
gee | -0.272 |
boa | -0.262 |
Merchants | -0.243 |
Token | Be |
Token ID | 1355 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
thur | +1.649 |
andise | +1.596 |
gee | +1.566 |
boa | +1.525 |
heed | +1.424 |
Neg logit contributions | |
ta | -1.118 |
Else | -1.092 |
Defendants | -1.088 |
core | -1.087 |
Secondary | -1.071 |
Token | the |
Token ID | 262 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
thur | +0.317 |
andise | +0.307 |
gee | +0.299 |
boa | +0.291 |
Merchants | +0.270 |
Neg logit contributions | |
ta | -0.243 |
Else | -0.241 |
core | -0.239 |
Defendants | -0.239 |
cial | -0.235 |
Token | first |
Token ID | 717 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
thur | +0.752 |
andise | +0.731 |
gee | +0.711 |
boa | +0.688 |
Merchants | +0.641 |
Neg logit contributions | |
ta | -0.589 |
Else | -0.580 |
Defendants | -0.580 |
core | -0.578 |
cial | -0.565 |
Token | to |
Token ID | 284 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
thur | +1.150 |
andise | +1.116 |
gee | +1.092 |
boa | +1.057 |
Merchants | +0.993 |
Neg logit contributions | |
ta | -0.788 |
core | -0.765 |
Defendants | -0.757 |
Else | -0.754 |
cial | -0.750 |
Token | hear |
Token ID | 3285 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
thur | +0.313 |
andise | +0.302 |
gee | +0.293 |
boa | +0.285 |
Merchants | +0.263 |
Neg logit contributions | |
ta | -0.293 |
Else | -0.291 |
core | -0.290 |
Defendants | -0.289 |
cial | -0.284 |
Token | Queensland |
Token ID | 21105 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Else | +0.184 |
ta | +0.184 |
core | +0.182 |
Defendants | +0.182 |
cial | +0.178 |
Neg logit contributions | |
thur | -0.279 |
andise | -0.271 |
gee | -0.265 |
boa | -0.258 |
Merchants | -0.242 |
Token | , |
Token ID | 11 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
ta | +0.090 |
Else | +0.090 |
core | +0.089 |
Defendants | +0.089 |
cial | +0.087 |
Neg logit contributions | |
thur | -0.104 |
andise | -0.101 |
gee | -0.098 |
boa | -0.095 |
Merchants | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ta | +0.221 |
Else | +0.221 |
core | +0.219 |
Defendants | +0.218 |
cial | +0.214 |
Neg logit contributions | |
thur | -0.279 |
andise | -0.270 |
gee | -0.264 |
boa | -0.257 |
Merchants | -0.239 |
Token | b |
Token ID | 275 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Else | +0.252 |
ta | +0.252 |
core | +0.249 |
Defendants | +0.248 |
cial | +0.244 |
Neg logit contributions | |
thur | -0.341 |
andise | -0.329 |
gee | -0.322 |
boa | -0.314 |
Merchants | -0.292 |
Token | ic |
Token ID | 291 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
thur | +0.295 |
andise | +0.288 |
gee | +0.283 |
boa | +0.277 |
Merchants | +0.265 |
Neg logit contributions | |
ta | -0.088 |
Else | -0.088 |
core | -0.086 |
Defendants | -0.086 |
cial | -0.083 |
Token | am |
Token ID | 321 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ta | +0.300 |
Else | +0.300 |
Defendants | +0.298 |
core | +0.297 |
cial | +0.293 |
Neg logit contributions | |
thur | -0.216 |
andise | -0.206 |
gee | -0.200 |
boa | -0.192 |
Merchants | -0.173 |
Token | eral |
Token ID | 1691 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
thur | +0.908 |
andise | +0.855 |
gee | +0.811 |
boa | +0.772 |
Merchants | +0.712 |
Neg logit contributions | |
ta | -1.835 |
core | -1.834 |
cial | -1.819 |
Defendants | -1.808 |
Else | -1.807 |
Token | in |
Token ID | 287 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Else | +0.248 |
ta | +0.248 |
Defendants | +0.245 |
core | +0.245 |
cial | +0.240 |
Neg logit contributions | |
thur | -0.316 |
andise | -0.305 |
gee | -0.298 |
boa | -0.290 |
Merchants | -0.270 |
Token | the |
Token ID | 262 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
ta | +0.099 |
Else | +0.099 |
core | +0.097 |
Defendants | +0.097 |
cial | +0.095 |
Neg logit contributions | |
thur | -0.131 |
andise | -0.127 |
gee | -0.124 |
boa | -0.120 |
Merchants | -0.112 |
Token | other |
Token ID | 584 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Else | +0.167 |
ta | +0.167 |
core | +0.164 |
Defendants | +0.164 |
cial | +0.159 |
Neg logit contributions | |
thur | -0.456 |
andise | -0.444 |
gee | -0.437 |
boa | -0.427 |
Merchants | -0.406 |
Token | states |
Token ID | 2585 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
ta | +0.065 |
Else | +0.064 |
core | +0.064 |
Defendants | +0.064 |
cial | +0.062 |
Neg logit contributions | |
thur | -0.099 |
andise | -0.096 |
gee | -0.094 |
boa | -0.092 |
Merchants | -0.086 |
Token | national |
Token ID | 2260 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
thur | +0.228 |
andise | +0.221 |
gee | +0.216 |
boa | +0.210 |
Merchants | +0.196 |
Neg logit contributions | |
ta | -0.161 |
Else | -0.160 |
core | -0.159 |
Defendants | -0.158 |
cial | -0.155 |
Token | economics |
Token ID | 12446 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
thur | +0.020 |
andise | +0.019 |
gee | +0.019 |
boa | +0.019 |
Merchants | +0.017 |
Neg logit contributions | |
ta | -0.012 |
Else | -0.012 |
core | -0.012 |
Defendants | -0.012 |
cial | -0.012 |
Token | correspondent |
Token ID | 21076 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Else | +0.269 |
ta | +0.269 |
Defendants | +0.266 |
core | +0.264 |
cial | +0.259 |
Neg logit contributions | |
thur | -0.463 |
andise | -0.450 |
gee | -0.441 |
boa | -0.430 |
Merchants | -0.405 |
Token | for |
Token ID | 329 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
thur | +0.115 |
andise | +0.111 |
gee | +0.108 |
boa | +0.105 |
Merchants | +0.098 |
Neg logit contributions | |
ta | -0.091 |
Else | -0.091 |
core | -0.090 |
Defendants | -0.090 |
cial | -0.088 |
Token | McCl |
Token ID | 23780 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
thur | +0.200 |
andise | +0.193 |
gee | +0.189 |
boa | +0.184 |
Merchants | +0.170 |
Neg logit contributions | |
ta | -0.162 |
Else | -0.162 |
core | -0.160 |
Defendants | -0.160 |
cial | -0.157 |
Token | atch |
Token ID | 963 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
thur | +0.696 |
andise | +0.678 |
gee | +0.664 |
boa | +0.644 |
Merchants | +0.602 |
Neg logit contributions | |
ta | -0.508 |
core | -0.504 |
Else | -0.502 |
Defendants | -0.496 |
cial | -0.488 |
Token | y |
Token ID | 88 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
thur | +1.730 |
andise | +1.697 |
gee | +1.645 |
boa | +1.638 |
Merchants | +1.529 |
Neg logit contributions | |
core | -0.972 |
ta | -0.969 |
Else | -0.956 |
Defendants | -0.951 |
cial | -0.940 |
Token | Newsp |
Token ID | 36765 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
thur | +0.455 |
andise | +0.440 |
gee | +0.429 |
boa | +0.415 |
Merchants | +0.382 |
Neg logit contributions | |
ta | -0.429 |
Else | -0.428 |
core | -0.424 |
Defendants | -0.424 |
cial | -0.416 |
Token | apers |
Token ID | 5656 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
thur | +0.112 |
andise | +0.104 |
gee | +0.098 |
boa | +0.092 |
Merchants | +0.076 |
Neg logit contributions | |
ta | -0.329 |
Else | -0.328 |
core | -0.327 |
Defendants | -0.326 |
cial | -0.323 |
Token | . |
Token ID | 13 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
thur | +0.234 |
andise | +0.226 |
gee | +0.220 |
boa | +0.214 |
Merchants | +0.199 |
Neg logit contributions | |
ta | -0.196 |
Else | -0.195 |
core | -0.194 |
Defendants | -0.193 |
cial | -0.190 |
Token | Jay |
Token ID | 9180 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
thur | +0.372 |
andise | +0.359 |
gee | +0.350 |
boa | +0.341 |
Merchants | +0.315 |
Neg logit contributions | |
ta | -0.307 |
Else | -0.306 |
Defendants | -0.304 |
core | -0.303 |
cial | -0.298 |
Token | Get |
Token ID | 3855 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
ta | +0.108 |
Else | +0.108 |
core | +0.107 |
Defendants | +0.107 |
cial | +0.105 |
Neg logit contributions | |
thur | -0.129 |
andise | -0.125 |
gee | -0.122 |
boa | -0.118 |
Merchants | -0.110 |
Token | The |
Token ID | 383 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
thur | +0.485 |
andise | +0.466 |
gee | +0.452 |
boa | +0.439 |
Merchants | +0.402 |
Neg logit contributions | |
ta | -0.512 |
Else | -0.507 |
Defendants | -0.507 |
core | -0.503 |
cial | -0.496 |
Token | Times |
Token ID | 3782 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
thur | +0.049 |
andise | +0.048 |
gee | +0.046 |
boa | +0.045 |
Merchants | +0.041 |
Neg logit contributions | |
ta | -0.047 |
Else | -0.047 |
core | -0.047 |
Defendants | -0.047 |
cial | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
thur | +0.126 |
andise | +0.122 |
gee | +0.119 |
boa | +0.116 |
Merchants | +0.107 |
Neg logit contributions | |
ta | -0.099 |
Else | -0.099 |
core | -0.098 |
Defendants | -0.098 |
cial | -0.096 |
Token | Israel |
Token ID | 2692 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
thur | +0.236 |
andise | +0.231 |
gee | +0.227 |
boa | +0.223 |
Merchants | +0.212 |
Neg logit contributions | |
ta | -0.062 |
Else | -0.061 |
core | -0.060 |
Defendants | -0.060 |
cial | -0.057 |
Token | 's |
Token ID | 338 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
thur | +0.716 |
andise | +0.688 |
gee | +0.673 |
boa | +0.652 |
Merchants | +0.603 |
Neg logit contributions | |
ta | -0.651 |
Else | -0.644 |
core | -0.642 |
Defendants | -0.639 |
cial | -0.630 |
Token | Daily |
Token ID | 6714 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
thur | +1.593 |
andise | +1.514 |
gee | +1.482 |
boa | +1.462 |
endi | +1.351 |
Neg logit contributions | |
ta | -1.150 |
Defendants | -1.134 |
core | -1.126 |
Else | -1.108 |
Secondary | -1.103 |
Token | Edition |
Token ID | 5061 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
thur | +0.365 |
andise | +0.350 |
gee | +0.341 |
boa | +0.333 |
Merchants | +0.307 |
Neg logit contributions | |
ta | -0.332 |
Else | -0.331 |
core | -0.329 |
Defendants | -0.327 |
cial | -0.321 |
Token | by |
Token ID | 416 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
thur | +0.276 |
andise | +0.266 |
gee | +0.260 |
boa | +0.254 |
Merchants | +0.237 |
Neg logit contributions | |
ta | -0.188 |
Else | -0.186 |
core | -0.185 |
Defendants | -0.184 |
cial | -0.180 |
Token | email |
Token ID | 3053 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
thur | +0.552 |
andise | +0.536 |
gee | +0.524 |
boa | +0.513 |
Merchants | +0.480 |
Neg logit contributions | |
ta | -0.315 |
Else | -0.311 |
Defendants | -0.309 |
core | -0.308 |
cial | -0.301 |
Token | and |
Token ID | 290 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
thur | +0.517 |
andise | +0.498 |
gee | +0.486 |
boa | +0.475 |
Merchants | +0.440 |
Neg logit contributions | |
ta | -0.403 |
Else | -0.398 |
core | -0.397 |
Defendants | -0.397 |
cial | -0.389 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ta | +0.131 |
Else | +0.131 |
core | +0.129 |
Defendants | +0.129 |
cial | +0.127 |
Neg logit contributions | |
thur | -0.155 |
andise | -0.150 |
gee | -0.146 |
boa | -0.142 |
Merchants | -0.132 |
Token | OS |
Token ID | 7294 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
thur | +0.103 |
andise | +0.100 |
gee | +0.097 |
boa | +0.094 |
Merchants | +0.088 |
Neg logit contributions | |
ta | -0.087 |
Else | -0.087 |
Defendants | -0.086 |
core | -0.086 |
cial | -0.084 |
Token | HA |
Token ID | 7801 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
ta | +0.007 |
Else | +0.007 |
core | +0.007 |
Defendants | +0.007 |
cial | +0.007 |
Neg logit contributions | |
thur | -0.007 |
andise | -0.007 |
gee | -0.007 |
boa | -0.006 |
Merchants | -0.006 |
Token | ( |
Token ID | 357 |
Feature activation | -9.96e-03 |
Pos logit contributions | |
ta | +0.031 |
Else | +0.031 |
core | +0.030 |
Defendants | +0.030 |
cial | +0.030 |
Neg logit contributions | |
thur | -0.040 |
andise | -0.039 |
gee | -0.038 |
boa | -0.037 |
Merchants | -0.034 |
Token | Occup |
Token ID | 47658 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
thur | +0.008 |
andise | +0.008 |
gee | +0.008 |
boa | +0.008 |
Merchants | +0.007 |
Neg logit contributions | |
ta | -0.005 |
Else | -0.005 |
core | -0.005 |
Defendants | -0.005 |
cial | -0.005 |
Token | ational |
Token ID | 864 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
thur | +0.342 |
andise | +0.331 |
gee | +0.323 |
boa | +0.315 |
Merchants | +0.294 |
Neg logit contributions | |
ta | -0.258 |
Else | -0.256 |
core | -0.255 |
Defendants | -0.254 |
cial | -0.249 |
Token | Health |
Token ID | 3893 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
thur | +1.130 |
andise | +1.074 |
gee | +1.031 |
boa | +1.021 |
Merchants | +0.906 |
Neg logit contributions | |
ta | -1.486 |
Defendants | -1.478 |
Else | -1.471 |
core | -1.462 |
Secondary | -1.451 |
Token | and |
Token ID | 290 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
thur | +0.014 |
andise | +0.014 |
gee | +0.014 |
boa | +0.013 |
Merchants | +0.012 |
Neg logit contributions | |
ta | -0.012 |
Else | -0.012 |
core | -0.012 |
Defendants | -0.012 |
cial | -0.011 |
Token | Safety |
Token ID | 11233 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
thur | +0.337 |
andise | +0.319 |
gee | +0.305 |
boa | +0.296 |
Merchants | +0.260 |
Neg logit contributions | |
ta | -0.570 |
Else | -0.568 |
Defendants | -0.567 |
core | -0.565 |
Secondary | -0.559 |
Token | Administration |
Token ID | 8694 |
Feature activation | -9.60e-04 |
Pos logit contributions | |
ta | +0.101 |
Else | +0.101 |
core | +0.100 |
Defendants | +0.100 |
cial | +0.098 |
Neg logit contributions | |
thur | -0.091 |
andise | -0.088 |
gee | -0.085 |
boa | -0.082 |
Merchants | -0.076 |
Token | ) |
Token ID | 8 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
thur | +0.001 |
andise | +0.001 |
gee | +0.001 |
boa | +0.001 |
Merchants | +0.001 |
Neg logit contributions | |
ta | -0.001 |
Else | -0.001 |
core | -0.001 |
Defendants | -0.001 |
cial | -0.001 |
Token | fr |
Token ID | 1216 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
thur | +0.178 |
andise | +0.173 |
gee | +0.169 |
boa | +0.164 |
Merchants | +0.153 |
Neg logit contributions | |
ta | -0.138 |
Else | -0.138 |
core | -0.136 |
Defendants | -0.136 |
cial | -0.133 |
Token | atern |
Token ID | 9205 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
thur | +0.429 |
andise | +0.414 |
gee | +0.403 |
boa | +0.391 |
Merchants | +0.362 |
Neg logit contributions | |
ta | -0.417 |
Else | -0.414 |
core | -0.412 |
Defendants | -0.411 |
cial | -0.404 |
Token | ities |
Token ID | 871 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
thur | +0.287 |
andise | +0.274 |
gee | +0.265 |
boa | +0.255 |
Merchants | +0.233 |
Neg logit contributions | |
ta | -0.398 |
Else | -0.397 |
core | -0.395 |
Defendants | -0.393 |
cial | -0.390 |
Token | and |
Token ID | 290 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
thur | +0.096 |
andise | +0.093 |
gee | +0.090 |
boa | +0.088 |
Merchants | +0.082 |
Neg logit contributions | |
ta | -0.081 |
Else | -0.081 |
core | -0.080 |
Defendants | -0.080 |
cial | -0.079 |
Token | sor |
Token ID | 25655 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
thur | +0.118 |
andise | +0.112 |
gee | +0.108 |
boa | +0.103 |
Merchants | +0.092 |
Neg logit contributions | |
ta | -0.196 |
Else | -0.195 |
core | -0.194 |
Defendants | -0.194 |
cial | -0.191 |
Token | or |
Token ID | 273 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ta | +0.100 |
Else | +0.100 |
Defendants | +0.099 |
core | +0.099 |
cial | +0.097 |
Neg logit contributions | |
thur | -0.147 |
andise | -0.143 |
gee | -0.140 |
boa | -0.136 |
Merchants | -0.127 |
Token | ities |
Token ID | 871 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
thur | +1.125 |
andise | +1.091 |
gee | +1.047 |
boa | +1.017 |
Merchants | +0.943 |
Neg logit contributions | |
ta | -1.458 |
Else | -1.446 |
core | -1.444 |
Defendants | -1.440 |
cial | -1.428 |
Token | on |
Token ID | 319 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
thur | +0.054 |
andise | +0.052 |
gee | +0.051 |
boa | +0.050 |
Merchants | +0.046 |
Neg logit contributions | |
ta | -0.047 |
Else | -0.046 |
core | -0.046 |
Defendants | -0.046 |
cial | -0.045 |
Token | campus |
Token ID | 7611 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
thur | +0.371 |
andise | +0.360 |
gee | +0.351 |
boa | +0.341 |
Merchants | +0.318 |
Neg logit contributions | |
ta | -0.282 |
Else | -0.280 |
core | -0.278 |
Defendants | -0.277 |
cial | -0.271 |
Token | ), |
Token ID | 828 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ta | +0.022 |
Else | +0.022 |
core | +0.022 |
Defendants | +0.022 |
cial | +0.022 |
Neg logit contributions | |
thur | -0.026 |
andise | -0.025 |
gee | -0.024 |
boa | -0.024 |
Merchants | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
thur | +0.245 |
andise | +0.237 |
gee | +0.231 |
boa | +0.225 |
Merchants | +0.209 |
Neg logit contributions | |
ta | -0.197 |
Else | -0.196 |
core | -0.195 |
Defendants | -0.194 |
cial | -0.190 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
thur | +0.001 |
andise | +0.001 |
gee | +0.001 |
boa | +0.001 |
Merchants | +0.001 |
Neg logit contributions | |
ta | -0.001 |
Else | -0.001 |
core | -0.001 |
Defendants | -0.001 |
cial | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
thur | +0.107 |
andise | +0.104 |
gee | +0.101 |
boa | +0.098 |
Merchants | +0.091 |
Neg logit contributions | |
ta | -0.096 |
Else | -0.096 |
core | -0.095 |
Defendants | -0.095 |
cial | -0.093 |
Token | Sl |
Token ID | 11122 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
ta | +0.032 |
Else | +0.032 |
core | +0.031 |
Defendants | +0.031 |
cial | +0.031 |
Neg logit contributions | |
thur | -0.038 |
andise | -0.037 |
gee | -0.036 |
boa | -0.035 |
Merchants | -0.032 |
Token | ideshow |
Token ID | 42286 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
ta | +0.191 |
Else | +0.190 |
Defendants | +0.187 |
core | +0.187 |
cial | +0.181 |
Neg logit contributions | |
thur | -0.414 |
andise | -0.402 |
gee | -0.394 |
boa | -0.386 |
Merchants | -0.364 |
Token | ( |
Token ID | 357 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
ta | +0.299 |
Else | +0.298 |
core | +0.295 |
Defendants | +0.295 |
cial | +0.291 |
Neg logit contributions | |
thur | -0.327 |
andise | -0.315 |
gee | -0.307 |
boa | -0.298 |
Merchants | -0.277 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
thur | +0.168 |
andise | +0.162 |
gee | +0.158 |
boa | +0.153 |
Merchants | +0.142 |
Neg logit contributions | |
ta | -0.156 |
Else | -0.156 |
core | -0.154 |
Defendants | -0.154 |
cial | -0.151 |
Token | Images |
Token ID | 5382 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
thur | +0.947 |
andise | +0.884 |
gee | +0.833 |
boa | +0.814 |
heed | +0.711 |
Neg logit contributions | |
ta | -1.681 |
core | -1.667 |
Defendants | -1.663 |
Else | -1.658 |
cial | -1.622 |
Token | ) |
Token ID | 8 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
thur | +0.155 |
andise | +0.150 |
gee | +0.146 |
boa | +0.142 |
Merchants | +0.132 |
Neg logit contributions | |
ta | -0.130 |
Else | -0.129 |
core | -0.128 |
Defendants | -0.128 |
cial | -0.126 |
Token |
|
Token ID | 198 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
ta | +0.143 |
Else | +0.143 |
core | +0.142 |
Defendants | +0.141 |
cial | +0.139 |
Neg logit contributions | |
thur | -0.154 |
andise | -0.148 |
gee | -0.144 |
boa | -0.140 |
Merchants | -0.130 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
thur | +0.028 |
andise | +0.027 |
gee | +0.026 |
boa | +0.025 |
Merchants | +0.024 |
Neg logit contributions | |
ta | -0.025 |
Else | -0.025 |
core | -0.025 |
Defendants | -0.025 |
cial | -0.024 |
Token | SW |
Token ID | 17887 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ta | +0.062 |
Else | +0.062 |
core | +0.062 |
Defendants | +0.062 |
cial | +0.060 |
Neg logit contributions | |
thur | -0.075 |
andise | -0.072 |
gee | -0.070 |
boa | -0.068 |
Merchants | -0.064 |
Token | mail |
Token ID | 4529 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ta | +0.091 |
Else | +0.091 |
Defendants | +0.089 |
core | +0.089 |
cial | +0.087 |
Neg logit contributions | |
thur | -0.180 |
andise | -0.175 |
gee | -0.172 |
boa | -0.168 |
Merchants | -0.159 |
Token | this |
Token ID | 428 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
thur | +1.255 |
andise | +1.227 |
gee | +1.204 |
boa | +1.179 |
isec | +1.089 |
Neg logit contributions | |
ta | -0.891 |
core | -0.878 |
Defendants | -0.874 |
Else | -0.863 |
Secondary | -0.856 |
Token | to |
Token ID | 284 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
thur | +0.753 |
andise | +0.722 |
gee | +0.714 |
boa | +0.696 |
Merchants | +0.649 |
Neg logit contributions | |
ta | -0.528 |
core | -0.515 |
Else | -0.513 |
Defendants | -0.510 |
cial | -0.498 |
Token | a |
Token ID | 257 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Else | +0.384 |
ta | +0.381 |
Defendants | +0.378 |
core | +0.378 |
cial | +0.372 |
Neg logit contributions | |
thur | -0.483 |
andise | -0.467 |
gee | -0.453 |
boa | -0.442 |
Merchants | -0.412 |
Token | friend |
Token ID | 1545 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
thur | +0.183 |
andise | +0.176 |
gee | +0.171 |
boa | +0.166 |
Merchants | +0.152 |
Neg logit contributions | |
ta | -0.201 |
Else | -0.200 |
core | -0.199 |
Defendants | -0.198 |
cial | -0.195 |
Token | Print |
Token ID | 12578 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
thur | +0.512 |
andise | +0.500 |
gee | +0.492 |
boa | +0.484 |
Merchants | +0.459 |
Neg logit contributions | |
ta | -0.125 |
Else | -0.122 |
core | -0.121 |
Defendants | -0.121 |
cial | -0.115 |
Token | able |
Token ID | 540 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
thur | +1.413 |
andise | +1.365 |
gee | +1.341 |
boa | +1.305 |
isec | +1.194 |
Neg logit contributions | |
ta | -1.179 |
core | -1.158 |
Else | -1.146 |
Defendants | -1.146 |
Secondary | -1.126 |
Token | version |
Token ID | 2196 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
thur | +0.815 |
andise | +0.795 |
gee | +0.778 |
boa | +0.756 |
Merchants | +0.699 |
Neg logit contributions | |
ta | -0.623 |
Else | -0.618 |
Defendants | -0.617 |
core | -0.616 |
cial | -0.600 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.19e-03 |
Pos logit contributions | |
ta | +0.274 |
Else | +0.274 |
core | +0.271 |
Defendants | +0.270 |
cial | +0.266 |
Neg logit contributions | |
thur | -0.277 |
andise | -0.268 |
gee | -0.260 |
boa | -0.252 |
Merchants | -0.234 |
Token | Rob |
Token ID | 14350 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
ta | +0.001 |
Else | +0.001 |
core | +0.001 |
Defendants | +0.001 |
cial | +0.001 |
Neg logit contributions | |
thur | -0.002 |
andise | -0.002 |
gee | -0.002 |
boa | -0.001 |
Merchants | -0.001 |
Token | C |
Token ID | 327 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
ta | +0.037 |
Else | +0.037 |
core | +0.037 |
Defendants | +0.037 |
cial | +0.036 |
Neg logit contributions | |
thur | -0.047 |
andise | -0.046 |
gee | -0.045 |
boa | -0.044 |
Merchants | -0.041 |
Token | uk |
Token ID | 2724 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
thur | +0.086 |
andise | +0.084 |
gee | +0.083 |
boa | +0.081 |
Merchants | +0.078 |
Neg logit contributions | |
ta | -0.013 |
Else | -0.013 |
core | -0.012 |
Defendants | -0.012 |
cial | -0.012 |
Token | or |
Token ID | 393 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
thur | +0.513 |
andise | +0.494 |
gee | +0.486 |
boa | +0.471 |
Merchants | +0.434 |
Neg logit contributions | |
ta | -0.475 |
Else | -0.474 |
core | -0.471 |
Defendants | -0.470 |
cial | -0.462 |
Token | call |
Token ID | 869 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
thur | +0.934 |
andise | +0.918 |
gee | +0.888 |
boa | +0.845 |
Merchants | +0.775 |
Neg logit contributions | |
ta | -1.243 |
Else | -1.237 |
core | -1.228 |
Defendants | -1.213 |
cial | -1.205 |
Token | 0 |
Token ID | 657 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
thur | +0.835 |
andise | +0.812 |
gee | +0.793 |
boa | +0.773 |
Merchants | +0.718 |
Neg logit contributions | |
ta | -0.739 |
Else | -0.736 |
core | -0.728 |
Defendants | -0.724 |
Secondary | -0.712 |
Token | 207 |
Token ID | 22745 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ta | +0.374 |
Else | +0.372 |
Defendants | +0.370 |
core | +0.368 |
cial | +0.359 |
Neg logit contributions | |
thur | -0.437 |
andise | -0.419 |
gee | -0.409 |
boa | -0.396 |
Merchants | -0.367 |
Token | 7 |
Token ID | 767 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
thur | +0.857 |
andise | +0.828 |
gee | +0.813 |
boa | +0.795 |
endi | +0.730 |
Neg logit contributions | |
ta | -0.711 |
Else | -0.710 |
core | -0.709 |
Defendants | -0.701 |
cial | -0.695 |
Token | 82 |
Token ID | 6469 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
thur | +1.260 |
andise | +1.236 |
gee | +1.170 |
boa | +1.153 |
endi | +1.047 |
Neg logit contributions | |
Else | -1.310 |
ta | -1.301 |
Defendants | -1.274 |
cial | -1.272 |
core | -1.271 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
thur | +0.053 |
andise | +0.051 |
gee | +0.050 |
boa | +0.048 |
Merchants | +0.045 |
Neg logit contributions | |
ta | -0.045 |
Else | -0.045 |
core | -0.044 |
Defendants | -0.044 |
cial | -0.043 |
Token | 368 |
Token ID | 27412 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
thur | +0.135 |
andise | +0.131 |
gee | +0.127 |
boa | +0.124 |
Merchants | +0.115 |
Neg logit contributions | |
ta | -0.115 |
Else | -0.115 |
core | -0.114 |
Defendants | -0.113 |
cial | -0.112 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.56e-03 |
Pos logit contributions | |
thur | +0.333 |
andise | +0.322 |
gee | +0.314 |
boa | +0.305 |
Merchants | +0.283 |
Neg logit contributions | |
ta | -0.284 |
Else | -0.283 |
core | -0.281 |
Defendants | -0.280 |
cial | -0.275 |
Token | To |
Token ID | 2514 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
thur | +0.006 |
andise | +0.006 |
gee | +0.006 |
boa | +0.006 |
Merchants | +0.005 |
Neg logit contributions | |
ta | -0.005 |
Else | -0.005 |
core | -0.005 |
Defendants | -0.005 |
cial | -0.005 |
Token | I |
Token ID | 314 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ta | +0.087 |
Else | +0.086 |
core | +0.086 |
Defendants | +0.086 |
cial | +0.084 |
Neg logit contributions | |
thur | -0.096 |
andise | -0.093 |
gee | -0.090 |
boa | -0.088 |
Merchants | -0.081 |
Token | started |
Token ID | 2067 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ta | +0.096 |
Else | +0.096 |
core | +0.095 |
Defendants | +0.095 |
cial | +0.093 |
Neg logit contributions | |
thur | -0.121 |
andise | -0.117 |
gee | -0.114 |
boa | -0.111 |
Merchants | -0.103 |
Token | thinking |
Token ID | 3612 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Else | +0.168 |
ta | +0.167 |
core | +0.165 |
Defendants | +0.165 |
cial | +0.162 |
Neg logit contributions | |
thur | -0.242 |
andise | -0.235 |
gee | -0.230 |
boa | -0.224 |
Merchants | -0.209 |
Token | about |
Token ID | 546 |
Feature activation | +8.49e-03 |
Pos logit contributions | |
thur | +0.097 |
andise | +0.094 |
gee | +0.092 |
boa | +0.089 |
Merchants | +0.083 |
Neg logit contributions | |
ta | -0.074 |
Else | -0.074 |
core | -0.073 |
Defendants | -0.073 |
cial | -0.071 |
Token | W |
Token ID | 370 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
ta | +0.005 |
Else | +0.005 |
core | +0.005 |
Defendants | +0.005 |
cial | +0.005 |
Neg logit contributions | |
thur | -0.006 |
andise | -0.006 |
gee | -0.006 |
boa | -0.006 |
Merchants | -0.005 |
Token | ile |
Token ID | 576 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
thur | +0.024 |
andise | +0.023 |
gee | +0.023 |
boa | +0.022 |
Merchants | +0.021 |
Neg logit contributions | |
ta | -0.017 |
Else | -0.017 |
core | -0.017 |
Defendants | -0.017 |
cial | -0.017 |
Token | E |
Token ID | 412 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
thur | +1.272 |
andise | +1.246 |
gee | +1.201 |
boa | +1.167 |
heed | +1.073 |
Neg logit contributions | |
ta | -1.299 |
core | -1.285 |
Else | -1.278 |
Defendants | -1.255 |
Secondary | -1.245 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ta | +0.204 |
Else | +0.204 |
Defendants | +0.201 |
core | +0.201 |
cial | +0.198 |
Neg logit contributions | |
thur | -0.225 |
andise | -0.217 |
gee | -0.212 |
boa | -0.205 |
Merchants | -0.190 |
Token | Coy |
Token ID | 26887 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Else | +0.755 |
ta | +0.747 |
core | +0.740 |
Defendants | +0.738 |
cial | +0.731 |
Neg logit contributions | |
thur | -1.326 |
andise | -1.284 |
gee | -1.264 |
boa | -1.230 |
endi | -1.157 |
Token | ote |
Token ID | 1258 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Else | +0.253 |
ta | +0.253 |
Defendants | +0.249 |
core | +0.247 |
cial | +0.242 |
Neg logit contributions | |
thur | -0.464 |
andise | -0.449 |
gee | -0.441 |
boa | -0.431 |
Merchants | -0.404 |
Token | and |
Token ID | 290 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ta | +0.165 |
Else | +0.165 |
core | +0.163 |
Defendants | +0.163 |
cial | +0.160 |
Neg logit contributions | |
thur | -0.196 |
andise | -0.190 |
gee | -0.185 |
boa | -0.180 |
Merchants | -0.167 |
Token | - |
Token ID | 12 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
thur | +0.093 |
andise | +0.090 |
gee | +0.088 |
boa | +0.085 |
Merchants | +0.079 |
Neg logit contributions | |
ta | -0.081 |
Else | -0.080 |
core | -0.080 |
Defendants | -0.079 |
cial | -0.078 |
Token | street |
Token ID | 25662 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
ta | +0.169 |
Else | +0.168 |
Defendants | +0.166 |
core | +0.166 |
cial | +0.163 |
Neg logit contributions | |
thur | -0.225 |
andise | -0.218 |
gee | -0.213 |
boa | -0.207 |
Merchants | -0.193 |
Token | harassment |
Token ID | 10556 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
thur | +0.027 |
andise | +0.026 |
gee | +0.025 |
boa | +0.024 |
Merchants | +0.022 |
Neg logit contributions | |
ta | -0.028 |
Else | -0.028 |
core | -0.028 |
Defendants | -0.028 |
cial | -0.027 |
Token | organization |
Token ID | 4009 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ta | +0.022 |
Else | +0.022 |
core | +0.022 |
Defendants | +0.022 |
cial | +0.021 |
Neg logit contributions | |
thur | -0.026 |
andise | -0.025 |
gee | -0.024 |
boa | -0.024 |
Merchants | -0.022 |
Token | Holl |
Token ID | 11806 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ta | +0.134 |
Else | +0.133 |
core | +0.132 |
Defendants | +0.132 |
cial | +0.129 |
Neg logit contributions | |
thur | -0.165 |
andise | -0.160 |
gee | -0.156 |
boa | -0.152 |
Merchants | -0.142 |
Token | ab |
Token ID | 397 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ta | +0.070 |
Else | +0.070 |
Defendants | +0.069 |
core | +0.069 |
cial | +0.067 |
Neg logit contributions | |
thur | -0.110 |
andise | -0.107 |
gee | -0.105 |
boa | -0.102 |
Merchants | -0.096 |
Token | ack |
Token ID | 441 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
thur | +1.771 |
andise | +1.709 |
gee | +1.674 |
boa | +1.651 |
Merchants | +1.573 |
Neg logit contributions | |
ta | -0.759 |
core | -0.758 |
Else | -0.752 |
Defendants | -0.732 |
cial | -0.729 |
Token | showed |
Token ID | 3751 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ta | +0.029 |
Else | +0.029 |
core | +0.028 |
Defendants | +0.028 |
cial | +0.028 |
Neg logit contributions | |
thur | -0.039 |
andise | -0.038 |
gee | -0.037 |
boa | -0.036 |
Merchants | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | +2.32e-03 |
Pos logit contributions | |
ta | +0.064 |
Else | +0.063 |
core | +0.063 |
Defendants | +0.063 |
cial | +0.062 |
Neg logit contributions | |
thur | -0.083 |
andise | -0.081 |
gee | -0.079 |
boa | -0.077 |
Merchants | -0.071 |
Token | 90 |
Token ID | 4101 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
ta | +0.001 |
Else | +0.001 |
core | +0.001 |
Defendants | +0.001 |
cial | +0.001 |
Neg logit contributions | |
thur | -0.002 |
andise | -0.002 |
gee | -0.002 |
boa | -0.002 |
Merchants | -0.001 |
Token | percent |
Token ID | 1411 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Else | +0.279 |
ta | +0.278 |
Defendants | +0.274 |
core | +0.274 |
cial | +0.269 |
Neg logit contributions | |
thur | -0.417 |
andise | -0.404 |
gee | -0.395 |
boa | -0.386 |
Merchants | -0.361 |
Token | with |
Token ID | 351 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
thur | +0.185 |
andise | +0.179 |
gee | +0.175 |
boa | +0.170 |
Merchants | +0.158 |
Neg logit contributions | |
ta | -0.150 |
Else | -0.149 |
core | -0.148 |
Defendants | -0.148 |
cial | -0.145 |
Token | point |
Token ID | 966 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ta | +0.029 |
Else | +0.029 |
core | +0.029 |
Defendants | +0.029 |
cial | +0.028 |
Neg logit contributions | |
thur | -0.037 |
andise | -0.036 |
gee | -0.035 |
boa | -0.034 |
Merchants | -0.032 |
Token | guard |
Token ID | 4860 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
thur | +0.379 |
andise | +0.365 |
gee | +0.354 |
boa | +0.343 |
Merchants | +0.316 |
Neg logit contributions | |
ta | -0.388 |
Else | -0.385 |
core | -0.384 |
Defendants | -0.384 |
cial | -0.376 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Else | +0.411 |
ta | +0.407 |
core | +0.401 |
Defendants | +0.401 |
cial | +0.394 |
Neg logit contributions | |
thur | -0.647 |
andise | -0.627 |
gee | -0.615 |
boa | -0.598 |
Merchants | -0.561 |
Token | o |
Token ID | 78 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
ta | +0.111 |
Else | +0.111 |
Defendants | +0.110 |
core | +0.109 |
cial | +0.107 |
Neg logit contributions | |
thur | -0.171 |
andise | -0.166 |
gee | -0.162 |
boa | -0.158 |
Merchants | -0.148 |
Token | U |
Token ID | 471 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Else | +0.525 |
ta | +0.524 |
Defendants | +0.521 |
core | +0.519 |
cial | +0.512 |
Neg logit contributions | |
thur | -0.397 |
andise | -0.381 |
gee | -0.370 |
boa | -0.356 |
Merchants | -0.324 |
Token | dri |
Token ID | 7553 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Defendants | +1.490 |
Else | +1.484 |
ta | +1.480 |
core | +1.451 |
Secondary | +1.437 |
Neg logit contributions | |
thur | -1.040 |
andise | -0.991 |
gee | -0.962 |
boa | -0.921 |
endi | -0.820 |
Token | h |
Token ID | 71 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ta | +0.151 |
Else | +0.151 |
Defendants | +0.149 |
core | +0.149 |
cial | +0.147 |
Neg logit contributions | |
thur | -0.127 |
andise | -0.122 |
gee | -0.118 |
boa | -0.114 |
Merchants | -0.104 |
Token | , |
Token ID | 11 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ta | +0.066 |
Else | +0.066 |
core | +0.066 |
Defendants | +0.066 |
cial | +0.064 |
Neg logit contributions | |
thur | -0.081 |
andise | -0.078 |
gee | -0.076 |
boa | -0.074 |
Merchants | -0.069 |
Token | according |
Token ID | 1864 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
ta | +0.111 |
Else | +0.111 |
core | +0.109 |
Defendants | +0.109 |
cial | +0.107 |
Neg logit contributions | |
thur | -0.150 |
andise | -0.146 |
gee | -0.142 |
boa | -0.138 |
Merchants | -0.129 |
Token | to |
Token ID | 284 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ta | +0.043 |
Else | +0.043 |
core | +0.043 |
Defendants | +0.043 |
cial | +0.042 |
Neg logit contributions | |
thur | -0.058 |
andise | -0.056 |
gee | -0.055 |
boa | -0.054 |
Merchants | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
thur | +0.025 |
andise | +0.024 |
gee | +0.024 |
boa | +0.023 |
Merchants | +0.021 |
Neg logit contributions | |
ta | -0.022 |
Else | -0.022 |
core | -0.022 |
Defendants | -0.022 |
cial | -0.021 |
Token | 7 |
Token ID | 22 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ta | +0.037 |
Else | +0.036 |
core | +0.036 |
Defendants | +0.036 |
cial | +0.035 |
Neg logit contributions | |
thur | -0.040 |
andise | -0.038 |
gee | -0.037 |
boa | -0.036 |
Merchants | -0.034 |
Token | trillion |
Token ID | 12989 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
thur | +0.149 |
andise | +0.144 |
gee | +0.141 |
boa | +0.136 |
Merchants | +0.127 |
Neg logit contributions | |
ta | -0.126 |
Else | -0.125 |
core | -0.124 |
Defendants | -0.124 |
cial | -0.121 |
Token |
|
Token ID | 198 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
ta | +0.280 |
Else | +0.280 |
Defendants | +0.276 |
core | +0.276 |
cial | +0.272 |
Neg logit contributions | |
thur | -0.320 |
andise | -0.309 |
gee | -0.301 |
boa | -0.293 |
Merchants | -0.271 |
Token |
|
Token ID | 198 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
thur | +0.026 |
andise | +0.025 |
gee | +0.024 |
boa | +0.023 |
Merchants | +0.022 |
Neg logit contributions | |
ta | -0.023 |
Else | -0.023 |
core | -0.023 |
Defendants | -0.023 |
cial | -0.022 |
Token | Tre |
Token ID | 31055 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
thur | +0.019 |
andise | +0.019 |
gee | +0.018 |
boa | +0.018 |
Merchants | +0.016 |
Neg logit contributions | |
ta | -0.016 |
Else | -0.016 |
core | -0.015 |
Defendants | -0.015 |
cial | -0.015 |
Token | asury |
Token ID | 11579 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Else | +0.639 |
ta | +0.636 |
Defendants | +0.627 |
core | +0.621 |
Secondary | +0.608 |
Neg logit contributions | |
thur | -0.970 |
andise | -0.949 |
gee | -0.930 |
boa | -0.904 |
heed | -0.840 |
Token | takes |
Token ID | 2753 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
ta | +0.175 |
Else | +0.175 |
core | +0.173 |
Defendants | +0.173 |
cial | +0.170 |
Neg logit contributions | |
thur | -0.241 |
andise | -0.234 |
gee | -0.228 |
boa | -0.222 |
Merchants | -0.208 |
Token | final |
Token ID | 2457 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
ta | +0.002 |
Else | +0.002 |
core | +0.002 |
Defendants | +0.002 |
cial | +0.002 |
Neg logit contributions | |
thur | -0.003 |
andise | -0.003 |
gee | -0.003 |
boa | -0.003 |
Merchants | -0.003 |
Token | measures |
Token ID | 5260 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
thur | +0.660 |
andise | +0.638 |
gee | +0.620 |
boa | +0.603 |
Merchants | +0.560 |
Neg logit contributions | |
ta | -0.568 |
Else | -0.562 |
core | -0.560 |
Defendants | -0.559 |
cial | -0.549 |
Token | to |
Token ID | 284 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
ta | +0.098 |
Else | +0.098 |
core | +0.097 |
Defendants | +0.097 |
cial | +0.095 |
Neg logit contributions | |
thur | -0.127 |
andise | -0.123 |
gee | -0.120 |
boa | -0.117 |
Merchants | -0.109 |
Token | their |
Token ID | 511 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ta | +0.004 |
Else | +0.004 |
core | +0.004 |
Defendants | +0.004 |
cial | +0.004 |
Neg logit contributions | |
thur | -0.005 |
andise | -0.005 |
gee | -0.005 |
boa | -0.005 |
Merchants | -0.004 |
Token | destruction |
Token ID | 8166 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ta | +0.148 |
Else | +0.148 |
core | +0.147 |
Defendants | +0.146 |
cial | +0.144 |
Neg logit contributions | |
thur | -0.174 |
andise | -0.168 |
gee | -0.164 |
boa | -0.159 |
Merchants | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ta | +0.197 |
Else | +0.197 |
core | +0.195 |
Defendants | +0.195 |
cial | +0.191 |
Neg logit contributions | |
thur | -0.232 |
andise | -0.224 |
gee | -0.219 |
boa | -0.212 |
Merchants | -0.197 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
thur | +0.210 |
andise | +0.202 |
gee | +0.197 |
boa | +0.192 |
Merchants | +0.177 |
Neg logit contributions | |
ta | -0.187 |
Else | -0.186 |
Defendants | -0.185 |
core | -0.185 |
cial | -0.181 |
Token | Now |
Token ID | 3844 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
thur | +0.011 |
andise | +0.011 |
gee | +0.011 |
boa | +0.010 |
Merchants | +0.010 |
Neg logit contributions | |
ta | -0.009 |
Else | -0.009 |
core | -0.009 |
Defendants | -0.009 |
cial | -0.009 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
thur | +0.084 |
andise | +0.082 |
gee | +0.080 |
boa | +0.077 |
Merchants | +0.072 |
Neg logit contributions | |
ta | -0.069 |
Else | -0.068 |
core | -0.068 |
Defendants | -0.068 |
cial | -0.066 |
Token | : |
Token ID | 25 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
ta | +1.008 |
Else | +1.003 |
Defendants | +0.991 |
core | +0.988 |
cial | +0.979 |
Neg logit contributions | |
thur | -0.998 |
andise | -0.971 |
gee | -0.942 |
boa | -0.917 |
Merchants | -0.848 |
Token | Watch |
Token ID | 6305 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ta | +1.457 |
Else | +1.455 |
Defendants | +1.420 |
cial | +1.417 |
core | +1.415 |
Neg logit contributions | |
thur | -1.287 |
andise | -1.239 |
gee | -1.221 |
boa | -1.171 |
Merchants | -1.092 |
Token | this |
Token ID | 428 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ta | +0.076 |
Else | +0.076 |
core | +0.075 |
Defendants | +0.075 |
cial | +0.074 |
Neg logit contributions | |
thur | -0.097 |
andise | -0.094 |
gee | -0.092 |
boa | -0.089 |
Merchants | -0.083 |
Token | : |
Token ID | 25 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Else | +0.328 |
ta | +0.328 |
Defendants | +0.324 |
core | +0.324 |
cial | +0.318 |
Neg logit contributions | |
thur | -0.346 |
andise | -0.334 |
gee | -0.326 |
boa | -0.316 |
Merchants | -0.292 |
Token | US |
Token ID | 1294 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
ta | +0.124 |
Else | +0.124 |
core | +0.123 |
Defendants | +0.122 |
cial | +0.120 |
Neg logit contributions | |
thur | -0.154 |
andise | -0.149 |
gee | -0.146 |
boa | -0.142 |
Merchants | -0.132 |
Token | ve |
Token ID | 303 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
thur | +0.607 |
andise | +0.588 |
gee | +0.573 |
boa | +0.558 |
Merchants | +0.523 |
Neg logit contributions | |
ta | -0.414 |
core | -0.409 |
Else | -0.408 |
Defendants | -0.405 |
cial | -0.395 |
Token | written |
Token ID | 3194 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
thur | +0.442 |
andise | +0.429 |
gee | +0.419 |
boa | +0.408 |
Merchants | +0.381 |
Neg logit contributions | |
ta | -0.318 |
Else | -0.315 |
core | -0.313 |
Defendants | -0.312 |
cial | -0.304 |
Token | a |
Token ID | 257 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
thur | +0.793 |
andise | +0.766 |
gee | +0.752 |
boa | +0.729 |
heed | +0.678 |
Neg logit contributions | |
ta | -0.570 |
Else | -0.563 |
core | -0.560 |
Defendants | -0.557 |
cial | -0.545 |
Token | couple |
Token ID | 3155 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
thur | +0.334 |
andise | +0.324 |
gee | +0.316 |
boa | +0.306 |
Merchants | +0.283 |
Neg logit contributions | |
ta | -0.297 |
Else | -0.294 |
core | -0.293 |
Defendants | -0.291 |
cial | -0.286 |
Token | of |
Token ID | 286 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
Else | +0.873 |
Defendants | +0.872 |
core | +0.857 |
ta | +0.854 |
cial | +0.850 |
Neg logit contributions | |
thur | -0.994 |
andise | -0.953 |
gee | -0.933 |
boa | -0.917 |
Merchants | -0.845 |
Token | books |
Token ID | 3835 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Else | +0.308 |
Defendants | +0.306 |
ta | +0.305 |
core | +0.303 |
cial | +0.297 |
Neg logit contributions | |
thur | -0.473 |
andise | -0.458 |
gee | -0.450 |
boa | -0.439 |
Merchants | -0.411 |
Token | , |
Token ID | 11 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Else | +0.756 |
ta | +0.753 |
Defendants | +0.751 |
core | +0.739 |
cial | +0.731 |
Neg logit contributions | |
thur | -0.820 |
andise | -0.787 |
gee | -0.773 |
boa | -0.752 |
heed | -0.689 |
Token | which |
Token ID | 543 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
thur | +0.111 |
andise | +0.106 |
gee | +0.103 |
boa | +0.100 |
Merchants | +0.092 |
Neg logit contributions | |
ta | -0.116 |
Else | -0.115 |
core | -0.115 |
Defendants | -0.115 |
cial | -0.113 |
Token | you |
Token ID | 345 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
ta | +0.801 |
Else | +0.797 |
Defendants | +0.786 |
core | +0.780 |
cial | +0.771 |
Neg logit contributions | |
thur | -0.783 |
andise | -0.754 |
gee | -0.733 |
boa | -0.708 |
Merchants | -0.649 |
Token | might |
Token ID | 1244 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Else | +0.238 |
ta | +0.236 |
Defendants | +0.234 |
core | +0.234 |
cial | +0.230 |
Neg logit contributions | |
thur | -0.372 |
andise | -0.363 |
gee | -0.356 |
boa | -0.346 |
Merchants | -0.325 |
Token | want |
Token ID | 765 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Else | +0.496 |
ta | +0.488 |
Defendants | +0.484 |
core | +0.484 |
cial | +0.479 |
Neg logit contributions | |
thur | -0.853 |
andise | -0.837 |
gee | -0.818 |
boa | -0.803 |
Merchants | -0.752 |
Token | SELECT |
Token ID | 33493 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
thur | +0.431 |
andise | +0.418 |
gee | +0.409 |
boa | +0.398 |
Merchants | +0.372 |
Neg logit contributions | |
ta | -0.305 |
Else | -0.303 |
core | -0.300 |
Defendants | -0.299 |
cial | -0.293 |
Token | REG |
Token ID | 23337 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
ta | +0.042 |
Else | +0.042 |
core | +0.042 |
Defendants | +0.042 |
cial | +0.041 |
Neg logit contributions | |
thur | -0.047 |
andise | -0.046 |
gee | -0.044 |
boa | -0.043 |
Merchants | -0.040 |
Token | EXP |
Token ID | 49864 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
thur | +0.545 |
andise | +0.525 |
gee | +0.513 |
boa | +0.501 |
Merchants | +0.463 |
Neg logit contributions | |
ta | -0.426 |
Else | -0.426 |
Defendants | -0.421 |
core | -0.421 |
cial | -0.412 |
Token | _ |
Token ID | 62 |
Feature activation | +8.17e-03 |
Pos logit contributions | |
thur | +0.106 |
andise | +0.103 |
gee | +0.100 |
boa | +0.097 |
Merchants | +0.091 |
Neg logit contributions | |
ta | -0.086 |
Else | -0.086 |
core | -0.085 |
Defendants | -0.085 |
cial | -0.083 |
Token | EX |
Token ID | 6369 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
ta | +0.005 |
Else | +0.005 |
core | +0.005 |
Defendants | +0.005 |
cial | +0.005 |
Neg logit contributions | |
thur | -0.006 |
andise | -0.006 |
gee | -0.006 |
boa | -0.006 |
Merchants | -0.005 |
Token | TR |
Token ID | 5446 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
thur | +0.435 |
andise | +0.421 |
gee | +0.412 |
boa | +0.401 |
Merchants | +0.373 |
Neg logit contributions | |
ta | -0.320 |
Else | -0.319 |
Defendants | -0.317 |
core | -0.316 |
cial | -0.310 |
Token | ACT |
Token ID | 10659 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ta | +0.648 |
Else | +0.644 |
core | +0.638 |
Defendants | +0.633 |
cial | +0.625 |
Neg logit contributions | |
thur | -1.078 |
andise | -1.052 |
gee | -1.025 |
boa | -0.999 |
Merchants | -0.943 |
Token | ( |
Token ID | 357 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
ta | +0.136 |
Else | +0.136 |
core | +0.135 |
Defendants | +0.135 |
cial | +0.132 |
Neg logit contributions | |
thur | -0.160 |
andise | -0.155 |
gee | -0.151 |
boa | -0.146 |
Merchants | -0.136 |
Token | line |
Token ID | 1627 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
thur | +0.043 |
andise | +0.042 |
gee | +0.041 |
boa | +0.040 |
Merchants | +0.037 |
Neg logit contributions | |
ta | -0.034 |
Else | -0.033 |
core | -0.033 |
Defendants | -0.033 |
cial | -0.032 |
Token | , |
Token ID | 837 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
thur | +0.030 |
andise | +0.028 |
gee | +0.028 |
boa | +0.027 |
Merchants | +0.025 |
Neg logit contributions | |
ta | -0.029 |
Else | -0.029 |
core | -0.029 |
Defendants | -0.029 |
cial | -0.028 |
Token | r |
Token ID | 374 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
thur | +0.085 |
andise | +0.083 |
gee | +0.081 |
boa | +0.079 |
Merchants | +0.073 |
Neg logit contributions | |
ta | -0.068 |
Else | -0.067 |
core | -0.067 |
Defendants | -0.067 |
cial | -0.065 |
Token | in |
Token ID | 287 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
thur | +0.005 |
andise | +0.005 |
gee | +0.005 |
boa | +0.005 |
Merchants | +0.004 |
Neg logit contributions | |
ta | -0.004 |
Else | -0.004 |
core | -0.004 |
Defendants | -0.004 |
cial | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
thur | +0.044 |
andise | +0.042 |
gee | +0.041 |
boa | +0.040 |
Merchants | +0.037 |
Neg logit contributions | |
ta | -0.034 |
Else | -0.034 |
core | -0.034 |
Defendants | -0.034 |
cial | -0.033 |
Token | foot |
Token ID | 2366 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
thur | +0.067 |
andise | +0.065 |
gee | +0.063 |
boa | +0.061 |
Merchants | +0.057 |
Neg logit contributions | |
ta | -0.054 |
Else | -0.054 |
core | -0.054 |
Defendants | -0.054 |
cial | -0.053 |
Token | notes |
Token ID | 17815 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
thur | +0.085 |
andise | +0.081 |
gee | +0.078 |
boa | +0.074 |
Merchants | +0.065 |
Neg logit contributions | |
ta | -0.170 |
Else | -0.169 |
core | -0.168 |
Defendants | -0.168 |
cial | -0.166 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ta | +0.015 |
Else | +0.015 |
core | +0.015 |
Defendants | +0.015 |
cial | +0.015 |
Neg logit contributions | |
thur | -0.018 |
andise | -0.018 |
gee | -0.017 |
boa | -0.017 |
Merchants | -0.016 |
Token | references |
Token ID | 10288 |
Feature activation | +6.20e-03 |
Pos logit contributions | |
thur | +0.084 |
andise | +0.082 |
gee | +0.080 |
boa | +0.077 |
Merchants | +0.072 |
Neg logit contributions | |
ta | -0.065 |
Else | -0.065 |
core | -0.065 |
Defendants | -0.065 |
cial | -0.063 |
Token | of |
Token ID | 286 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
ta | +0.004 |
Else | +0.004 |
core | +0.004 |
Defendants | +0.004 |
cial | +0.003 |
Neg logit contributions | |
thur | -0.005 |
andise | -0.005 |
gee | -0.004 |
boa | -0.004 |
Merchants | -0.004 |
Token | some |
Token ID | 617 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
thur | +0.096 |
andise | +0.093 |
gee | +0.091 |
boa | +0.089 |
Merchants | +0.082 |
Neg logit contributions | |
ta | -0.079 |
Else | -0.078 |
core | -0.077 |
Defendants | -0.077 |
cial | -0.076 |
Token | observations |
Token ID | 13050 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
thur | +0.124 |
andise | +0.120 |
gee | +0.117 |
boa | +0.114 |
Merchants | +0.106 |
Neg logit contributions | |
ta | -0.103 |
Else | -0.103 |
core | -0.102 |
Defendants | -0.102 |
cial | -0.100 |
Token | made |
Token ID | 925 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
thur | +0.103 |
andise | +0.100 |
gee | +0.097 |
boa | +0.095 |
Merchants | +0.088 |
Neg logit contributions | |
ta | -0.083 |
Else | -0.083 |
core | -0.082 |
Defendants | -0.082 |
cial | -0.080 |
Token | during |
Token ID | 1141 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ta | +0.027 |
Else | +0.027 |
core | +0.026 |
Defendants | +0.026 |
cial | +0.026 |
Neg logit contributions | |
thur | -0.035 |
andise | -0.034 |
gee | -0.033 |
boa | -0.032 |
Merchants | -0.030 |
Token | 2016 |
Token ID | 5304 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
ta | +0.047 |
Else | +0.046 |
core | +0.046 |
Defendants | +0.046 |
cial | +0.045 |
Neg logit contributions | |
thur | -0.071 |
andise | -0.069 |
gee | -0.068 |
boa | -0.066 |
Merchants | -0.062 |
Token | / |
Token ID | 14 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
thur | +0.064 |
andise | +0.062 |
gee | +0.061 |
boa | +0.059 |
Merchants | +0.055 |
Neg logit contributions | |
ta | -0.056 |
Else | -0.056 |
core | -0.055 |
Defendants | -0.055 |
cial | -0.054 |
Token | 05 |
Token ID | 2713 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ta | +0.110 |
Else | +0.109 |
Defendants | +0.108 |
core | +0.108 |
cial | +0.106 |
Neg logit contributions | |
thur | -0.176 |
andise | -0.171 |
gee | -0.167 |
boa | -0.163 |
Merchants | -0.153 |
Token | / |
Token ID | 14 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ta | +0.133 |
Else | +0.133 |
Defendants | +0.131 |
core | +0.131 |
cial | +0.129 |
Neg logit contributions | |
thur | -0.151 |
andise | -0.146 |
gee | -0.142 |
boa | -0.138 |
Merchants | -0.128 |
Token | 5 |
Token ID | 20 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
ta | +0.103 |
Else | +0.103 |
Defendants | +0.102 |
core | +0.101 |
cial | +0.099 |
Neg logit contributions | |
thur | -0.142 |
andise | -0.137 |
gee | -0.134 |
boa | -0.131 |
Merchants | -0.122 |
Token | - |
Token ID | 12 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ta | +0.044 |
Else | +0.044 |
core | +0.044 |
Defendants | +0.044 |
cial | +0.043 |
Neg logit contributions | |
thur | -0.052 |
andise | -0.050 |
gee | -0.049 |
boa | -0.048 |
Merchants | -0.044 |
Token | ways |
Token ID | 1322 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
ta | +0.063 |
Else | +0.062 |
Defendants | +0.062 |
core | +0.062 |
cial | +0.060 |
Neg logit contributions | |
thur | -0.080 |
andise | -0.077 |
gee | -0.075 |
boa | -0.073 |
Merchants | -0.068 |
Token | - |
Token ID | 12 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ta | +0.093 |
Else | +0.093 |
core | +0.092 |
Defendants | +0.092 |
cial | +0.090 |
Neg logit contributions | |
thur | -0.107 |
andise | -0.103 |
gee | -0.100 |
boa | -0.098 |
Merchants | -0.090 |
Token | law |
Token ID | 6270 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
ta | +0.200 |
Else | +0.200 |
Defendants | +0.198 |
core | +0.197 |
cial | +0.193 |
Neg logit contributions | |
thur | -0.241 |
andise | -0.233 |
gee | -0.228 |
boa | -0.221 |
Merchants | -0.205 |
Token | - |
Token ID | 12 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
ta | +0.055 |
Else | +0.055 |
core | +0.055 |
Defendants | +0.055 |
cial | +0.054 |
Neg logit contributions | |
thur | -0.056 |
andise | -0.054 |
gee | -0.052 |
boa | -0.051 |
Merchants | -0.047 |
Token | enforcement |
Token ID | 44976 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ta | +0.128 |
Else | +0.128 |
Defendants | +0.127 |
core | +0.127 |
cial | +0.124 |
Neg logit contributions | |
thur | -0.155 |
andise | -0.149 |
gee | -0.146 |
boa | -0.142 |
Merchants | -0.132 |
Token | line |
Token ID | 1627 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
thur | +0.184 |
andise | +0.177 |
gee | +0.173 |
boa | +0.167 |
Merchants | +0.155 |
Neg logit contributions | |
ta | -0.172 |
Else | -0.171 |
core | -0.169 |
Defendants | -0.169 |
cial | -0.166 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
thur | +0.109 |
andise | +0.105 |
gee | +0.103 |
boa | +0.100 |
Merchants | +0.093 |
Neg logit contributions | |
ta | -0.090 |
Else | -0.090 |
core | -0.089 |
Defendants | -0.089 |
cial | -0.087 |
Token | he |
Token ID | 339 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
thur | +0.117 |
andise | +0.113 |
gee | +0.111 |
boa | +0.107 |
Merchants | +0.099 |
Neg logit contributions | |
ta | -0.106 |
Else | -0.106 |
core | -0.105 |
Defendants | -0.105 |
cial | -0.103 |
Token | kindly |
Token ID | 26820 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
thur | +0.144 |
andise | +0.139 |
gee | +0.136 |
boa | +0.133 |
Merchants | +0.124 |
Neg logit contributions | |
ta | -0.095 |
Else | -0.094 |
core | -0.094 |
Defendants | -0.093 |
cial | -0.091 |
Token | explained |
Token ID | 4893 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ta | +0.028 |
Else | +0.028 |
core | +0.028 |
Defendants | +0.028 |
cial | +0.027 |
Neg logit contributions | |
thur | -0.046 |
andise | -0.045 |
gee | -0.044 |
boa | -0.043 |
Merchants | -0.040 |
Token | that |
Token ID | 326 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
thur | +0.008 |
andise | +0.008 |
gee | +0.008 |
boa | +0.008 |
Merchants | +0.007 |
Neg logit contributions | |
ta | -0.006 |
Else | -0.006 |
core | -0.006 |
Defendants | -0.006 |
cial | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ta | +0.045 |
Else | +0.044 |
core | +0.044 |
Defendants | +0.044 |
cial | +0.043 |
Neg logit contributions | |
thur | -0.055 |
andise | -0.053 |
gee | -0.052 |
boa | -0.050 |
Merchants | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Else | +0.162 |
ta | +0.162 |
core | +0.160 |
Defendants | +0.160 |
cial | +0.157 |
Neg logit contributions | |
thur | -0.211 |
andise | -0.205 |
gee | -0.200 |
boa | -0.194 |
Merchants | -0.181 |
Token | not |
Token ID | 407 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
thur | +0.210 |
andise | +0.204 |
gee | +0.199 |
boa | +0.194 |
Merchants | +0.180 |
Neg logit contributions | |
ta | -0.162 |
Else | -0.161 |
core | -0.159 |
Defendants | -0.159 |
cial | -0.156 |
Token | directed |
Token ID | 7924 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
thur | +0.284 |
andise | +0.275 |
gee | +0.268 |
boa | +0.261 |
Merchants | +0.242 |
Neg logit contributions | |
ta | -0.225 |
Else | -0.223 |
core | -0.222 |
Defendants | -0.222 |
cial | -0.217 |
Token | at |
Token ID | 379 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Else | +0.246 |
ta | +0.245 |
core | +0.242 |
Defendants | +0.242 |
cial | +0.237 |
Neg logit contributions | |
thur | -0.318 |
andise | -0.308 |
gee | -0.301 |
boa | -0.292 |
Merchants | -0.272 |
Token | Human |
Token ID | 5524 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
thur | +0.422 |
andise | +0.409 |
gee | +0.397 |
boa | +0.387 |
heed | +0.359 |
Neg logit contributions | |
ta | -0.331 |
Else | -0.329 |
Defendants | -0.328 |
core | -0.327 |
Secondary | -0.320 |
Token | Services |
Token ID | 6168 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
thur | +0.042 |
andise | +0.041 |
gee | +0.040 |
boa | +0.039 |
Merchants | +0.036 |
Neg logit contributions | |
ta | -0.036 |
Else | -0.036 |
core | -0.036 |
Defendants | -0.036 |
cial | -0.035 |
Token | ; |
Token ID | 26 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
ta | +0.180 |
Else | +0.180 |
core | +0.178 |
Defendants | +0.178 |
cial | +0.174 |
Neg logit contributions | |
thur | -0.257 |
andise | -0.249 |
gee | -0.243 |
boa | -0.237 |
Merchants | -0.221 |
Token | 2006 |
Token ID | 4793 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ta | +0.124 |
Else | +0.124 |
core | +0.122 |
Defendants | +0.122 |
cial | +0.120 |
Neg logit contributions | |
thur | -0.138 |
andise | -0.134 |
gee | -0.130 |
boa | -0.126 |
Merchants | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ta | +0.172 |
Else | +0.172 |
Defendants | +0.170 |
core | +0.170 |
cial | +0.167 |
Neg logit contributions | |
thur | -0.189 |
andise | -0.182 |
gee | -0.178 |
boa | -0.172 |
Merchants | -0.160 |
Token | Available |
Token ID | 14898 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
ta | +0.172 |
Else | +0.171 |
core | +0.169 |
Defendants | +0.169 |
cial | +0.166 |
Neg logit contributions | |
thur | -0.209 |
andise | -0.203 |
gee | -0.198 |
boa | -0.192 |
Merchants | -0.179 |
Token | at |
Token ID | 379 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
ta | +0.123 |
Else | +0.123 |
core | +0.121 |
Defendants | +0.121 |
cial | +0.119 |
Neg logit contributions | |
thur | -0.162 |
andise | -0.157 |
gee | -0.154 |
boa | -0.149 |
Merchants | -0.139 |
Token | http |
Token ID | 2638 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
ta | +0.194 |
Else | +0.194 |
core | +0.192 |
Defendants | +0.192 |
cial | +0.189 |
Neg logit contributions | |
thur | -0.178 |
andise | -0.171 |
gee | -0.167 |
boa | -0.161 |
Merchants | -0.148 |
Token | :// |
Token ID | 1378 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ta | +0.087 |
Else | +0.086 |
core | +0.086 |
Defendants | +0.086 |
cial | +0.084 |
Neg logit contributions | |
thur | -0.083 |
andise | -0.080 |
gee | -0.078 |
boa | -0.076 |
Merchants | -0.070 |
Token | public |
Token ID | 11377 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
ta | +0.077 |
Else | +0.077 |
Defendants | +0.076 |
core | +0.076 |
cial | +0.075 |
Neg logit contributions | |
thur | -0.101 |
andise | -0.098 |
gee | -0.096 |
boa | -0.093 |
Merchants | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
thur | +0.507 |
andise | +0.492 |
gee | +0.478 |
boa | +0.466 |
Merchants | +0.436 |
Neg logit contributions | |
ta | -0.386 |
Else | -0.383 |
core | -0.383 |
Defendants | -0.380 |
cial | -0.375 |
Token | in |
Token ID | 287 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Else | +0.170 |
ta | +0.170 |
core | +0.168 |
Defendants | +0.168 |
cial | +0.164 |
Neg logit contributions | |
thur | -0.214 |
andise | -0.207 |
gee | -0.202 |
boa | -0.196 |
Merchants | -0.182 |
Token | as |
Token ID | 355 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
Else | +0.199 |
ta | +0.199 |
core | +0.197 |
Defendants | +0.197 |
cial | +0.193 |
Neg logit contributions | |
thur | -0.256 |
andise | -0.248 |
gee | -0.242 |
boa | -0.236 |
Merchants | -0.220 |
Token | many |
Token ID | 867 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ta | +0.225 |
Else | +0.225 |
core | +0.222 |
Defendants | +0.222 |
cial | +0.217 |
Neg logit contributions | |
thur | -0.315 |
andise | -0.305 |
gee | -0.298 |
boa | -0.291 |
Merchants | -0.271 |
Token | chains |
Token ID | 14659 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
Else | +0.295 |
ta | +0.295 |
core | +0.292 |
Defendants | +0.291 |
cial | +0.286 |
Neg logit contributions | |
thur | -0.380 |
andise | -0.368 |
gee | -0.359 |
boa | -0.349 |
Merchants | -0.325 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Else | +0.398 |
ta | +0.396 |
Defendants | +0.392 |
core | +0.390 |
cial | +0.383 |
Neg logit contributions | |
thur | -0.490 |
andise | -0.475 |
gee | -0.462 |
boa | -0.451 |
Merchants | -0.417 |
Token | spikes |
Token ID | 27198 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ta | +0.083 |
Else | +0.083 |
core | +0.082 |
Defendants | +0.082 |
cial | +0.081 |
Neg logit contributions | |
thur | -0.104 |
andise | -0.100 |
gee | -0.098 |
boa | -0.095 |
Merchants | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Else | +0.269 |
ta | +0.268 |
Defendants | +0.266 |
core | +0.265 |
cial | +0.261 |
Neg logit contributions | |
thur | -0.315 |
andise | -0.305 |
gee | -0.298 |
boa | -0.289 |
Merchants | -0.268 |
Token | and |
Token ID | 290 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
ta | +0.140 |
Else | +0.140 |
core | +0.138 |
Defendants | +0.138 |
cial | +0.135 |
Neg logit contributions | |
thur | -0.170 |
andise | -0.164 |
gee | -0.160 |
boa | -0.156 |
Merchants | -0.145 |
Token | stainless |
Token ID | 25704 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Else | +0.155 |
ta | +0.155 |
core | +0.153 |
Defendants | +0.153 |
cial | +0.150 |
Neg logit contributions | |
thur | -0.194 |
andise | -0.188 |
gee | -0.183 |
boa | -0.178 |
Merchants | -0.166 |
Token | steel |
Token ID | 7771 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Else | +0.203 |
ta | +0.203 |
Defendants | +0.200 |
core | +0.200 |
cial | +0.197 |
Neg logit contributions | |
thur | -0.232 |
andise | -0.224 |
gee | -0.219 |
boa | -0.212 |
Merchants | -0.197 |
Token | pieces |
Token ID | 5207 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Else | +0.208 |
ta | +0.208 |
Defendants | +0.206 |
core | +0.205 |
cial | +0.202 |
Neg logit contributions | |
thur | -0.250 |
andise | -0.242 |
gee | -0.236 |
boa | -0.229 |
Merchants | -0.213 |
Token | ro |
Token ID | 305 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ta | +0.029 |
Else | +0.029 |
core | +0.028 |
Defendants | +0.028 |
cial | +0.028 |
Neg logit contributions | |
thur | -0.023 |
andise | -0.022 |
gee | -0.021 |
boa | -0.021 |
Merchants | -0.019 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
thur | +0.163 |
andise | +0.157 |
gee | +0.153 |
boa | +0.149 |
Merchants | +0.138 |
Neg logit contributions | |
ta | -0.144 |
Else | -0.143 |
core | -0.142 |
Defendants | -0.142 |
cial | -0.139 |
Token |
|
Token ID | 198 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
thur | +0.192 |
andise | +0.186 |
gee | +0.181 |
boa | +0.176 |
Merchants | +0.163 |
Neg logit contributions | |
ta | -0.171 |
Else | -0.171 |
core | -0.170 |
Defendants | -0.169 |
cial | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
thur | +0.041 |
andise | +0.040 |
gee | +0.039 |
boa | +0.038 |
Merchants | +0.035 |
Neg logit contributions | |
ta | -0.037 |
Else | -0.037 |
core | -0.037 |
Defendants | -0.037 |
cial | -0.036 |
Token | As |
Token ID | 1722 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
thur | +0.037 |
andise | +0.036 |
gee | +0.035 |
boa | +0.034 |
Merchants | +0.031 |
Neg logit contributions | |
ta | -0.033 |
Else | -0.033 |
core | -0.033 |
Defendants | -0.033 |
cial | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
ta | +0.006 |
Else | +0.006 |
core | +0.006 |
Defendants | +0.006 |
cial | +0.006 |
Neg logit contributions | |
thur | -0.008 |
andise | -0.008 |
gee | -0.008 |
boa | -0.007 |
Merchants | -0.007 |
Token | announced |
Token ID | 3414 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
thur | +0.259 |
andise | +0.251 |
gee | +0.246 |
boa | +0.240 |
Merchants | +0.225 |
Neg logit contributions | |
ta | -0.166 |
Else | -0.165 |
core | -0.164 |
Defendants | -0.164 |
cial | -0.160 |
Token | at |
Token ID | 379 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
thur | +0.183 |
andise | +0.178 |
gee | +0.173 |
boa | +0.169 |
Merchants | +0.157 |
Neg logit contributions | |
ta | -0.142 |
Else | -0.141 |
core | -0.140 |
Defendants | -0.140 |
cial | -0.137 |
Token | AWS |
Token ID | 30865 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
thur | +0.010 |
andise | +0.009 |
gee | +0.009 |
boa | +0.009 |
Merchants | +0.008 |
Neg logit contributions | |
ta | -0.008 |
Else | -0.008 |
core | -0.008 |
Defendants | -0.008 |
cial | -0.008 |
Token | re |
Token ID | 302 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
thur | +0.048 |
andise | +0.046 |
gee | +0.045 |
boa | +0.044 |
Merchants | +0.041 |
Neg logit contributions | |
ta | -0.039 |
Else | -0.039 |
core | -0.039 |
Defendants | -0.039 |
cial | -0.038 |
Token | : |
Token ID | 25 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
thur | +0.203 |
andise | +0.196 |
gee | +0.191 |
boa | +0.186 |
Merchants | +0.173 |
Neg logit contributions | |
ta | -0.169 |
Else | -0.169 |
core | -0.168 |
Defendants | -0.167 |
cial | -0.164 |
Token | � |
Token ID | 250 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
ta | +0.025 |
Else | +0.025 |
core | +0.025 |
Defendants | +0.025 |
cial | +0.024 |
Neg logit contributions | |
thur | -0.048 |
andise | -0.046 |
gee | -0.045 |
boa | -0.044 |
Merchants | -0.042 |
Token | re |
Token ID | 260 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
ta | +0.041 |
Else | +0.040 |
core | +0.040 |
Defendants | +0.040 |
cial | +0.039 |
Neg logit contributions | |
thur | -0.047 |
andise | -0.046 |
gee | -0.044 |
boa | -0.043 |
Merchants | -0.040 |
Token | - |
Token ID | 12 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
Else | +0.244 |
ta | +0.243 |
Defendants | +0.241 |
core | +0.240 |
cial | +0.235 |
Neg logit contributions | |
thur | -0.313 |
andise | -0.302 |
gee | -0.295 |
boa | -0.287 |
Merchants | -0.267 |
Token | eval |
Token ID | 18206 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
thur | +0.060 |
andise | +0.058 |
gee | +0.057 |
boa | +0.055 |
Merchants | +0.051 |
Neg logit contributions | |
ta | -0.049 |
Else | -0.048 |
core | -0.048 |
Defendants | -0.048 |
cial | -0.047 |
Token | uated |
Token ID | 6605 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
thur | +0.343 |
andise | +0.334 |
gee | +0.326 |
boa | +0.318 |
Merchants | +0.297 |
Neg logit contributions | |
ta | -0.236 |
Else | -0.233 |
core | -0.233 |
Defendants | -0.232 |
cial | -0.227 |
Token | � |
Token ID | 447 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
thur | +0.023 |
andise | +0.022 |
gee | +0.022 |
boa | +0.021 |
Merchants | +0.020 |
Neg logit contributions | |
ta | -0.019 |
Else | -0.019 |
core | -0.019 |
Defendants | -0.019 |
cial | -0.019 |
Token | � |
Token ID | 251 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
thur | +0.291 |
andise | +0.283 |
gee | +0.277 |
boa | +0.271 |
Merchants | +0.256 |
Neg logit contributions | |
ta | -0.140 |
Else | -0.139 |
core | -0.138 |
Defendants | -0.137 |
cial | -0.134 |
Token | his |
Token ID | 465 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
thur | +0.014 |
andise | +0.014 |
gee | +0.014 |
boa | +0.013 |
Merchants | +0.012 |
Neg logit contributions | |
ta | -0.012 |
Else | -0.012 |
core | -0.012 |
Defendants | -0.012 |
cial | -0.012 |
Token | language |
Token ID | 3303 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
thur | +0.154 |
andise | +0.149 |
gee | +0.146 |
boa | +0.142 |
Merchants | +0.132 |
Neg logit contributions | |
ta | -0.123 |
Else | -0.122 |
core | -0.121 |
Defendants | -0.121 |
cial | -0.119 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ta | +0.056 |
Else | +0.056 |
core | +0.055 |
Defendants | +0.055 |
cial | +0.054 |
Neg logit contributions | |
thur | -0.068 |
andise | -0.066 |
gee | -0.064 |
boa | -0.062 |
Merchants | -0.058 |
Token | that |
Token ID | 326 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
ta | +0.065 |
Else | +0.065 |
core | +0.065 |
Defendants | +0.064 |
cial | +0.063 |
Neg logit contributions | |
thur | -0.088 |
andise | -0.085 |
gee | -0.083 |
boa | -0.081 |
Merchants | -0.075 |
Token | solid |
Token ID | 4735 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
thur | +0.126 |
andise | +0.122 |
gee | +0.119 |
boa | +0.115 |
Merchants | +0.108 |
Neg logit contributions | |
ta | -0.096 |
Else | -0.095 |
core | -0.094 |
Defendants | -0.094 |
cial | -0.092 |
Token | curriculum |
Token ID | 20583 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ta | +0.139 |
Else | +0.139 |
Defendants | +0.137 |
core | +0.137 |
cial | +0.134 |
Neg logit contributions | |
thur | -0.184 |
andise | -0.178 |
gee | -0.174 |
boa | -0.169 |
Merchants | -0.158 |
Token | is |
Token ID | 318 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
ta | +0.089 |
Else | +0.089 |
Defendants | +0.088 |
core | +0.088 |
cial | +0.086 |
Neg logit contributions | |
thur | -0.116 |
andise | -0.112 |
gee | -0.109 |
boa | -0.106 |
Merchants | -0.099 |
Token | one |
Token ID | 530 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
thur | +0.056 |
andise | +0.054 |
gee | +0.053 |
boa | +0.051 |
Merchants | +0.048 |
Neg logit contributions | |
ta | -0.047 |
Else | -0.047 |
core | -0.047 |
Defendants | -0.047 |
cial | -0.046 |
Token | piece |
Token ID | 3704 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
thur | +0.316 |
andise | +0.306 |
gee | +0.298 |
boa | +0.289 |
Merchants | +0.269 |
Neg logit contributions | |
ta | -0.257 |
Else | -0.256 |
core | -0.254 |
Defendants | -0.253 |
cial | -0.249 |
Token | of |
Token ID | 286 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
ta | +0.103 |
Else | +0.103 |
core | +0.102 |
Defendants | +0.102 |
cial | +0.100 |
Neg logit contributions | |
thur | -0.129 |
andise | -0.125 |
gee | -0.122 |
boa | -0.119 |
Merchants | -0.110 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
thur | +0.066 |
andise | +0.063 |
gee | +0.062 |
boa | +0.060 |
Merchants | +0.056 |
Neg logit contributions | |
ta | -0.050 |
Else | -0.050 |
core | -0.049 |
Defendants | -0.049 |
cial | -0.048 |
Token | puzzle |
Token ID | 15027 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
thur | +0.077 |
andise | +0.074 |
gee | +0.072 |
boa | +0.070 |
Merchants | +0.066 |
Neg logit contributions | |
ta | -0.058 |
Else | -0.058 |
core | -0.058 |
Defendants | -0.058 |
cial | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
ta | +0.180 |
Else | +0.180 |
Defendants | +0.178 |
core | +0.178 |
cial | +0.175 |
Neg logit contributions | |
thur | -0.213 |
andise | -0.206 |
gee | -0.201 |
boa | -0.195 |
Merchants | -0.182 |
Token | We |
Token ID | 775 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ta | +0.091 |
Else | +0.090 |
core | +0.089 |
Defendants | +0.089 |
cial | +0.088 |
Neg logit contributions | |
thur | -0.103 |
andise | -0.100 |
gee | -0.097 |
boa | -0.094 |
Merchants | -0.088 |
Token | also |
Token ID | 635 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
thur | +0.084 |
andise | +0.081 |
gee | +0.079 |
boa | +0.077 |
Merchants | +0.072 |
Neg logit contributions | |
ta | -0.068 |
Else | -0.068 |
core | -0.067 |
Defendants | -0.067 |
cial | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
ta | +0.058 |
Else | +0.058 |
core | +0.058 |
Defendants | +0.058 |
cial | +0.056 |
Neg logit contributions | |
thur | -0.067 |
andise | -0.065 |
gee | -0.063 |
boa | -0.061 |
Merchants | -0.057 |
Token | And |
Token ID | 843 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
thur | +0.001 |
andise | +0.001 |
gee | +0.001 |
boa | +0.001 |
Merchants | +0.001 |
Neg logit contributions | |
ta | -0.001 |
Else | -0.001 |
core | -0.001 |
Defendants | -0.001 |
cial | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
thur | +0.087 |
andise | +0.084 |
gee | +0.082 |
boa | +0.080 |
Merchants | +0.074 |
Neg logit contributions | |
ta | -0.072 |
Else | -0.072 |
core | -0.071 |
Defendants | -0.071 |
cial | -0.069 |
Token | � |
Token ID | 447 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
thur | +0.338 |
andise | +0.327 |
gee | +0.319 |
boa | +0.310 |
Merchants | +0.288 |
Neg logit contributions | |
ta | -0.272 |
Else | -0.271 |
core | -0.268 |
Defendants | -0.268 |
cial | -0.263 |
Token | � |
Token ID | 247 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
ta | +0.035 |
Else | +0.035 |
core | +0.035 |
Defendants | +0.035 |
cial | +0.034 |
Neg logit contributions | |
thur | -0.034 |
andise | -0.032 |
gee | -0.031 |
boa | -0.030 |
Merchants | -0.028 |
Token | s |
Token ID | 82 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
thur | +0.021 |
andise | +0.020 |
gee | +0.020 |
boa | +0.019 |
Merchants | +0.018 |
Neg logit contributions | |
ta | -0.019 |
Else | -0.019 |
core | -0.019 |
Defendants | -0.019 |
cial | -0.018 |
Token | also |
Token ID | 635 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
thur | +0.238 |
andise | +0.230 |
gee | +0.225 |
boa | +0.218 |
Merchants | +0.203 |
Neg logit contributions | |
ta | -0.189 |
Else | -0.187 |
core | -0.186 |
Defendants | -0.185 |
cial | -0.182 |
Token | in |
Token ID | 287 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
thur | +0.276 |
andise | +0.267 |
gee | +0.261 |
boa | +0.254 |
Merchants | +0.236 |
Neg logit contributions | |
ta | -0.213 |
Else | -0.211 |
core | -0.210 |
Defendants | -0.209 |
cial | -0.205 |
Token | LA |
Token ID | 9131 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ta | +0.171 |
Else | +0.171 |
core | +0.169 |
Defendants | +0.169 |
cial | +0.166 |
Neg logit contributions | |
thur | -0.223 |
andise | -0.216 |
gee | -0.211 |
boa | -0.205 |
Merchants | -0.192 |
Token | , |
Token ID | 11 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ta | +0.190 |
Else | +0.190 |
Defendants | +0.188 |
core | +0.188 |
cial | +0.184 |
Neg logit contributions | |
thur | -0.220 |
andise | -0.212 |
gee | -0.207 |
boa | -0.201 |
Merchants | -0.186 |
Token | too |
Token ID | 1165 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
thur | +0.138 |
andise | +0.133 |
gee | +0.130 |
boa | +0.126 |
Merchants | +0.117 |
Neg logit contributions | |
ta | -0.119 |
Else | -0.118 |
core | -0.117 |
Defendants | -0.117 |
cial | -0.115 |
Token | we |
Token ID | 356 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
thur | +0.032 |
andise | +0.031 |
gee | +0.031 |
boa | +0.030 |
Merchants | +0.028 |
Neg logit contributions | |
ta | -0.025 |
Else | -0.025 |
core | -0.024 |
Defendants | -0.024 |
cial | -0.024 |
Token | have |
Token ID | 423 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
ta | +0.058 |
Else | +0.057 |
core | +0.057 |
Defendants | +0.057 |
cial | +0.056 |
Neg logit contributions | |
thur | -0.070 |
andise | -0.068 |
gee | -0.066 |
boa | -0.064 |
Merchants | -0.060 |
Token | very |
Token ID | 845 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
thur | +0.010 |
andise | +0.010 |
gee | +0.009 |
boa | +0.009 |
Merchants | +0.009 |
Neg logit contributions | |
ta | -0.007 |
Else | -0.007 |
core | -0.007 |
Defendants | -0.007 |
cial | -0.007 |
Token | few |
Token ID | 1178 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
thur | +0.070 |
andise | +0.068 |
gee | +0.066 |
boa | +0.064 |
Merchants | +0.060 |
Neg logit contributions | |
ta | -0.051 |
Else | -0.051 |
core | -0.051 |
Defendants | -0.051 |
cial | -0.050 |
Token | truly |
Token ID | 4988 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
thur | +0.066 |
andise | +0.063 |
gee | +0.062 |
boa | +0.060 |
Merchants | +0.056 |
Neg logit contributions | |
ta | -0.053 |
Else | -0.053 |
core | -0.052 |
Defendants | -0.052 |
cial | -0.051 |
Token | old |
Token ID | 1468 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
thur | +0.104 |
andise | +0.101 |
gee | +0.099 |
boa | +0.096 |
Merchants | +0.090 |
Neg logit contributions | |
ta | -0.071 |
Else | -0.070 |
core | -0.070 |
Defendants | -0.070 |
cial | -0.068 |
Token | books |
Token ID | 3835 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
thur | +0.053 |
andise | +0.051 |
gee | +0.050 |
boa | +0.049 |
Merchants | +0.046 |
Neg logit contributions | |
ta | -0.038 |
Else | -0.038 |
core | -0.038 |
Defendants | -0.038 |
cial | -0.037 |
Token | anyway |
Token ID | 6949 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ta | +0.150 |
Else | +0.150 |
Defendants | +0.148 |
core | +0.148 |
cial | +0.145 |
Neg logit contributions | |
thur | -0.179 |
andise | -0.173 |
gee | -0.169 |
boa | -0.164 |
Merchants | -0.153 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
thur | +0.185 |
andise | +0.178 |
gee | +0.174 |
boa | +0.169 |
Merchants | +0.156 |
Neg logit contributions | |
ta | -0.163 |
Else | -0.163 |
core | -0.161 |
Defendants | -0.161 |
cial | -0.158 |
Token | We |
Token ID | 775 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
ta | +0.007 |
Else | +0.007 |
core | +0.007 |
Defendants | +0.007 |
cial | +0.007 |
Neg logit contributions | |
thur | -0.008 |
andise | -0.008 |
gee | -0.008 |
boa | -0.008 |
Merchants | -0.007 |
Token | usually |
Token ID | 3221 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
thur | +0.033 |
andise | +0.032 |
gee | +0.031 |
boa | +0.030 |
Merchants | +0.028 |
Neg logit contributions | |
ta | -0.026 |
Else | -0.026 |
core | -0.026 |
Defendants | -0.026 |
cial | -0.025 |
Token | go |
Token ID | 467 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
thur | +0.129 |
andise | +0.124 |
gee | +0.120 |
boa | +0.116 |
Merchants | +0.106 |
Neg logit contributions | |
ta | -0.150 |
Else | -0.149 |
core | -0.148 |
Defendants | -0.148 |
cial | -0.146 |
Token | to |
Token ID | 284 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
ta | +0.114 |
Else | +0.113 |
Defendants | +0.112 |
core | +0.112 |
cial | +0.110 |
Neg logit contributions | |
thur | -0.151 |
andise | -0.146 |
gee | -0.143 |
boa | -0.139 |
Merchants | -0.130 |
Token | book |
Token ID | 1492 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
thur | +0.046 |
andise | +0.045 |
gee | +0.044 |
boa | +0.043 |
Merchants | +0.040 |
Neg logit contributions | |
ta | -0.033 |
Else | -0.033 |
core | -0.033 |
Defendants | -0.033 |
cial | -0.032 |
Token | shop |
Token ID | 24643 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
thur | +0.145 |
andise | +0.134 |
gee | +0.126 |
boa | +0.118 |
Merchants | +0.096 |
Neg logit contributions | |
ta | -0.451 |
Else | -0.449 |
core | -0.448 |
Defendants | -0.446 |
cial | -0.442 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
thur | +0.470 |
andise | +0.453 |
gee | +0.442 |
boa | +0.431 |
Merchants | +0.399 |
Neg logit contributions | |
ta | -0.409 |
Else | -0.406 |
core | -0.405 |
Defendants | -0.402 |
cial | -0.395 |
Token | the |
Token ID | 1169 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
thur | +0.835 |
andise | +0.808 |
gee | +0.785 |
boa | +0.762 |
Merchants | +0.706 |
Neg logit contributions | |
ta | -0.779 |
Else | -0.777 |
core | -0.777 |
Defendants | -0.770 |
cial | -0.753 |
Token | guard |
Token ID | 14864 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
thur | +1.248 |
andise | +1.197 |
gee | +1.171 |
boa | +1.120 |
Merchants | +1.046 |
Neg logit contributions | |
ta | -1.507 |
core | -1.503 |
Else | -1.479 |
Defendants | -1.471 |
Secondary | -1.444 |
Token | ian |
Token ID | 666 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
Else | +0.322 |
ta | +0.322 |
Defendants | +0.319 |
core | +0.319 |
cial | +0.314 |
Neg logit contributions | |
thur | -0.234 |
andise | -0.225 |
gee | -0.217 |
boa | -0.209 |
Merchants | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
thur | +0.294 |
andise | +0.284 |
gee | +0.277 |
boa | +0.269 |
Merchants | +0.249 |
Neg logit contributions | |
ta | -0.260 |
Else | -0.259 |
core | -0.257 |
Defendants | -0.256 |
cial | -0.252 |
Token | com |
Token ID | 785 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
thur | +0.576 |
andise | +0.562 |
gee | +0.547 |
boa | +0.537 |
Merchants | +0.505 |
Neg logit contributions | |
ta | -0.310 |
Else | -0.307 |
core | -0.306 |
Defendants | -0.303 |
cial | -0.296 |
Token | or |
Token ID | 393 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
thur | +0.354 |
andise | +0.340 |
gee | +0.333 |
boa | +0.322 |
Merchants | +0.297 |
Neg logit contributions | |
ta | -0.335 |
Else | -0.333 |
core | -0.331 |
Defendants | -0.330 |
cial | -0.324 |
Token | looking |
Token ID | 2045 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ta | +0.134 |
Else | +0.134 |
Defendants | +0.133 |
core | +0.132 |
cial | +0.130 |
Neg logit contributions | |
thur | -0.199 |
andise | -0.193 |
gee | -0.189 |
boa | -0.184 |
Merchants | -0.172 |
Token | to |
Token ID | 284 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
thur | +0.148 |
andise | +0.144 |
gee | +0.140 |
boa | +0.136 |
Merchants | +0.127 |
Neg logit contributions | |
ta | -0.108 |
Else | -0.108 |
core | -0.107 |
Defendants | -0.106 |
cial | -0.104 |
Token | g |
Token ID | 308 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
thur | +0.204 |
andise | +0.198 |
gee | +0.193 |
boa | +0.188 |
Merchants | +0.175 |
Neg logit contributions | |
ta | -0.160 |
Else | -0.159 |
core | -0.157 |
Defendants | -0.157 |
cial | -0.154 |
Token | ank |
Token ID | 962 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
thur | +0.491 |
andise | +0.476 |
gee | +0.464 |
boa | +0.453 |
Merchants | +0.425 |
Neg logit contributions | |
ta | -0.330 |
Else | -0.328 |
core | -0.326 |
Defendants | -0.324 |
cial | -0.319 |
Token | immedi |
Token ID | 2729 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
thur | +0.104 |
andise | +0.101 |
gee | +0.098 |
boa | +0.095 |
Merchants | +0.089 |
Neg logit contributions | |
ta | -0.082 |
Else | -0.082 |
core | -0.081 |
Defendants | -0.081 |
cial | -0.080 |
Token | at |
Token ID | 265 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
thur | +0.337 |
andise | +0.326 |
gee | +0.317 |
boa | +0.307 |
Merchants | +0.285 |
Neg logit contributions | |
ta | -0.308 |
Else | -0.306 |
core | -0.304 |
Defendants | -0.303 |
cial | -0.298 |
Token | ly |
Token ID | 306 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
thur | +0.844 |
andise | +0.813 |
gee | +0.788 |
boa | +0.769 |
Merchants | +0.711 |
Neg logit contributions | |
ta | -0.821 |
core | -0.810 |
Else | -0.809 |
Defendants | -0.806 |
cial | -0.798 |
Token | after |
Token ID | 706 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
thur | +0.066 |
andise | +0.064 |
gee | +0.062 |
boa | +0.060 |
Merchants | +0.056 |
Neg logit contributions | |
ta | -0.054 |
Else | -0.054 |
core | -0.053 |
Defendants | -0.053 |
cial | -0.052 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
thur | +0.124 |
andise | +0.120 |
gee | +0.117 |
boa | +0.114 |
Merchants | +0.106 |
Neg logit contributions | |
ta | -0.096 |
Else | -0.095 |
core | -0.095 |
Defendants | -0.095 |
cial | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
thur | +0.117 |
andise | +0.112 |
gee | +0.109 |
boa | +0.105 |
Merchants | +0.096 |
Neg logit contributions | |
ta | -0.134 |
Else | -0.133 |
core | -0.132 |
Defendants | -0.132 |
cial | -0.130 |
Token | With |
Token ID | 2080 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
thur | +0.019 |
andise | +0.018 |
gee | +0.018 |
boa | +0.017 |
Merchants | +0.016 |
Neg logit contributions | |
ta | -0.018 |
Else | -0.018 |
core | -0.018 |
Defendants | -0.018 |
cial | -0.018 |
Token | he |
Token ID | 339 |
Feature activation | -7.93e-04 |
Pos logit contributions | |
ta | +0.023 |
Else | +0.023 |
core | +0.023 |
Defendants | +0.023 |
cial | +0.022 |
Neg logit contributions | |
thur | -0.029 |
andise | -0.028 |
gee | -0.027 |
boa | -0.026 |
Merchants | -0.024 |
Token | lab |
Token ID | 2248 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
thur | +0.001 |
andise | +0.001 |
gee | +0.001 |
boa | +0.001 |
Merchants | +0.001 |
Neg logit contributions | |
ta | -0.000 |
Else | -0.000 |
core | -0.000 |
Defendants | -0.000 |
cial | -0.000 |
Token | ored |
Token ID | 1850 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
ta | +0.163 |
Else | +0.163 |
core | +0.161 |
Defendants | +0.161 |
cial | +0.159 |
Neg logit contributions | |
thur | -0.140 |
andise | -0.135 |
gee | -0.131 |
boa | -0.126 |
Merchants | -0.115 |
Token | and |
Token ID | 290 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
thur | +0.315 |
andise | +0.306 |
gee | +0.298 |
boa | +0.290 |
Merchants | +0.270 |
Neg logit contributions | |
ta | -0.248 |
Else | -0.245 |
core | -0.244 |
Defendants | -0.243 |
cial | -0.238 |
Token | proc |
Token ID | 13834 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
thur | +0.050 |
andise | +0.048 |
gee | +0.047 |
boa | +0.046 |
Merchants | +0.043 |
Neg logit contributions | |
ta | -0.037 |
Else | -0.037 |
core | -0.037 |
Defendants | -0.037 |
cial | -0.036 |
Token | rast |
Token ID | 5685 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
thur | +0.306 |
andise | +0.295 |
gee | +0.286 |
boa | +0.278 |
Merchants | +0.255 |
Neg logit contributions | |
ta | -0.326 |
Else | -0.324 |
core | -0.322 |
Defendants | -0.321 |
cial | -0.316 |
Token | inated |
Token ID | 3898 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
thur | +0.805 |
andise | +0.761 |
gee | +0.747 |
boa | +0.723 |
Merchants | +0.647 |
Neg logit contributions | |
ta | -1.295 |
Else | -1.282 |
core | -1.280 |
Defendants | -1.273 |
cial | -1.268 |
Token | in |
Token ID | 287 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
ta | +0.065 |
Else | +0.065 |
core | +0.064 |
Defendants | +0.064 |
cial | +0.063 |
Neg logit contributions | |
thur | -0.085 |
andise | -0.083 |
gee | -0.081 |
boa | -0.078 |
Merchants | -0.073 |
Token | writing |
Token ID | 3597 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
ta | +0.024 |
Else | +0.024 |
core | +0.023 |
Defendants | +0.023 |
cial | +0.023 |
Neg logit contributions | |
thur | -0.032 |
andise | -0.031 |
gee | -0.030 |
boa | -0.029 |
Merchants | -0.027 |
Token | them |
Token ID | 606 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ta | +0.046 |
Else | +0.046 |
core | +0.045 |
Defendants | +0.045 |
cial | +0.045 |
Neg logit contributions | |
thur | -0.060 |
andise | -0.058 |
gee | -0.057 |
boa | -0.055 |
Merchants | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
ta | +0.094 |
Else | +0.094 |
core | +0.093 |
Defendants | +0.093 |
cial | +0.091 |
Neg logit contributions | |
thur | -0.119 |
andise | -0.115 |
gee | -0.113 |
boa | -0.109 |
Merchants | -0.102 |
Token | out |
Token ID | 503 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
thur | +0.081 |
andise | +0.078 |
gee | +0.076 |
boa | +0.074 |
Merchants | +0.069 |
Neg logit contributions | |
ta | -0.060 |
Else | -0.060 |
core | -0.059 |
Defendants | -0.059 |
cial | -0.058 |
Token | pictures |
Token ID | 5986 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
thur | +0.142 |
andise | +0.138 |
gee | +0.134 |
boa | +0.131 |
Merchants | +0.122 |
Neg logit contributions | |
ta | -0.109 |
Else | -0.108 |
core | -0.108 |
Defendants | -0.107 |
cial | -0.105 |
Token | of |
Token ID | 286 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
thur | +0.081 |
andise | +0.078 |
gee | +0.076 |
boa | +0.074 |
Merchants | +0.069 |
Neg logit contributions | |
ta | -0.065 |
Else | -0.065 |
core | -0.065 |
Defendants | -0.064 |
cial | -0.063 |
Token | meat |
Token ID | 6174 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
thur | +0.235 |
andise | +0.228 |
gee | +0.222 |
boa | +0.217 |
Merchants | +0.201 |
Neg logit contributions | |
ta | -0.180 |
Else | -0.179 |
Defendants | -0.177 |
core | -0.177 |
cial | -0.173 |
Token | from |
Token ID | 422 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
ta | +0.024 |
Else | +0.024 |
core | +0.024 |
Defendants | +0.024 |
cial | +0.023 |
Neg logit contributions | |
thur | -0.029 |
andise | -0.028 |
gee | -0.028 |
boa | -0.027 |
Merchants | -0.025 |
Token | grocery |
Token ID | 16918 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
thur | +0.311 |
andise | +0.301 |
gee | +0.294 |
boa | +0.286 |
Merchants | +0.266 |
Neg logit contributions | |
ta | -0.244 |
Else | -0.242 |
core | -0.240 |
Defendants | -0.240 |
cial | -0.235 |
Token | - |
Token ID | 12 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
thur | +0.813 |
andise | +0.780 |
gee | +0.762 |
boa | +0.743 |
heed | +0.679 |
Neg logit contributions | |
ta | -0.820 |
Else | -0.807 |
core | -0.807 |
Defendants | -0.804 |
cial | -0.793 |
Token | store |
Token ID | 8095 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
thur | +0.812 |
andise | +0.782 |
gee | +0.765 |
boa | +0.746 |
Merchants | +0.686 |
Neg logit contributions | |
ta | -0.731 |
Else | -0.727 |
core | -0.726 |
Defendants | -0.718 |
cial | -0.711 |
Token | fl |
Token ID | 781 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
thur | +0.245 |
andise | +0.236 |
gee | +0.229 |
boa | +0.221 |
Merchants | +0.201 |
Neg logit contributions | |
ta | -0.299 |
Else | -0.297 |
core | -0.295 |
Defendants | -0.295 |
cial | -0.290 |
Token | iers |
Token ID | 3183 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
thur | +0.466 |
andise | +0.449 |
gee | +0.438 |
boa | +0.424 |
Merchants | +0.395 |
Neg logit contributions | |
ta | -0.428 |
Else | -0.426 |
core | -0.424 |
Defendants | -0.422 |
cial | -0.417 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
thur | +0.061 |
andise | +0.059 |
gee | +0.058 |
boa | +0.056 |
Merchants | +0.052 |
Neg logit contributions | |
ta | -0.050 |
Else | -0.050 |
core | -0.049 |
Defendants | -0.049 |
cial | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
ta | +0.111 |
Else | +0.111 |
core | +0.110 |
Defendants | +0.110 |
cial | +0.108 |
Neg logit contributions | |
thur | -0.142 |
andise | -0.138 |
gee | -0.135 |
boa | -0.131 |
Merchants | -0.122 |
Token | game |
Token ID | 983 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
ta | +0.060 |
Else | +0.060 |
core | +0.060 |
Defendants | +0.060 |
cial | +0.059 |
Neg logit contributions | |
thur | -0.070 |
andise | -0.068 |
gee | -0.066 |
boa | -0.064 |
Merchants | -0.060 |
Token | due |
Token ID | 2233 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
thur | +0.060 |
andise | +0.058 |
gee | +0.057 |
boa | +0.055 |
Merchants | +0.051 |
Neg logit contributions | |
ta | -0.049 |
Else | -0.049 |
core | -0.048 |
Defendants | -0.048 |
cial | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ta | +0.018 |
Else | +0.018 |
core | +0.018 |
Defendants | +0.018 |
cial | +0.018 |
Neg logit contributions | |
thur | -0.024 |
andise | -0.024 |
gee | -0.023 |
boa | -0.022 |
Merchants | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
thur | +0.160 |
andise | +0.155 |
gee | +0.151 |
boa | +0.147 |
Merchants | +0.137 |
Neg logit contributions | |
ta | -0.123 |
Else | -0.122 |
core | -0.121 |
Defendants | -0.121 |
cial | -0.118 |
Token | g |
Token ID | 308 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ta | +0.051 |
Else | +0.051 |
core | +0.050 |
Defendants | +0.050 |
cial | +0.049 |
Neg logit contributions | |
thur | -0.069 |
andise | -0.066 |
gee | -0.065 |
boa | -0.063 |
Merchants | -0.059 |
Token | ash |
Token ID | 1077 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
thur | +0.912 |
andise | +0.876 |
gee | +0.854 |
boa | +0.829 |
Merchants | +0.779 |
Neg logit contributions | |
ta | -0.777 |
Else | -0.769 |
core | -0.767 |
Defendants | -0.761 |
cial | -0.758 |
Token | that |
Token ID | 326 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
ta | +0.075 |
Else | +0.075 |
core | +0.074 |
Defendants | +0.074 |
cial | +0.073 |
Neg logit contributions | |
thur | -0.094 |
andise | -0.091 |
gee | -0.088 |
boa | -0.086 |
Merchants | -0.080 |
Token | required |
Token ID | 2672 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
thur | +0.046 |
andise | +0.044 |
gee | +0.043 |
boa | +0.042 |
Merchants | +0.039 |
Neg logit contributions | |
ta | -0.035 |
Else | -0.035 |
core | -0.035 |
Defendants | -0.035 |
cial | -0.034 |
Token | 10 |
Token ID | 838 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
thur | +0.166 |
andise | +0.161 |
gee | +0.157 |
boa | +0.153 |
Merchants | +0.143 |
Neg logit contributions | |
ta | -0.118 |
Else | -0.117 |
core | -0.116 |
Defendants | -0.116 |
cial | -0.114 |
Token | stitches |
Token ID | 28096 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
thur | +0.063 |
andise | +0.061 |
gee | +0.059 |
boa | +0.058 |
Merchants | +0.054 |
Neg logit contributions | |
ta | -0.044 |
Else | -0.044 |
core | -0.043 |
Defendants | -0.043 |
cial | -0.042 |