Token | and |
Token ID | 290 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Russ | +1.973 |
Dems | +1.923 |
oit | +1.914 |
andre | +1.780 |
jamin | +1.765 |
Neg logit contributions | |
warr | -1.996 |
Reply | -1.894 |
Interstitial | -1.817 |
mans | -1.747 |
lers | -1.699 |
Token | imposing |
Token ID | 20814 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Russ | +0.685 |
Dems | +0.670 |
oit | +0.665 |
andre | +0.619 |
jamin | +0.614 |
Neg logit contributions | |
warr | -0.694 |
Reply | -0.657 |
Interstitial | -0.631 |
mans | -0.609 |
lers | -0.592 |
Token | final |
Token ID | 2457 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
warr | +1.471 |
Reply | +1.385 |
Interstitial | +1.324 |
mans | +1.293 |
lers | +1.264 |
Neg logit contributions | |
Russ | -1.307 |
oit | -1.269 |
Dems | -1.269 |
andre | -1.187 |
jamin | -1.177 |
Token | defeat |
Token ID | 7433 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
warr | +0.902 |
Reply | +0.856 |
Interstitial | +0.819 |
mans | +0.800 |
lers | +0.780 |
Neg logit contributions | |
Russ | -0.762 |
Dems | -0.741 |
oit | -0.738 |
andre | -0.689 |
jamin | -0.681 |
Token | at |
Token ID | 379 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
Russ | +0.775 |
Dems | +0.760 |
oit | +0.759 |
andre | +0.712 |
jamin | +0.707 |
Neg logit contributions | |
warr | -0.656 |
Reply | -0.615 |
Interstitial | -0.586 |
mans | -0.565 |
lers | -0.548 |
Token | Lub |
Token ID | 40753 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
warr | +0.129 |
Reply | +0.122 |
Interstitial | +0.118 |
mans | +0.113 |
lers | +0.110 |
Neg logit contributions | |
Russ | -0.125 |
Dems | -0.122 |
oit | -0.122 |
andre | -0.114 |
jamin | -0.113 |
Token | lin |
Token ID | 2815 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
warr | +4.825 |
mans | +4.657 |
Reply | +4.588 |
lers | +4.396 |
Interstitial | +3.988 |
Neg logit contributions | |
Russ | -8.620 |
Dems | -8.329 |
oit | -8.180 |
ILLE | -8.021 |
andre | -7.855 |
Token | .[ |
Token ID | 3693 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
warr | +0.918 |
Reply | +0.867 |
Interstitial | +0.826 |
mans | +0.800 |
lers | +0.777 |
Neg logit contributions | |
Russ | -1.047 |
Dems | -1.021 |
oit | -1.015 |
andre | -0.954 |
jamin | -0.949 |
Token | 23 |
Token ID | 1954 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
Russ | +0.707 |
oit | +0.689 |
Dems | +0.687 |
andre | +0.651 |
jamin | +0.647 |
Neg logit contributions | |
warr | -0.502 |
Reply | -0.464 |
Interstitial | -0.443 |
mans | -0.424 |
lers | -0.409 |
Token | ] |
Token ID | 60 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
warr | +0.363 |
Reply | +0.344 |
Interstitial | +0.327 |
mans | +0.316 |
lers | +0.307 |
Neg logit contributions | |
Russ | -0.420 |
Dems | -0.411 |
oit | -0.410 |
andre | -0.386 |
jamin | -0.382 |
Token |
|
Token ID | 198 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
Russ | +0.507 |
Dems | +0.493 |
oit | +0.489 |
andre | +0.455 |
jamin | +0.452 |
Neg logit contributions | |
warr | -0.581 |
Reply | -0.547 |
Interstitial | -0.528 |
mans | -0.511 |
lers | -0.497 |
Token | he |
Token ID | 339 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
warr | +0.026 |
Reply | +0.024 |
Interstitial | +0.023 |
mans | +0.023 |
lers | +0.022 |
Neg logit contributions | |
Russ | -0.022 |
Dems | -0.022 |
oit | -0.022 |
andre | -0.020 |
jamin | -0.020 |
Token | offered |
Token ID | 4438 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
Russ | +0.578 |
Dems | +0.569 |
oit | +0.564 |
andre | +0.531 |
jamin | +0.527 |
Neg logit contributions | |
warr | -0.515 |
Reply | -0.483 |
Interstitial | -0.462 |
mans | -0.443 |
lers | -0.429 |
Token | a |
Token ID | 257 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
warr | +1.252 |
Reply | +1.192 |
Interstitial | +1.130 |
mans | +1.101 |
lers | +1.080 |
Neg logit contributions | |
Russ | -1.209 |
oit | -1.179 |
Dems | -1.169 |
andre | -1.100 |
jamin | -1.092 |
Token | tweet |
Token ID | 6126 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
warr | +0.466 |
Reply | +0.445 |
Interstitial | +0.421 |
mans | +0.411 |
lers | +0.402 |
Neg logit contributions | |
Russ | -0.428 |
oit | -0.416 |
Dems | -0.415 |
andre | -0.388 |
jamin | -0.383 |
Token | of |
Token ID | 286 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Russ | +0.479 |
Dems | +0.468 |
oit | +0.467 |
andre | +0.438 |
jamin | +0.435 |
Neg logit contributions | |
warr | -0.428 |
Reply | -0.404 |
Interstitial | -0.385 |
mans | -0.373 |
lers | -0.362 |
Token | condol |
Token ID | 35059 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
warr | +0.524 |
Reply | +0.496 |
Interstitial | +0.472 |
mans | +0.458 |
lers | +0.447 |
Neg logit contributions | |
Russ | -0.536 |
Dems | -0.521 |
oit | -0.520 |
andre | -0.488 |
jamin | -0.485 |
Token | ence |
Token ID | 594 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
Reply | +6.484 |
warr | +6.364 |
mans | +6.202 |
Interstitial | +6.101 |
lers | +6.054 |
Neg logit contributions | |
Russ | -6.743 |
Dems | -6.540 |
oit | -6.238 |
ILLE | -6.030 |
jamin | -6.017 |
Token | to |
Token ID | 284 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
warr | +0.231 |
Reply | +0.217 |
Interstitial | +0.207 |
mans | +0.200 |
lers | +0.195 |
Neg logit contributions | |
Russ | -0.259 |
Dems | -0.253 |
oit | -0.252 |
andre | -0.237 |
jamin | -0.235 |
Token | those |
Token ID | 883 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
warr | +0.447 |
Reply | +0.422 |
Interstitial | +0.404 |
mans | +0.391 |
lers | +0.380 |
Neg logit contributions | |
Russ | -0.455 |
Dems | -0.444 |
oit | -0.443 |
andre | -0.414 |
jamin | -0.411 |
Token | affected |
Token ID | 5676 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
warr | +0.361 |
Reply | +0.335 |
Interstitial | +0.317 |
mans | +0.303 |
lers | +0.291 |
Neg logit contributions | |
Russ | -0.527 |
Dems | -0.517 |
oit | -0.512 |
andre | -0.485 |
jamin | -0.482 |
Token | by |
Token ID | 416 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
warr | +1.996 |
Reply | +1.897 |
Interstitial | +1.764 |
mans | +1.742 |
lers | +1.681 |
Neg logit contributions | |
Russ | -2.689 |
oit | -2.633 |
Dems | -2.620 |
andre | -2.479 |
jamin | -2.453 |
Token | Log |
Token ID | 5972 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
warr | +0.236 |
Reply | +0.223 |
Interstitial | +0.214 |
mans | +0.207 |
lers | +0.201 |
Neg logit contributions | |
Russ | -0.234 |
Dems | -0.228 |
oit | -0.228 |
andre | -0.213 |
jamin | -0.211 |
Token | ical |
Token ID | 605 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Russ | +0.558 |
oit | +0.545 |
Dems | +0.544 |
andre | +0.504 |
jamin | +0.501 |
Neg logit contributions | |
warr | -0.649 |
Reply | -0.613 |
Interstitial | -0.591 |
mans | -0.567 |
lers | -0.554 |
Token |
|
Token ID | 198 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Russ | +2.989 |
Dems | +2.929 |
oit | +2.929 |
andre | +2.717 |
jamin | +2.696 |
Neg logit contributions | |
warr | -3.284 |
Reply | -3.095 |
Interstitial | -2.999 |
mans | -2.881 |
lers | -2.805 |
Token |
|
Token ID | 198 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
warr | +0.922 |
Reply | +0.899 |
Interstitial | +0.858 |
mans | +0.838 |
lers | +0.816 |
Neg logit contributions | |
Russ | -0.827 |
Dems | -0.804 |
oit | -0.802 |
andre | -0.747 |
jamin | -0.738 |
Token | - |
Token ID | 12 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
warr | +0.629 |
Reply | +0.604 |
Interstitial | +0.577 |
mans | +0.560 |
lers | +0.545 |
Neg logit contributions | |
Russ | -0.531 |
Dems | -0.521 |
oit | -0.518 |
andre | -0.479 |
jamin | -0.476 |
Token | Stub |
Token ID | 41135 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
Russ | +0.302 |
Dems | +0.294 |
oit | +0.293 |
andre | +0.274 |
jamin | +0.272 |
Neg logit contributions | |
warr | -0.303 |
Reply | -0.286 |
Interstitial | -0.274 |
mans | -0.265 |
lers | -0.257 |
Token | born |
Token ID | 6286 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Reply | +4.968 |
warr | +4.939 |
mans | +4.426 |
Interstitial | +4.410 |
lers | +4.346 |
Neg logit contributions | |
Russ | -7.645 |
oit | -7.578 |
Dems | -7.539 |
andre | -7.189 |
ILLE | -7.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Russ | +1.569 |
Dems | +1.535 |
oit | +1.533 |
andre | +1.436 |
jamin | +1.425 |
Neg logit contributions | |
warr | -1.387 |
Reply | -1.302 |
Interstitial | -1.244 |
mans | -1.201 |
lers | -1.163 |
Token | Int |
Token ID | 2558 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
warr | +0.225 |
Reply | +0.212 |
Interstitial | +0.203 |
mans | +0.196 |
lers | +0.191 |
Neg logit contributions | |
Russ | -0.228 |
Dems | -0.222 |
oit | -0.222 |
andre | -0.207 |
jamin | -0.206 |
Token | ract |
Token ID | 974 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
Russ | +0.607 |
oit | +0.591 |
Dems | +0.591 |
andre | +0.549 |
jamin | +0.544 |
Neg logit contributions | |
warr | -0.698 |
Reply | -0.659 |
Interstitial | -0.636 |
mans | -0.612 |
lers | -0.597 |
Token | able |
Token ID | 540 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
warr | +0.770 |
Reply | +0.738 |
Interstitial | +0.712 |
mans | +0.695 |
lers | +0.681 |
Neg logit contributions | |
Russ | -0.456 |
Dems | -0.440 |
oit | -0.436 |
andre | -0.399 |
jamin | -0.394 |
Token | the |
Token ID | 262 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
Russ | +1.065 |
Dems | +1.040 |
oit | +1.038 |
andre | +0.966 |
jamin | +0.958 |
Neg logit contributions | |
warr | -1.153 |
Reply | -1.091 |
Interstitial | -1.050 |
mans | -1.013 |
lers | -0.988 |
Token | development |
Token ID | 2478 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
Russ | +0.069 |
Dems | +0.068 |
oit | +0.068 |
andre | +0.063 |
jamin | +0.062 |
Neg logit contributions | |
warr | -0.075 |
Reply | -0.071 |
Interstitial | -0.068 |
mans | -0.066 |
lers | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
warr | +1.107 |
Reply | +1.038 |
Interstitial | +0.994 |
mans | +0.970 |
lers | +0.945 |
Neg logit contributions | |
Russ | -1.030 |
Dems | -1.003 |
oit | -0.998 |
andre | -0.936 |
jamin | -0.926 |
Token | support |
Token ID | 1104 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
Russ | +0.493 |
Dems | +0.479 |
oit | +0.477 |
andre | +0.441 |
jamin | +0.437 |
Neg logit contributions | |
warr | -0.639 |
Reply | -0.607 |
Interstitial | -0.585 |
mans | -0.568 |
lers | -0.555 |
Token | for |
Token ID | 329 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
warr | +0.081 |
Reply | +0.076 |
Interstitial | +0.074 |
mans | +0.071 |
lers | +0.070 |
Neg logit contributions | |
Russ | -0.072 |
Dems | -0.070 |
oit | -0.070 |
andre | -0.066 |
jamin | -0.065 |
Token | Koh |
Token ID | 24754 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
Russ | +0.059 |
Dems | +0.058 |
oit | +0.057 |
andre | +0.054 |
jamin | +0.053 |
Neg logit contributions | |
warr | -0.063 |
Reply | -0.060 |
Interstitial | -0.057 |
mans | -0.056 |
lers | -0.054 |
Token | a |
Token ID | 64 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
warr | +5.136 |
Reply | +4.736 |
mans | +4.512 |
Interstitial | +4.460 |
lers | +4.438 |
Neg logit contributions | |
Russ | -7.437 |
Dems | -7.343 |
oit | -7.248 |
andre | -6.934 |
jamin | -6.882 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Russ | +0.180 |
Dems | +0.176 |
oit | +0.175 |
andre | +0.164 |
jamin | +0.163 |
Neg logit contributions | |
warr | -0.179 |
Reply | -0.169 |
Interstitial | -0.161 |
mans | -0.156 |
lers | -0.152 |
Token | recently |
Token ID | 2904 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
warr | +0.149 |
Reply | +0.141 |
Interstitial | +0.135 |
mans | +0.129 |
lers | +0.126 |
Neg logit contributions | |
Russ | -0.164 |
Dems | -0.161 |
oit | -0.160 |
andre | -0.150 |
jamin | -0.149 |
Token | formed |
Token ID | 7042 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
warr | +1.143 |
Reply | +1.074 |
Interstitial | +1.023 |
mans | +0.987 |
lers | +0.958 |
Neg logit contributions | |
Russ | -1.354 |
Dems | -1.323 |
oit | -1.320 |
andre | -1.240 |
jamin | -1.232 |
Token | an |
Token ID | 281 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
warr | +2.635 |
Reply | +2.493 |
Interstitial | +2.382 |
mans | +2.320 |
lers | +2.276 |
Neg logit contributions | |
Russ | -2.386 |
Dems | -2.325 |
oit | -2.316 |
andre | -2.162 |
jamin | -2.150 |
Token | flagged |
Token ID | 34060 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
warr | +0.926 |
Reply | +0.870 |
Interstitial | +0.828 |
mans | +0.802 |
lers | +0.778 |
Neg logit contributions | |
Russ | -1.092 |
Dems | -1.065 |
oit | -1.064 |
andre | -1.000 |
jamin | -0.990 |
Token | off |
Token ID | 572 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
warr | +3.352 |
Reply | +3.195 |
Interstitial | +2.977 |
mans | +2.945 |
lers | +2.866 |
Neg logit contributions | |
Russ | -4.116 |
Dems | -4.000 |
oit | -3.984 |
andre | -3.760 |
jamin | -3.692 |
Token | between |
Token ID | 1022 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
warr | +0.465 |
Reply | +0.438 |
Interstitial | +0.418 |
mans | +0.404 |
lers | +0.392 |
Neg logit contributions | |
Russ | -0.514 |
Dems | -0.502 |
oit | -0.501 |
andre | -0.470 |
jamin | -0.466 |
Token | Sar |
Token ID | 6866 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
warr | +2.081 |
Reply | +1.970 |
Interstitial | +1.877 |
mans | +1.841 |
lers | +1.793 |
Neg logit contributions | |
Russ | -1.809 |
Dems | -1.745 |
oit | -1.742 |
andre | -1.631 |
jamin | -1.613 |
Token | ai |
Token ID | 1872 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
warr | +1.726 |
Reply | +1.600 |
Interstitial | +1.498 |
mans | +1.455 |
lers | +1.388 |
Neg logit contributions | |
Russ | -3.125 |
Dems | -3.064 |
oit | -3.041 |
andre | -2.892 |
jamin | -2.886 |
Token | Roh |
Token ID | 32694 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
warr | +1.432 |
Reply | +1.359 |
Interstitial | +1.291 |
mans | +1.266 |
lers | +1.226 |
Neg logit contributions | |
Russ | -1.510 |
Dems | -1.472 |
oit | -1.451 |
andre | -1.363 |
jamin | -1.358 |
Token | illa |
Token ID | 5049 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
warr | +5.777 |
Reply | +5.511 |
mans | +5.320 |
lers | +5.212 |
Interstitial | +5.149 |
Neg logit contributions | |
Russ | -6.573 |
Dems | -6.249 |
oit | -6.141 |
jamin | -5.853 |
andre | -5.772 |
Token | station |
Token ID | 4429 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
warr | +0.077 |
Reply | +0.073 |
Interstitial | +0.070 |
mans | +0.068 |
lers | +0.066 |
Neg logit contributions | |
Russ | -0.076 |
Dems | -0.074 |
oit | -0.074 |
andre | -0.069 |
jamin | -0.069 |
Token | in |
Token ID | 287 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Russ | +1.661 |
oit | +1.623 |
Dems | +1.622 |
andre | +1.512 |
jamin | +1.499 |
Neg logit contributions | |
warr | -1.766 |
Reply | -1.666 |
Interstitial | -1.607 |
mans | -1.542 |
lers | -1.508 |
Token | Delhi |
Token ID | 12517 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
Russ | +0.494 |
Dems | +0.483 |
oit | +0.482 |
andre | +0.451 |
jamin | +0.449 |
Neg logit contributions | |
warr | -0.457 |
Reply | -0.430 |
Interstitial | -0.413 |
mans | -0.397 |
lers | -0.386 |
Token | to |
Token ID | 284 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
warr | +4.361 |
Reply | +4.168 |
Interstitial | +3.888 |
mans | +3.848 |
lers | +3.746 |
Neg logit contributions | |
Russ | -5.099 |
Dems | -4.936 |
oit | -4.887 |
andre | -4.593 |
jamin | -4.547 |
Token | slain |
Token ID | 27029 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
warr | +0.163 |
Reply | +0.153 |
Interstitial | +0.147 |
mans | +0.141 |
lers | +0.137 |
Neg logit contributions | |
Russ | -0.182 |
Dems | -0.178 |
oit | -0.177 |
andre | -0.166 |
jamin | -0.165 |
Token | by |
Token ID | 416 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Russ | +1.094 |
oit | +1.075 |
Dems | +1.073 |
andre | +1.009 |
jamin | +1.000 |
Neg logit contributions | |
warr | -0.966 |
Reply | -0.903 |
Interstitial | -0.867 |
mans | -0.828 |
lers | -0.804 |
Token | a |
Token ID | 257 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Russ | +0.464 |
Dems | +0.453 |
oit | +0.452 |
andre | +0.422 |
jamin | +0.418 |
Neg logit contributions | |
warr | -0.484 |
Reply | -0.460 |
Interstitial | -0.441 |
mans | -0.425 |
lers | -0.414 |
Token | company |
Token ID | 1664 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
warr | +0.273 |
Reply | +0.257 |
Interstitial | +0.246 |
mans | +0.240 |
lers | +0.233 |
Neg logit contributions | |
Russ | -0.251 |
Dems | -0.244 |
oit | -0.243 |
andre | -0.227 |
jamin | -0.225 |
Token | of |
Token ID | 286 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
warr | +1.693 |
Reply | +1.580 |
Interstitial | +1.505 |
mans | +1.478 |
lers | +1.428 |
Neg logit contributions | |
Russ | -1.637 |
Dems | -1.590 |
oit | -1.586 |
andre | -1.485 |
jamin | -1.471 |
Token | Roh |
Token ID | 32694 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
warr | +0.428 |
Reply | +0.404 |
Interstitial | +0.387 |
mans | +0.374 |
lers | +0.364 |
Neg logit contributions | |
Russ | -0.429 |
Dems | -0.418 |
oit | -0.417 |
andre | -0.390 |
jamin | -0.387 |
Token | ir |
Token ID | 343 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
warr | +5.804 |
Reply | +5.687 |
mans | +5.681 |
lers | +5.558 |
Interstitial | +5.553 |
Neg logit contributions | |
Russ | -6.126 |
Dems | -5.848 |
oit | -5.767 |
jamin | -5.541 |
ILLE | -5.455 |
Token | rim |
Token ID | 3036 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
warr | +0.864 |
Reply | +0.793 |
Interstitial | +0.752 |
mans | +0.692 |
lers | +0.681 |
Neg logit contributions | |
Russ | -1.463 |
Dems | -1.440 |
oit | -1.437 |
andre | -1.370 |
jamin | -1.346 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
warr | +3.546 |
Reply | +3.313 |
Interstitial | +3.148 |
mans | +3.105 |
lers | +3.024 |
Neg logit contributions | |
Russ | -4.158 |
Dems | -4.059 |
oit | -4.027 |
jamin | -3.805 |
andre | -3.795 |
Token | Merry |
Token ID | 39001 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
warr | +0.198 |
Reply | +0.186 |
Interstitial | +0.178 |
mans | +0.172 |
lers | +0.168 |
Neg logit contributions | |
Russ | -0.187 |
Dems | -0.182 |
oit | -0.182 |
andre | -0.169 |
jamin | -0.168 |
Token | and |
Token ID | 290 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
warr | +1.418 |
Reply | +1.337 |
Interstitial | +1.270 |
mans | +1.239 |
lers | +1.202 |
Neg logit contributions | |
Russ | -1.496 |
Dems | -1.457 |
oit | -1.451 |
andre | -1.358 |
jamin | -1.349 |
Token | started |
Token ID | 2067 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
warr | +0.174 |
Reply | +0.164 |
Interstitial | +0.157 |
mans | +0.151 |
lers | +0.147 |
Neg logit contributions | |
Russ | -0.193 |
Dems | -0.189 |
oit | -0.188 |
andre | -0.176 |
jamin | -0.176 |
Token | at |
Token ID | 379 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
warr | +0.418 |
Reply | +0.393 |
Interstitial | +0.374 |
mans | +0.361 |
lers | +0.350 |
Neg logit contributions | |
Russ | -0.501 |
Dems | -0.489 |
oit | -0.488 |
andre | -0.459 |
jamin | -0.456 |
Token | Sam |
Token ID | 3409 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
warr | +1.144 |
Reply | +1.080 |
Interstitial | +1.031 |
mans | +0.999 |
lers | +0.971 |
Neg logit contributions | |
Russ | -1.200 |
Dems | -1.170 |
oit | -1.167 |
andre | -1.093 |
jamin | -1.084 |
Token | pl |
Token ID | 489 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
Russ | +0.799 |
Dems | +0.781 |
oit | +0.780 |
andre | +0.735 |
jamin | +0.729 |
Neg logit contributions | |
warr | -0.652 |
Reply | -0.611 |
Interstitial | -0.582 |
mans | -0.558 |
lers | -0.542 |
Token | a |
Token ID | 64 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
warr | +1.168 |
Reply | +1.103 |
Interstitial | +1.048 |
mans | +1.023 |
lers | +0.989 |
Neg logit contributions | |
Russ | -1.329 |
Dems | -1.295 |
oit | -1.285 |
andre | -1.209 |
jamin | -1.203 |
Token | Roh |
Token ID | 32694 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
Russ | +0.373 |
Dems | +0.365 |
oit | +0.364 |
andre | +0.340 |
jamin | +0.338 |
Neg logit contributions | |
warr | -0.361 |
Reply | -0.340 |
Interstitial | -0.326 |
mans | -0.314 |
lers | -0.306 |
Token | t |
Token ID | 83 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
warr | +5.668 |
Reply | +5.467 |
mans | +5.225 |
Interstitial | +5.102 |
lers | +5.079 |
Neg logit contributions | |
Russ | -6.471 |
Dems | -6.157 |
oit | -6.110 |
jamin | -5.777 |
andre | -5.759 |
Token | ak |
Token ID | 461 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
warr | +1.691 |
Reply | +1.594 |
Interstitial | +1.515 |
mans | +1.493 |
lers | +1.444 |
Neg logit contributions | |
Russ | -1.987 |
Dems | -1.931 |
oit | -1.927 |
andre | -1.808 |
jamin | -1.796 |
Token | by |
Token ID | 416 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
warr | +0.328 |
Reply | +0.310 |
Interstitial | +0.296 |
mans | +0.287 |
lers | +0.280 |
Neg logit contributions | |
Russ | -0.321 |
Dems | -0.313 |
oit | -0.312 |
andre | -0.292 |
jamin | -0.289 |
Token | blocking |
Token ID | 12013 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
Russ | +0.317 |
Dems | +0.309 |
oit | +0.308 |
andre | +0.287 |
jamin | +0.285 |
Neg logit contributions | |
warr | -0.333 |
Reply | -0.315 |
Interstitial | -0.302 |
mans | -0.292 |
lers | -0.285 |
Token | national |
Token ID | 2260 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
warr | +1.175 |
Reply | +1.115 |
Interstitial | +1.062 |
mans | +1.038 |
lers | +1.010 |
Neg logit contributions | |
Russ | -1.074 |
oit | -1.047 |
Dems | -1.044 |
andre | -0.971 |
jamin | -0.960 |
Token | exchange |
Token ID | 5163 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Russ | +0.693 |
Dems | +0.673 |
oit | +0.671 |
andre | +0.620 |
jamin | +0.614 |
Neg logit contributions | |
warr | -0.922 |
Reply | -0.877 |
Interstitial | -0.845 |
mans | -0.821 |
lers | -0.802 |
Token | for |
Token ID | 329 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
warr | +0.175 |
Reply | +0.165 |
Interstitial | +0.158 |
mans | +0.153 |
lers | +0.149 |
Neg logit contributions | |
Russ | -0.181 |
Dems | -0.177 |
oit | -0.176 |
andre | -0.165 |
jamin | -0.164 |
Token | a |
Token ID | 257 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
warr | +0.740 |
Reply | +0.699 |
Interstitial | +0.669 |
mans | +0.650 |
lers | +0.632 |
Neg logit contributions | |
Russ | -0.728 |
Dems | -0.709 |
oit | -0.708 |
andre | -0.661 |
jamin | -0.657 |
Token | deal |
Token ID | 1730 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
warr | +0.195 |
Reply | +0.184 |
Interstitial | +0.176 |
mans | +0.171 |
lers | +0.167 |
Neg logit contributions | |
Russ | -0.183 |
Dems | -0.178 |
oit | -0.178 |
andre | -0.166 |
jamin | -0.165 |
Token | on |
Token ID | 319 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
warr | +1.979 |
Reply | +1.863 |
Interstitial | +1.767 |
mans | +1.717 |
lers | +1.670 |
Neg logit contributions | |
Russ | -2.361 |
Dems | -2.296 |
oit | -2.293 |
andre | -2.159 |
jamin | -2.143 |
Token | harmon |
Token ID | 25625 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
warr | +1.471 |
Reply | +1.388 |
Interstitial | +1.324 |
mans | +1.297 |
lers | +1.261 |
Neg logit contributions | |
Russ | -1.421 |
oit | -1.383 |
Dems | -1.378 |
andre | -1.290 |
jamin | -1.281 |
Token | ising |
Token ID | 1710 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
warr | +5.187 |
Reply | +4.899 |
mans | +4.669 |
Interstitial | +4.647 |
lers | +4.544 |
Neg logit contributions | |
Russ | -6.893 |
Dems | -6.670 |
oit | -6.591 |
andre | -6.201 |
jamin | -6.185 |
Token | tax |
Token ID | 1687 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
warr | +0.187 |
Reply | +0.177 |
Interstitial | +0.169 |
mans | +0.163 |
lers | +0.159 |
Neg logit contributions | |
Russ | -0.189 |
Dems | -0.184 |
oit | -0.184 |
andre | -0.172 |
jamin | -0.170 |
Token | bases |
Token ID | 12536 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
warr | +0.170 |
Reply | +0.160 |
Interstitial | +0.153 |
mans | +0.147 |
lers | +0.143 |
Neg logit contributions | |
Russ | -0.196 |
Dems | -0.192 |
oit | -0.191 |
andre | -0.180 |
jamin | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
warr | +0.067 |
Reply | +0.063 |
Interstitial | +0.061 |
mans | +0.058 |
lers | +0.057 |
Neg logit contributions | |
Russ | -0.071 |
Dems | -0.069 |
oit | -0.069 |
andre | -0.064 |
jamin | -0.064 |
Token | Others |
Token ID | 12691 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Russ | +0.203 |
Dems | +0.197 |
oit | +0.196 |
andre | +0.183 |
jamin | +0.181 |
Neg logit contributions | |
warr | -0.236 |
Reply | -0.223 |
Interstitial | -0.214 |
mans | -0.208 |
lers | -0.202 |
Token | PA |
Token ID | 4537 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
warr | +0.202 |
Reply | +0.189 |
Interstitial | +0.181 |
mans | +0.174 |
lers | +0.169 |
Neg logit contributions | |
Russ | -0.246 |
Dems | -0.240 |
oit | -0.240 |
andre | -0.226 |
jamin | -0.224 |
Token | ( |
Token ID | 357 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Russ | +1.805 |
Dems | +1.779 |
oit | +1.760 |
andre | +1.649 |
jamin | +1.643 |
Neg logit contributions | |
warr | -1.770 |
Reply | -1.660 |
Interstitial | -1.617 |
mans | -1.544 |
lers | -1.515 |
Token | on |
Token ID | 261 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Russ | +0.318 |
Dems | +0.308 |
oit | +0.308 |
andre | +0.290 |
jamin | +0.286 |
Neg logit contributions | |
warr | -0.302 |
Reply | -0.279 |
Interstitial | -0.269 |
mans | -0.259 |
lers | -0.254 |
Token | behalf |
Token ID | 8378 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
warr | +1.940 |
Reply | +1.830 |
Interstitial | +1.701 |
mans | +1.658 |
lers | +1.598 |
Neg logit contributions | |
Russ | -2.822 |
oit | -2.749 |
Dems | -2.749 |
andre | -2.602 |
jamin | -2.574 |
Token | of |
Token ID | 286 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
warr | +1.207 |
Reply | +1.148 |
Interstitial | +1.101 |
mans | +1.071 |
lers | +1.044 |
Neg logit contributions | |
Russ | -1.036 |
Dems | -1.008 |
oit | -1.006 |
andre | -0.935 |
jamin | -0.926 |
Token | Fuj |
Token ID | 32671 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
warr | +0.355 |
Reply | +0.337 |
Interstitial | +0.324 |
mans | +0.313 |
lers | +0.306 |
Neg logit contributions | |
Russ | -0.314 |
Dems | -0.306 |
oit | -0.305 |
andre | -0.284 |
jamin | -0.282 |
Token | ita |
Token ID | 5350 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
warr | +6.419 |
Reply | +6.179 |
mans | +5.950 |
Interstitial | +5.912 |
lers | +5.857 |
Neg logit contributions | |
Russ | -5.541 |
Dems | -5.277 |
oit | -5.249 |
andre | -4.862 |
jamin | -4.793 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
warr | +0.092 |
Reply | +0.086 |
Interstitial | +0.083 |
mans | +0.080 |
lers | +0.078 |
Neg logit contributions | |
Russ | -0.094 |
Dems | -0.092 |
oit | -0.092 |
andre | -0.086 |
jamin | -0.085 |
Token | H |
Token ID | 367 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
warr | +0.298 |
Reply | +0.282 |
Interstitial | +0.272 |
mans | +0.261 |
lers | +0.254 |
Neg logit contributions | |
Russ | -0.289 |
Dems | -0.283 |
oit | -0.281 |
andre | -0.262 |
jamin | -0.260 |
Token | arg |
Token ID | 853 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
warr | +0.419 |
Reply | +0.394 |
Interstitial | +0.376 |
mans | +0.364 |
lers | +0.353 |
Neg logit contributions | |
Russ | -0.470 |
Dems | -0.460 |
oit | -0.458 |
andre | -0.430 |
jamin | -0.427 |
Token | ro |
Token ID | 305 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
warr | +0.216 |
Reply | +0.205 |
Interstitial | +0.194 |
mans | +0.190 |
lers | +0.184 |
Neg logit contributions | |
Russ | -0.261 |
Dems | -0.256 |
oit | -0.254 |
andre | -0.240 |
jamin | -0.238 |
Token | "] |
Token ID | 8973 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
warr | +0.398 |
Reply | +0.377 |
Interstitial | +0.361 |
mans | +0.350 |
lers | +0.341 |
Neg logit contributions | |
Russ | -0.372 |
Dems | -0.363 |
oit | -0.362 |
andre | -0.337 |
jamin | -0.335 |
Token | [ |
Token ID | 685 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
warr | +0.181 |
Reply | +0.169 |
Interstitial | +0.163 |
mans | +0.157 |
lers | +0.153 |
Neg logit contributions | |
Russ | -0.177 |
Dems | -0.174 |
oit | -0.172 |
andre | -0.160 |
jamin | -0.159 |
Token | Site |
Token ID | 29123 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
warr | +1.212 |
Reply | +1.149 |
Interstitial | +1.096 |
mans | +1.058 |
lers | +1.029 |
Neg logit contributions | |
Russ | -1.295 |
Dems | -1.267 |
oit | -1.263 |
andre | -1.185 |
jamin | -1.176 |
Token | " |
Token ID | 366 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
warr | +0.993 |
Reply | +0.951 |
Interstitial | +0.913 |
mans | +0.889 |
lers | +0.867 |
Neg logit contributions | |
Russ | -0.756 |
Dems | -0.736 |
oit | -0.734 |
andre | -0.680 |
jamin | -0.671 |
Token | W |
Token ID | 54 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
warr | +0.568 |
Reply | +0.536 |
Interstitial | +0.511 |
mans | +0.494 |
lers | +0.479 |
Neg logit contributions | |
Russ | -0.639 |
Dems | -0.624 |
oit | -0.623 |
andre | -0.585 |
jamin | -0.580 |
Token | ijk |
Token ID | 45961 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
warr | +0.762 |
Reply | +0.720 |
Interstitial | +0.688 |
mans | +0.668 |
lers | +0.649 |
Neg logit contributions | |
Russ | -0.815 |
Dems | -0.796 |
oit | -0.792 |
andre | -0.742 |
jamin | -0.737 |
Token | a |
Token ID | 257 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
warr | +5.766 |
Reply | +5.599 |
mans | +5.437 |
lers | +5.294 |
Interstitial | +5.002 |
Neg logit contributions | |
Russ | -6.097 |
Dems | -5.990 |
oit | -5.813 |
andre | -5.612 |
jamin | -5.505 |
Token | an |
Token ID | 272 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
warr | +0.303 |
Reply | +0.285 |
Interstitial | +0.268 |
mans | +0.262 |
lers | +0.253 |
Neg logit contributions | |
Russ | -0.473 |
Dems | -0.462 |
oit | -0.461 |
andre | -0.439 |
jamin | -0.438 |
Token | Z |
Token ID | 1168 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
warr | +1.552 |
Reply | +1.461 |
Interstitial | +1.388 |
mans | +1.371 |
lers | +1.316 |
Neg logit contributions | |
Russ | -1.828 |
oit | -1.770 |
Dems | -1.768 |
andre | -1.677 |
jamin | -1.653 |
Token | ee |
Token ID | 1453 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
warr | +0.791 |
Reply | +0.742 |
Interstitial | +0.712 |
mans | +0.683 |
lers | +0.664 |
Neg logit contributions | |
Russ | -0.826 |
oit | -0.808 |
Dems | -0.806 |
andre | -0.755 |
jamin | -0.748 |
Token | "] |
Token ID | 8973 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
warr | +0.976 |
Reply | +0.926 |
Interstitial | +0.875 |
mans | +0.868 |
lers | +0.842 |
Neg logit contributions | |
Russ | -1.060 |
oit | -1.031 |
Dems | -1.027 |
andre | -0.968 |
jamin | -0.958 |
Token | Pearce |
Token ID | 41902 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
warr | +1.596 |
Reply | +1.509 |
Interstitial | +1.446 |
mans | +1.401 |
lers | +1.364 |
Neg logit contributions | |
Russ | -1.541 |
Dems | -1.502 |
oit | -1.498 |
andre | -1.398 |
jamin | -1.387 |
Token | at |
Token ID | 379 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
warr | +1.504 |
Reply | +1.423 |
Interstitial | +1.357 |
mans | +1.316 |
lers | +1.280 |
Neg logit contributions | |
Russ | -1.602 |
Dems | -1.562 |
oit | -1.560 |
andre | -1.460 |
jamin | -1.452 |
Token | An |
Token ID | 1052 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
warr | +0.780 |
Reply | +0.739 |
Interstitial | +0.709 |
mans | +0.688 |
lers | +0.670 |
Neg logit contributions | |
Russ | -0.706 |
Dems | -0.687 |
oit | -0.685 |
andre | -0.638 |
jamin | -0.633 |
Token | Evening |
Token ID | 31867 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
warr | +1.628 |
Reply | +1.540 |
Interstitial | +1.471 |
mans | +1.424 |
lers | +1.383 |
Neg logit contributions | |
Russ | -1.724 |
Dems | -1.683 |
oit | -1.676 |
andre | -1.570 |
jamin | -1.562 |
Token | with |
Token ID | 351 |
Feature activation | -9.02e-01 |
Pos logit contributions | |
warr | +0.296 |
Reply | +0.279 |
Interstitial | +0.267 |
mans | +0.258 |
lers | +0.251 |
Neg logit contributions | |
Russ | -0.313 |
Dems | -0.306 |
oit | -0.305 |
andre | -0.285 |
jamin | -0.283 |
Token | Conor |
Token ID | 41708 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
Russ | +1.169 |
Dems | +1.146 |
oit | +1.135 |
andre | +1.059 |
jamin | +1.046 |
Neg logit contributions | |
warr | -1.253 |
Reply | -1.179 |
Interstitial | -1.132 |
mans | -1.095 |
lers | -1.065 |
Token | McGregor |
Token ID | 32777 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
warr | +4.493 |
Reply | +4.248 |
Interstitial | +3.939 |
mans | +3.827 |
lers | +3.639 |
Neg logit contributions | |
Russ | -7.396 |
Dems | -7.270 |
oit | -7.216 |
andre | -6.819 |
jamin | -6.812 |
Token | at |
Token ID | 379 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
warr | +2.988 |
Reply | +2.839 |
Interstitial | +2.686 |
mans | +2.609 |
lers | +2.526 |
Neg logit contributions | |
Russ | -3.451 |
oit | -3.372 |
Dems | -3.362 |
andre | -3.153 |
jamin | -3.144 |
Token | the |
Token ID | 262 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
warr | +0.785 |
Reply | +0.743 |
Interstitial | +0.714 |
mans | +0.691 |
lers | +0.674 |
Neg logit contributions | |
Russ | -0.718 |
Dems | -0.700 |
oit | -0.698 |
andre | -0.650 |
jamin | -0.644 |
Token | SEC |
Token ID | 10729 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
warr | +0.690 |
Reply | +0.652 |
Interstitial | +0.626 |
mans | +0.605 |
lers | +0.590 |
Neg logit contributions | |
Russ | -0.652 |
Dems | -0.636 |
oit | -0.634 |
andre | -0.591 |
jamin | -0.585 |
Token | Arm |
Token ID | 7057 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
Russ | +1.961 |
Dems | +1.918 |
oit | +1.903 |
andre | +1.779 |
jamin | +1.764 |
Neg logit contributions | |
warr | -1.825 |
Reply | -1.715 |
Interstitial | -1.633 |
mans | -1.570 |
lers | -1.533 |
Token | and |
Token ID | 290 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
Russ | +0.285 |
oit | +0.279 |
Dems | +0.278 |
andre | +0.260 |
jamin | +0.258 |
Neg logit contributions | |
warr | -0.272 |
Reply | -0.256 |
Interstitial | -0.246 |
mans | -0.234 |
lers | -0.229 |
Token | wetlands |
Token ID | 49297 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Russ | +0.044 |
Dems | +0.043 |
oit | +0.043 |
andre | +0.040 |
jamin | +0.040 |
Neg logit contributions | |
warr | -0.050 |
Reply | -0.047 |
Interstitial | -0.045 |
mans | -0.044 |
lers | -0.043 |
Token | at |
Token ID | 379 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
Russ | +1.739 |
oit | +1.702 |
Dems | +1.701 |
andre | +1.590 |
jamin | +1.574 |
Neg logit contributions | |
warr | -1.666 |
Reply | -1.561 |
Interstitial | -1.519 |
mans | -1.416 |
lers | -1.385 |
Token | Kan |
Token ID | 14248 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
warr | +0.788 |
Reply | +0.740 |
Interstitial | +0.705 |
mans | +0.685 |
lers | +0.663 |
Neg logit contributions | |
Russ | -0.883 |
Dems | -0.861 |
oit | -0.859 |
andre | -0.806 |
jamin | -0.801 |
Token | akia |
Token ID | 21897 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
warr | +3.313 |
Reply | +3.176 |
Interstitial | +3.046 |
mans | +3.017 |
lers | +2.921 |
Neg logit contributions | |
Russ | -3.480 |
Dems | -3.389 |
oit | -3.329 |
andre | -3.118 |
jamin | -3.088 |
Token | Nag |
Token ID | 15196 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
warr | +1.171 |
Reply | +1.086 |
Interstitial | +1.021 |
mans | +0.997 |
lers | +0.958 |
Neg logit contributions | |
Russ | -1.730 |
Dems | -1.691 |
oit | -1.684 |
andre | -1.600 |
jamin | -1.590 |
Token | ar |
Token ID | 283 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
warr | +4.957 |
Reply | +4.928 |
mans | +4.702 |
lers | +4.634 |
Interstitial | +4.586 |
Neg logit contributions | |
Russ | -6.403 |
Dems | -6.285 |
oit | -6.052 |
ILLE | -5.778 |
andre | -5.754 |
Token | in |
Token ID | 287 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
warr | +1.824 |
Reply | +1.728 |
Interstitial | +1.639 |
mans | +1.612 |
lers | +1.556 |
Neg logit contributions | |
Russ | -1.954 |
Dems | -1.903 |
oit | -1.886 |
andre | -1.777 |
jamin | -1.763 |
Token | Mir |
Token ID | 7381 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
warr | +0.057 |
Reply | +0.054 |
Interstitial | +0.052 |
mans | +0.050 |
lers | +0.048 |
Neg logit contributions | |
Russ | -0.060 |
Dems | -0.058 |
oit | -0.058 |
andre | -0.055 |
jamin | -0.054 |
Token | a |
Token ID | 64 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
Russ | +0.331 |
Dems | +0.325 |
oit | +0.325 |
andre | +0.304 |
jamin | +0.302 |
Neg logit contributions | |
warr | -0.325 |
Reply | -0.306 |
Interstitial | -0.295 |
mans | -0.280 |
lers | -0.275 |
Token | Road |
Token ID | 5567 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
warr | +1.052 |
Reply | +1.011 |
Interstitial | +0.945 |
mans | +0.935 |
lers | +0.894 |
Neg logit contributions | |
Russ | -1.091 |
Dems | -1.065 |
oit | -1.058 |
andre | -0.994 |
jamin | -0.988 |
Token | vm |
Token ID | 14761 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
Russ | +2.051 |
oit | +2.001 |
Dems | +1.985 |
andre | +1.867 |
jamin | +1.848 |
Neg logit contributions | |
warr | -2.076 |
Reply | -1.946 |
Interstitial | -1.879 |
mans | -1.795 |
lers | -1.747 |
Token | ash |
Token ID | 1077 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
warr | +1.105 |
Reply | +1.041 |
Interstitial | +0.991 |
mans | +0.977 |
lers | +0.950 |
Neg logit contributions | |
Russ | -1.110 |
Dems | -1.086 |
oit | -1.065 |
jamin | -0.999 |
andre | -0.997 |
Token | ship |
Token ID | 4074 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Russ | +1.091 |
Dems | +1.065 |
oit | +1.063 |
andre | +0.994 |
jamin | +0.986 |
Neg logit contributions | |
warr | -1.059 |
Reply | -1.000 |
Interstitial | -0.957 |
mans | -0.923 |
lers | -0.898 |
Token | yard |
Token ID | 9413 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Russ | +1.974 |
Dems | +1.931 |
oit | +1.929 |
andre | +1.807 |
jamin | +1.803 |
Neg logit contributions | |
warr | -1.740 |
Reply | -1.639 |
Interstitial | -1.576 |
mans | -1.488 |
lers | -1.451 |
Token | at |
Token ID | 379 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Russ | +2.512 |
Dems | +2.460 |
oit | +2.457 |
andre | +2.282 |
jamin | +2.264 |
Neg logit contributions | |
warr | -2.438 |
Reply | -2.314 |
Interstitial | -2.248 |
mans | -2.114 |
lers | -2.058 |
Token | Sever |
Token ID | 26434 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
warr | +0.505 |
Reply | +0.476 |
Interstitial | +0.454 |
mans | +0.444 |
lers | +0.432 |
Neg logit contributions | |
Russ | -0.479 |
Dems | -0.466 |
oit | -0.465 |
andre | -0.435 |
jamin | -0.431 |
Token | od |
Token ID | 375 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
warr | +4.942 |
mans | +4.669 |
Reply | +4.573 |
lers | +4.453 |
Interstitial | +4.124 |
Neg logit contributions | |
Russ | -6.588 |
Dems | -6.439 |
oit | -6.277 |
jamin | -6.032 |
ILLE | -6.010 |
Token | v |
Token ID | 85 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
warr | +1.341 |
Reply | +1.252 |
Interstitial | +1.197 |
mans | +1.187 |
lers | +1.148 |
Neg logit contributions | |
Russ | -1.595 |
Dems | -1.546 |
oit | -1.544 |
andre | -1.448 |
jamin | -1.444 |
Token | insk |
Token ID | 35803 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
warr | +1.353 |
Reply | +1.284 |
Interstitial | +1.215 |
mans | +1.200 |
lers | +1.177 |
Neg logit contributions | |
Russ | -1.578 |
Dems | -1.539 |
oit | -1.526 |
jamin | -1.442 |
andre | -1.441 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
Russ | +1.094 |
Dems | +1.068 |
oit | +1.068 |
andre | +0.999 |
jamin | +0.992 |
Neg logit contributions | |
warr | -1.017 |
Reply | -0.960 |
Interstitial | -0.918 |
mans | -0.884 |
lers | -0.859 |
Token | which |
Token ID | 543 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
warr | +0.015 |
Reply | +0.015 |
Interstitial | +0.014 |
mans | +0.014 |
lers | +0.013 |
Neg logit contributions | |
Russ | -0.012 |
Dems | -0.011 |
oit | -0.011 |
andre | -0.010 |
jamin | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
warr | +0.437 |
Reply | +0.412 |
Interstitial | +0.397 |
mans | +0.385 |
lers | +0.376 |
Neg logit contributions | |
Russ | -0.355 |
Dems | -0.345 |
oit | -0.344 |
andre | -0.319 |
jamin | -0.317 |
Token | Senior |
Token ID | 31224 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
warr | +0.196 |
Reply | +0.182 |
Interstitial | +0.174 |
mans | +0.168 |
lers | +0.163 |
Neg logit contributions | |
Russ | -0.236 |
Dems | -0.230 |
oit | -0.230 |
andre | -0.216 |
jamin | -0.215 |
Token | advocate |
Token ID | 12811 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
warr | +0.693 |
Reply | +0.654 |
Interstitial | +0.624 |
mans | +0.605 |
lers | +0.588 |
Neg logit contributions | |
Russ | -0.726 |
Dems | -0.707 |
oit | -0.707 |
andre | -0.661 |
jamin | -0.657 |
Token | Muk |
Token ID | 31509 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Russ | +0.529 |
Dems | +0.521 |
oit | +0.518 |
andre | +0.484 |
jamin | +0.482 |
Neg logit contributions | |
warr | -0.503 |
Reply | -0.475 |
Interstitial | -0.460 |
mans | -0.434 |
lers | -0.426 |
Token | ul |
Token ID | 377 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Russ | +0.741 |
Dems | +0.727 |
oit | +0.727 |
andre | +0.691 |
jamin | +0.685 |
Neg logit contributions | |
warr | -0.419 |
Reply | -0.385 |
Interstitial | -0.363 |
mans | -0.341 |
lers | -0.328 |
Token | Roh |
Token ID | 32694 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
warr | +2.337 |
Reply | +2.213 |
Interstitial | +2.095 |
mans | +2.057 |
lers | +1.990 |
Neg logit contributions | |
Russ | -2.579 |
Dems | -2.510 |
oit | -2.505 |
andre | -2.345 |
jamin | -2.326 |
Token | at |
Token ID | 265 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
warr | +5.039 |
Reply | +4.767 |
mans | +4.484 |
Interstitial | +4.434 |
lers | +4.323 |
Neg logit contributions | |
Russ | -6.789 |
Dems | -6.498 |
oit | -6.407 |
andre | -6.088 |
jamin | -6.082 |
Token | gi |
Token ID | 12397 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
warr | +1.304 |
Reply | +1.223 |
Interstitial | +1.165 |
mans | +1.120 |
lers | +1.087 |
Neg logit contributions | |
Russ | -1.592 |
Dems | -1.556 |
oit | -1.553 |
andre | -1.462 |
jamin | -1.451 |
Token | appearing |
Token ID | 12655 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
warr | +1.513 |
Reply | +1.429 |
Interstitial | +1.357 |
mans | +1.320 |
lers | +1.278 |
Neg logit contributions | |
Russ | -1.651 |
Dems | -1.608 |
oit | -1.604 |
andre | -1.505 |
jamin | -1.493 |
Token | for |
Token ID | 329 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
warr | +0.272 |
Reply | +0.256 |
Interstitial | +0.245 |
mans | +0.236 |
lers | +0.230 |
Neg logit contributions | |
Russ | -0.295 |
Dems | -0.288 |
oit | -0.288 |
andre | -0.270 |
jamin | -0.268 |
Token | Gh |
Token ID | 11972 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
warr | +1.419 |
Reply | +1.340 |
Interstitial | +1.269 |
mans | +1.244 |
lers | +1.202 |
Neg logit contributions | |
Russ | -1.521 |
Dems | -1.474 |
oit | -1.474 |
andre | -1.385 |
jamin | -1.371 |
Token | 16 |
Token ID | 1433 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
warr | +0.864 |
Reply | +0.803 |
Interstitial | +0.768 |
mans | +0.739 |
lers | +0.718 |
Neg logit contributions | |
Russ | -1.064 |
Dems | -1.040 |
oit | -1.037 |
andre | -0.976 |
jamin | -0.971 |
Token | , |
Token ID | 11 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
warr | +0.474 |
Reply | +0.445 |
Interstitial | +0.427 |
mans | +0.411 |
lers | +0.400 |
Neg logit contributions | |
Russ | -0.529 |
Dems | -0.517 |
oit | -0.515 |
andre | -0.484 |
jamin | -0.481 |
Token | violence |
Token ID | 3685 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
warr | +0.386 |
Reply | +0.366 |
Interstitial | +0.352 |
mans | +0.340 |
lers | +0.332 |
Neg logit contributions | |
Russ | -0.341 |
Dems | -0.333 |
oit | -0.331 |
andre | -0.308 |
jamin | -0.306 |
Token | erupted |
Token ID | 23681 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
warr | +0.435 |
Reply | +0.406 |
Interstitial | +0.387 |
mans | +0.372 |
lers | +0.359 |
Neg logit contributions | |
Russ | -0.579 |
Dems | -0.567 |
oit | -0.565 |
andre | -0.533 |
jamin | -0.530 |
Token | in |
Token ID | 287 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
warr | +0.539 |
Reply | +0.505 |
Interstitial | +0.482 |
mans | +0.464 |
lers | +0.450 |
Neg logit contributions | |
Russ | -0.640 |
Dems | -0.626 |
oit | -0.625 |
andre | -0.587 |
jamin | -0.583 |
Token | Roh |
Token ID | 32694 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Russ | +0.475 |
Dems | +0.465 |
oit | +0.463 |
andre | +0.433 |
jamin | +0.430 |
Neg logit contributions | |
warr | -0.467 |
Reply | -0.439 |
Interstitial | -0.426 |
mans | -0.407 |
lers | -0.397 |
Token | t |
Token ID | 83 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
warr | +4.904 |
Reply | +4.691 |
mans | +4.434 |
lers | +4.354 |
Interstitial | +4.205 |
Neg logit contributions | |
Russ | -6.663 |
Dems | -6.359 |
oit | -6.218 |
jamin | -5.947 |
andre | -5.876 |
Token | ak |
Token ID | 461 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
warr | +1.507 |
Reply | +1.435 |
Interstitial | +1.362 |
mans | +1.333 |
lers | +1.293 |
Neg logit contributions | |
Russ | -1.825 |
Dems | -1.782 |
oit | -1.769 |
andre | -1.660 |
jamin | -1.649 |
Token | city |
Token ID | 1748 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
warr | +0.156 |
Reply | +0.146 |
Interstitial | +0.140 |
mans | +0.135 |
lers | +0.132 |
Neg logit contributions | |
Russ | -0.164 |
Dems | -0.160 |
oit | -0.160 |
andre | -0.150 |
jamin | -0.149 |
Token | which |
Token ID | 543 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
warr | +0.025 |
Reply | +0.023 |
Interstitial | +0.022 |
mans | +0.021 |
lers | +0.021 |
Neg logit contributions | |
Russ | -0.026 |
Dems | -0.026 |
oit | -0.026 |
andre | -0.024 |
jamin | -0.024 |
Token | continued |
Token ID | 3767 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
warr | +1.136 |
Reply | +1.066 |
Interstitial | +1.018 |
mans | +0.981 |
lers | +0.952 |
Neg logit contributions | |
Russ | -1.332 |
Dems | -1.303 |
oit | -1.299 |
andre | -1.221 |
jamin | -1.212 |
Token | to |
Token ID | 284 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
warr | +1.351 |
Reply | +1.287 |
Interstitial | +1.223 |
mans | +1.191 |
lers | +1.162 |
Neg logit contributions | |
Russ | -1.329 |
Dems | -1.297 |
oit | -1.293 |
andre | -1.207 |
jamin | -1.197 |
Token | save |
Token ID | 3613 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Russ | +0.087 |
Dems | +0.085 |
oit | +0.085 |
andre | +0.079 |
jamin | +0.078 |
Neg logit contributions | |
warr | -0.091 |
Reply | -0.086 |
Interstitial | -0.083 |
mans | -0.080 |
lers | -0.078 |
Token | public |
Token ID | 1171 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
warr | +1.454 |
Reply | +1.376 |
Interstitial | +1.312 |
mans | +1.279 |
lers | +1.246 |
Neg logit contributions | |
Russ | -1.381 |
Dems | -1.342 |
oit | -1.340 |
andre | -1.250 |
jamin | -1.239 |
Token | property |
Token ID | 3119 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Russ | +0.796 |
Dems | +0.777 |
oit | +0.774 |
andre | +0.723 |
jamin | +0.718 |
Neg logit contributions | |
warr | -0.826 |
Reply | -0.779 |
Interstitial | -0.751 |
mans | -0.723 |
lers | -0.705 |
Token | in |
Token ID | 287 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
warr | +2.255 |
Reply | +2.136 |
Interstitial | +2.015 |
mans | +1.970 |
lers | +1.911 |
Neg logit contributions | |
Russ | -2.553 |
Dems | -2.497 |
oit | -2.491 |
andre | -2.340 |
jamin | -2.324 |
Token | Roh |
Token ID | 32694 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
Russ | +0.761 |
Dems | +0.743 |
oit | +0.741 |
andre | +0.693 |
jamin | +0.687 |
Neg logit contributions | |
warr | -0.764 |
Reply | -0.722 |
Interstitial | -0.694 |
mans | -0.670 |
lers | -0.652 |
Token | t |
Token ID | 83 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Reply | +4.713 |
warr | +4.626 |
mans | +4.431 |
lers | +4.363 |
Interstitial | +4.320 |
Neg logit contributions | |
Russ | -6.587 |
Dems | -6.433 |
oit | -6.201 |
ILLE | -5.920 |
andre | -5.916 |
Token | ak |
Token ID | 461 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
warr | +1.586 |
Reply | +1.525 |
Interstitial | +1.441 |
mans | +1.414 |
lers | +1.371 |
Neg logit contributions | |
Russ | -1.952 |
Dems | -1.909 |
oit | -1.892 |
andre | -1.777 |
jamin | -1.765 |
Token | city |
Token ID | 1748 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
Russ | +0.053 |
Dems | +0.051 |
oit | +0.051 |
andre | +0.048 |
jamin | +0.048 |
Neg logit contributions | |
warr | -0.052 |
Reply | -0.049 |
Interstitial | -0.047 |
mans | -0.045 |
lers | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Russ | +0.340 |
Dems | +0.332 |
oit | +0.331 |
andre | +0.310 |
jamin | +0.308 |
Neg logit contributions | |
warr | -0.321 |
Reply | -0.302 |
Interstitial | -0.289 |
mans | -0.279 |
lers | -0.271 |
Token | parts |
Token ID | 3354 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Russ | +0.476 |
Dems | +0.466 |
oit | +0.464 |
andre | +0.429 |
jamin | +0.424 |
Neg logit contributions | |
warr | -0.580 |
Reply | -0.550 |
Interstitial | -0.533 |
mans | -0.515 |
lers | -0.501 |
Token | 24 |
Token ID | 1987 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Russ | +0.617 |
Dems | +0.604 |
oit | +0.599 |
jamin | +0.556 |
andre | +0.554 |
Neg logit contributions | |
warr | -0.703 |
Reply | -0.645 |
Interstitial | -0.629 |
mans | -0.597 |
lers | -0.584 |
Token | , |
Token ID | 11 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
warr | +0.518 |
Reply | +0.488 |
Interstitial | +0.466 |
mans | +0.450 |
lers | +0.437 |
Neg logit contributions | |
Russ | -0.591 |
Dems | -0.577 |
oit | -0.576 |
andre | -0.540 |
jamin | -0.536 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
warr | +0.602 |
Reply | +0.568 |
Interstitial | +0.546 |
mans | +0.528 |
lers | +0.514 |
Neg logit contributions | |
Russ | -0.560 |
Dems | -0.547 |
oit | -0.544 |
andre | -0.507 |
jamin | -0.503 |
Token | , |
Token ID | 11 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
warr | +0.838 |
Reply | +0.792 |
Interstitial | +0.754 |
mans | +0.727 |
lers | +0.708 |
Neg logit contributions | |
Russ | -0.971 |
Dems | -0.945 |
oit | -0.944 |
andre | -0.885 |
jamin | -0.880 |
Token | in |
Token ID | 287 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
warr | +0.445 |
Reply | +0.418 |
Interstitial | +0.400 |
mans | +0.386 |
lers | +0.375 |
Neg logit contributions | |
Russ | -0.495 |
Dems | -0.484 |
oit | -0.483 |
andre | -0.453 |
jamin | -0.449 |
Token | Tiff |
Token ID | 35775 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
Russ | +0.147 |
Dems | +0.142 |
oit | +0.142 |
andre | +0.131 |
jamin | +0.130 |
Neg logit contributions | |
warr | -0.196 |
Reply | -0.187 |
Interstitial | -0.180 |
mans | -0.175 |
lers | -0.171 |
Token | in |
Token ID | 259 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
warr | +4.143 |
Reply | +3.857 |
mans | +3.834 |
lers | +3.783 |
Interstitial | +3.591 |
Neg logit contributions | |
Russ | -7.318 |
Dems | -7.098 |
oit | -6.787 |
jamin | -6.658 |
andre | -6.500 |
Token | , |
Token ID | 11 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Russ | +1.818 |
oit | +1.793 |
Dems | +1.788 |
andre | +1.675 |
jamin | +1.661 |
Neg logit contributions | |
warr | -1.728 |
Reply | -1.599 |
Interstitial | -1.541 |
mans | -1.479 |
lers | -1.436 |
Token | Iowa |
Token ID | 9406 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
warr | +0.678 |
Reply | +0.650 |
Interstitial | +0.629 |
mans | +0.616 |
lers | +0.605 |
Neg logit contributions | |
Russ | -0.322 |
Dems | -0.307 |
oit | -0.307 |
andre | -0.277 |
jamin | -0.272 |
Token | . |
Token ID | 13 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
Russ | +2.209 |
Dems | +2.169 |
oit | +2.161 |
andre | +2.022 |
jamin | +2.010 |
Neg logit contributions | |
warr | -2.172 |
Reply | -2.033 |
Interstitial | -1.952 |
mans | -1.886 |
lers | -1.826 |
Token | Hide |
Token ID | 10415 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
warr | +0.757 |
Reply | +0.718 |
Interstitial | +0.683 |
mans | +0.660 |
lers | +0.640 |
Neg logit contributions | |
Russ | -0.925 |
oit | -0.903 |
Dems | -0.897 |
andre | -0.850 |
jamin | -0.842 |
Token | Centre |
Token ID | 9072 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
warr | +3.112 |
Reply | +2.939 |
Interstitial | +2.820 |
mans | +2.771 |
lers | +2.690 |
Neg logit contributions | |
Russ | -3.145 |
Dems | -3.057 |
oit | -3.032 |
andre | -2.834 |
jamin | -2.811 |
Token | for |
Token ID | 329 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
warr | +2.031 |
Reply | +1.913 |
Interstitial | +1.837 |
mans | +1.773 |
lers | +1.721 |
Neg logit contributions | |
Russ | -2.322 |
Dems | -2.258 |
oit | -2.250 |
andre | -2.110 |
jamin | -2.104 |
Token | Psychological |
Token ID | 30583 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
warr | +0.860 |
Reply | +0.813 |
Interstitial | +0.778 |
mans | +0.754 |
lers | +0.734 |
Neg logit contributions | |
Russ | -0.861 |
Dems | -0.838 |
oit | -0.837 |
andre | -0.782 |
jamin | -0.776 |
Token | Services |
Token ID | 6168 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
warr | +0.474 |
Reply | +0.448 |
Interstitial | +0.430 |
mans | +0.417 |
lers | +0.406 |
Neg logit contributions | |
Russ | -0.445 |
Dems | -0.434 |
oit | -0.433 |
andre | -0.403 |
jamin | -0.400 |
Token | in |
Token ID | 287 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
warr | +0.300 |
Reply | +0.282 |
Interstitial | +0.269 |
mans | +0.260 |
lers | +0.253 |
Neg logit contributions | |
Russ | -0.333 |
Dems | -0.325 |
oit | -0.325 |
andre | -0.305 |
jamin | -0.302 |
Token | Rath |
Token ID | 26494 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
Russ | +0.496 |
Dems | +0.483 |
oit | +0.482 |
andre | +0.450 |
jamin | +0.446 |
Neg logit contributions | |
warr | -0.527 |
Reply | -0.498 |
Interstitial | -0.478 |
mans | -0.462 |
lers | -0.450 |
Token | gar |
Token ID | 4563 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
warr | +5.731 |
Reply | +5.501 |
mans | +5.317 |
Interstitial | +5.252 |
lers | +5.152 |
Neg logit contributions | |
Russ | -5.774 |
Dems | -5.672 |
oit | -5.535 |
andre | -5.188 |
jamin | -5.158 |
Token | . |
Token ID | 13 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
warr | +1.739 |
Reply | +1.638 |
Interstitial | +1.566 |
mans | +1.513 |
lers | +1.472 |
Neg logit contributions | |
Russ | -1.823 |
Dems | -1.778 |
oit | -1.776 |
andre | -1.663 |
jamin | -1.649 |
Token | Upon |
Token ID | 14438 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
warr | +0.873 |
Reply | +0.831 |
Interstitial | +0.798 |
mans | +0.773 |
lers | +0.753 |
Neg logit contributions | |
Russ | -0.789 |
Dems | -0.767 |
oit | -0.767 |
andre | -0.713 |
jamin | -0.707 |
Token | contacting |
Token ID | 27390 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
warr | +2.308 |
Reply | +2.189 |
Interstitial | +2.067 |
mans | +2.014 |
lers | +1.954 |
Neg logit contributions | |
Russ | -2.531 |
oit | -2.463 |
Dems | -2.454 |
andre | -2.307 |
jamin | -2.283 |
Token | the |
Token ID | 262 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
Russ | +0.303 |
Dems | +0.297 |
oit | +0.295 |
andre | +0.276 |
jamin | +0.273 |
Neg logit contributions | |
warr | -0.323 |
Reply | -0.306 |
Interstitial | -0.295 |
mans | -0.284 |
lers | -0.276 |
Token | Sherman |
Token ID | 23198 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
warr | +1.431 |
Reply | +1.356 |
Interstitial | +1.297 |
mans | +1.267 |
lers | +1.237 |
Neg logit contributions | |
Russ | -1.285 |
oit | -1.248 |
Dems | -1.248 |
andre | -1.168 |
jamin | -1.154 |
Token | , |
Token ID | 11 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
warr | +2.352 |
Reply | +2.237 |
Interstitial | +2.116 |
mans | +2.090 |
lers | +2.018 |
Neg logit contributions | |
Russ | -2.571 |
Dems | -2.514 |
oit | -2.504 |
andre | -2.361 |
jamin | -2.334 |
Token | Silver |
Token ID | 7698 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
Russ | +0.072 |
oit | +0.070 |
Dems | +0.070 |
andre | +0.065 |
jamin | +0.065 |
Neg logit contributions | |
warr | -0.077 |
Reply | -0.073 |
Interstitial | -0.071 |
mans | -0.068 |
lers | -0.066 |
Token | stein |
Token ID | 5714 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
warr | +0.762 |
Reply | +0.713 |
Interstitial | +0.676 |
mans | +0.652 |
lers | +0.630 |
Neg logit contributions | |
Russ | -1.017 |
Dems | -0.995 |
oit | -0.993 |
andre | -0.936 |
jamin | -0.930 |
Token | , |
Token ID | 11 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
warr | +0.104 |
Reply | +0.097 |
Interstitial | +0.093 |
mans | +0.090 |
lers | +0.087 |
Neg logit contributions | |
Russ | -0.119 |
Dems | -0.116 |
oit | -0.116 |
andre | -0.109 |
jamin | -0.108 |
Token | Koh |
Token ID | 24754 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
warr | +0.119 |
Reply | +0.112 |
Interstitial | +0.107 |
mans | +0.104 |
lers | +0.101 |
Neg logit contributions | |
Russ | -0.119 |
Dems | -0.116 |
oit | -0.116 |
andre | -0.108 |
jamin | -0.107 |
Token | l |
Token ID | 75 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
warr | +3.782 |
Reply | +3.554 |
mans | +3.436 |
lers | +3.350 |
Interstitial | +3.196 |
Neg logit contributions | |
Russ | -7.511 |
Dems | -7.479 |
oit | -7.255 |
andre | -7.015 |
jamin | -6.967 |
Token | , |
Token ID | 11 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
warr | +1.239 |
Reply | +1.168 |
Interstitial | +1.103 |
mans | +1.088 |
lers | +1.044 |
Neg logit contributions | |
Russ | -1.611 |
Dems | -1.577 |
oit | -1.570 |
andre | -1.482 |
jamin | -1.469 |
Token | Rose |
Token ID | 8049 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
warr | +0.252 |
Reply | +0.238 |
Interstitial | +0.228 |
mans | +0.220 |
lers | +0.214 |
Neg logit contributions | |
Russ | -0.260 |
Dems | -0.253 |
oit | -0.253 |
andre | -0.236 |
jamin | -0.235 |
Token | & |
Token ID | 1222 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
warr | +0.899 |
Reply | +0.846 |
Interstitial | +0.807 |
mans | +0.783 |
lers | +0.758 |
Neg logit contributions | |
Russ | -1.047 |
Dems | -1.023 |
oit | -1.020 |
andre | -0.958 |
jamin | -0.951 |
Token | Pod |
Token ID | 17437 |
Feature activation | +8.71e-02 |
Pos logit contributions | |
warr | +0.347 |
Reply | +0.328 |
Interstitial | +0.314 |
mans | +0.305 |
lers | +0.297 |
Neg logit contributions | |
Russ | -0.328 |
Dems | -0.320 |
oit | -0.319 |
andre | -0.298 |
jamin | -0.295 |
Token | Champions |
Token ID | 6662 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
warr | +4.484 |
Reply | +4.214 |
mans | +4.024 |
Interstitial | +3.993 |
lers | +3.868 |
Neg logit contributions | |
Russ | -4.650 |
oit | -4.498 |
Dems | -4.438 |
andre | -4.210 |
jamin | -4.167 |
Token | Cup |
Token ID | 5454 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
warr | +0.936 |
Reply | +0.881 |
Interstitial | +0.841 |
mans | +0.816 |
lers | +0.794 |
Neg logit contributions | |
Russ | -1.012 |
Dems | -0.987 |
oit | -0.986 |
andre | -0.923 |
jamin | -0.916 |
Token | pool |
Token ID | 5933 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
warr | +2.519 |
Reply | +2.372 |
Interstitial | +2.240 |
mans | +2.199 |
lers | +2.144 |
Neg logit contributions | |
Russ | -2.761 |
oit | -2.667 |
Dems | -2.657 |
andre | -2.487 |
jamin | -2.480 |
Token | match |
Token ID | 2872 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
Russ | +2.902 |
Dems | +2.851 |
oit | +2.846 |
andre | +2.644 |
jamin | +2.620 |
Neg logit contributions | |
warr | -3.205 |
Reply | -3.012 |
Interstitial | -2.953 |
mans | -2.793 |
lers | -2.721 |
Token | at |
Token ID | 379 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
warr | +1.181 |
Reply | +1.113 |
Interstitial | +1.052 |
mans | +1.025 |
lers | +0.998 |
Neg logit contributions | |
Russ | -1.391 |
Dems | -1.355 |
oit | -1.352 |
andre | -1.270 |
jamin | -1.261 |
Token | Wel |
Token ID | 22268 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
warr | +0.979 |
Reply | +0.923 |
Interstitial | +0.884 |
mans | +0.863 |
lers | +0.839 |
Neg logit contributions | |
Russ | -0.948 |
Dems | -0.921 |
oit | -0.919 |
andre | -0.859 |
jamin | -0.852 |
Token | ford |
Token ID | 3841 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
warr | +5.871 |
mans | +5.830 |
Reply | +5.488 |
lers | +5.466 |
Interstitial | +5.245 |
Neg logit contributions | |
Russ | -5.315 |
Dems | -4.924 |
oit | -4.854 |
ILLE | -4.802 |
jamin | -4.573 |
Token | Road |
Token ID | 5567 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
warr | +1.161 |
Reply | +1.095 |
Interstitial | +1.048 |
mans | +1.016 |
lers | +0.987 |
Neg logit contributions | |
Russ | -1.183 |
Dems | -1.152 |
oit | -1.150 |
andre | -1.076 |
jamin | -1.068 |
Token | . |
Token ID | 13 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
warr | +0.487 |
Reply | +0.458 |
Interstitial | +0.438 |
mans | +0.423 |
lers | +0.411 |
Neg logit contributions | |
Russ | -0.537 |
Dems | -0.524 |
oit | -0.523 |
andre | -0.490 |
jamin | -0.487 |
Token |
|
Token ID | 198 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
warr | +0.393 |
Reply | +0.379 |
Interstitial | +0.362 |
mans | +0.351 |
lers | +0.342 |
Neg logit contributions | |
Russ | -0.348 |
oit | -0.340 |
Dems | -0.339 |
andre | -0.316 |
jamin | -0.312 |
Token |
|
Token ID | 198 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
warr | +0.752 |
Reply | +0.720 |
Interstitial | +0.690 |
mans | +0.671 |
lers | +0.654 |
Neg logit contributions | |
Russ | -0.637 |
Dems | -0.620 |
oit | -0.618 |
andre | -0.574 |
jamin | -0.569 |
Token | warrant |
Token ID | 8084 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
warr | +0.483 |
Reply | +0.455 |
Interstitial | +0.432 |
mans | +0.421 |
lers | +0.410 |
Neg logit contributions | |
Russ | -0.470 |
Dems | -0.458 |
oit | -0.454 |
andre | -0.425 |
jamin | -0.421 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Russ | +0.399 |
oit | +0.391 |
Dems | +0.391 |
andre | +0.365 |
jamin | +0.363 |
Neg logit contributions | |
warr | -0.379 |
Reply | -0.357 |
Interstitial | -0.343 |
mans | -0.329 |
lers | -0.320 |
Token |
|
Token ID | 198 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Russ | +0.191 |
oit | +0.186 |
Dems | +0.186 |
andre | +0.173 |
jamin | +0.171 |
Neg logit contributions | |
warr | -0.214 |
Reply | -0.204 |
Interstitial | -0.195 |
mans | -0.190 |
lers | -0.186 |
Token |
|
Token ID | 198 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
Russ | +0.221 |
Dems | +0.215 |
oit | +0.214 |
andre | +0.198 |
jamin | +0.197 |
Neg logit contributions | |
warr | -0.279 |
Reply | -0.261 |
Interstitial | -0.252 |
mans | -0.244 |
lers | -0.238 |
Token | Wiki |
Token ID | 32603 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
Russ | +0.407 |
Dems | +0.394 |
oit | +0.394 |
andre | +0.371 |
jamin | +0.368 |
Neg logit contributions | |
warr | -0.362 |
Reply | -0.337 |
Interstitial | -0.323 |
mans | -0.311 |
lers | -0.302 |
Token | Leaks |
Token ID | 17874 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
Russ | +0.220 |
oit | +0.196 |
Dems | +0.191 |
andre | +0.146 |
jamin | +0.141 |
Neg logit contributions | |
warr | -1.426 |
Reply | -1.363 |
Interstitial | -1.344 |
mans | -1.308 |
lers | -1.285 |
Token | pr |
Token ID | 778 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
Dems | +6.029 |
Russ | +5.966 |
oit | +5.906 |
andre | +5.601 |
jamin | +5.517 |
Neg logit contributions | |
warr | -6.204 |
Interstitial | -5.923 |
Reply | -5.864 |
mans | -5.472 |
lers | -5.258 |
Token | ides |
Token ID | 1460 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
Russ | +0.854 |
oit | +0.831 |
Dems | +0.829 |
andre | +0.761 |
jamin | +0.752 |
Neg logit contributions | |
warr | -1.301 |
Reply | -1.239 |
Interstitial | -1.198 |
mans | -1.162 |
lers | -1.136 |
Token | itself |
Token ID | 2346 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
warr | +0.067 |
Reply | +0.064 |
Interstitial | +0.062 |
mans | +0.061 |
lers | +0.060 |
Neg logit contributions | |
Russ | -0.034 |
Dems | -0.033 |
oit | -0.033 |
andre | -0.030 |
jamin | -0.029 |
Token | as |
Token ID | 355 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
warr | +0.805 |
Reply | +0.753 |
Interstitial | +0.705 |
mans | +0.699 |
lers | +0.675 |
Neg logit contributions | |
Russ | -1.075 |
Dems | -1.055 |
oit | -1.045 |
andre | -0.987 |
jamin | -0.981 |
Token | a |
Token ID | 257 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
Russ | +1.323 |
Dems | +1.289 |
oit | +1.285 |
andre | +1.198 |
jamin | +1.188 |
Neg logit contributions | |
warr | -1.434 |
Reply | -1.357 |
Interstitial | -1.303 |
mans | -1.261 |
lers | -1.228 |
Token | Shell |
Token ID | 17537 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Russ | +0.306 |
oit | +0.298 |
Dems | +0.298 |
andre | +0.280 |
jamin | +0.278 |
Neg logit contributions | |
warr | -0.261 |
Reply | -0.245 |
Interstitial | -0.234 |
mans | -0.226 |
lers | -0.220 |
Token | to |
Token ID | 284 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
Russ | +3.958 |
Dems | +3.903 |
oit | +3.831 |
andre | +3.592 |
jamin | +3.560 |
Neg logit contributions | |
warr | -3.936 |
Reply | -3.702 |
Interstitial | -3.617 |
mans | -3.397 |
lers | -3.297 |
Token | drop |
Token ID | 4268 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Russ | +0.095 |
Dems | +0.093 |
oit | +0.092 |
andre | +0.085 |
jamin | +0.084 |
Neg logit contributions | |
warr | -0.101 |
Reply | -0.096 |
Interstitial | -0.092 |
mans | -0.089 |
lers | -0.086 |
Token | its |
Token ID | 663 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
Russ | +0.505 |
Dems | +0.489 |
oit | +0.489 |
andre | +0.453 |
jamin | +0.448 |
Neg logit contributions | |
warr | -0.647 |
Reply | -0.615 |
Interstitial | -0.590 |
mans | -0.575 |
lers | -0.562 |
Token | Arctic |
Token ID | 15723 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
warr | +0.087 |
Reply | +0.083 |
Interstitial | +0.079 |
mans | +0.077 |
lers | +0.075 |
Neg logit contributions | |
Russ | -0.072 |
Dems | -0.070 |
oit | -0.070 |
andre | -0.065 |
jamin | -0.064 |
Token | drilling |
Token ID | 19747 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
Russ | +1.881 |
Dems | +1.823 |
oit | +1.817 |
andre | +1.638 |
jamin | +1.627 |
Neg logit contributions | |
warr | -3.374 |
Reply | -3.231 |
Interstitial | -3.150 |
mans | -3.042 |
lers | -2.996 |
Token | plans |
Token ID | 3352 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Russ | +5.829 |
Dems | +5.717 |
oit | +5.662 |
jamin | +5.191 |
andre | +5.177 |
Neg logit contributions | |
warr | -5.889 |
Reply | -5.653 |
Interstitial | -5.586 |
mans | -5.171 |
lers | -5.111 |
Token | . |
Token ID | 13 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Russ | +0.226 |
Dems | +0.221 |
oit | +0.220 |
andre | +0.206 |
jamin | +0.204 |
Neg logit contributions | |
warr | -0.218 |
Reply | -0.206 |
Interstitial | -0.197 |
mans | -0.191 |
lers | -0.185 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Russ | +0.336 |
Dems | +0.327 |
oit | +0.326 |
andre | +0.304 |
jamin | +0.302 |
Neg logit contributions | |
warr | -0.361 |
Reply | -0.341 |
Interstitial | -0.327 |
mans | -0.317 |
lers | -0.309 |
Token | Good |
Token ID | 10248 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
warr | +0.269 |
Reply | +0.254 |
Interstitial | +0.242 |
mans | +0.234 |
lers | +0.227 |
Neg logit contributions | |
Russ | -0.305 |
Dems | -0.298 |
oit | -0.298 |
andre | -0.279 |
jamin | -0.277 |
Token | bye |
Token ID | 16390 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
warr | +0.474 |
Reply | +0.449 |
Interstitial | +0.431 |
mans | +0.421 |
lers | +0.408 |
Neg logit contributions | |
Russ | -0.410 |
oit | -0.397 |
Dems | -0.397 |
andre | -0.369 |
jamin | -0.366 |
Token | FOX |
Token ID | 19912 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
Russ | +0.823 |
Dems | +0.807 |
oit | +0.799 |
andre | +0.743 |
jamin | +0.736 |
Neg logit contributions | |
warr | -0.939 |
Reply | -0.889 |
Interstitial | -0.856 |
mans | -0.830 |
lers | -0.806 |
Token | propaganda |
Token ID | 11613 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
Russ | +0.633 |
Dems | +0.619 |
oit | +0.614 |
andre | +0.571 |
jamin | +0.566 |
Neg logit contributions | |
warr | -0.710 |
Reply | -0.673 |
Interstitial | -0.649 |
mans | -0.626 |
lers | -0.611 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
Russ | +1.011 |
Dems | +0.991 |
oit | +0.977 |
andre | +0.916 |
jamin | +0.909 |
Neg logit contributions | |
warr | -0.973 |
Reply | -0.917 |
Interstitial | -0.882 |
mans | -0.844 |
lers | -0.819 |
Token | These |
Token ID | 2312 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Russ | +0.379 |
Dems | +0.370 |
oit | +0.367 |
andre | +0.341 |
jamin | +0.338 |
Neg logit contributions | |
warr | -0.442 |
Reply | -0.418 |
Interstitial | -0.402 |
mans | -0.390 |
lers | -0.380 |
Token | outlets |
Token ID | 12527 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
warr | +0.430 |
Reply | +0.407 |
Interstitial | +0.390 |
mans | +0.377 |
lers | +0.367 |
Neg logit contributions | |
Russ | -0.423 |
Dems | -0.413 |
oit | -0.411 |
andre | -0.384 |
jamin | -0.381 |
Token | spew |
Token ID | 38645 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
Russ | +1.148 |
Dems | +1.128 |
oit | +1.120 |
andre | +1.058 |
jamin | +1.046 |
Neg logit contributions | |
warr | -0.826 |
Reply | -0.772 |
Interstitial | -0.737 |
mans | -0.699 |
lers | -0.675 |
Token | non |
Token ID | 1729 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Russ | +5.262 |
Dems | +5.163 |
oit | +5.083 |
andre | +4.729 |
jamin | +4.619 |
Neg logit contributions | |
warr | -6.534 |
Reply | -6.192 |
Interstitial | -6.082 |
mans | -5.745 |
lers | -5.489 |
Token | - |
Token ID | 12 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Russ | +1.924 |
Dems | +1.869 |
oit | +1.862 |
andre | +1.720 |
jamin | +1.704 |
Neg logit contributions | |
warr | -2.582 |
Reply | -2.457 |
Interstitial | -2.368 |
mans | -2.300 |
lers | -2.247 |
Token | stop |
Token ID | 11338 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Russ | +0.324 |
Dems | +0.316 |
oit | +0.316 |
andre | +0.293 |
jamin | +0.292 |
Neg logit contributions | |
warr | -0.351 |
Reply | -0.334 |
Interstitial | -0.319 |
mans | -0.311 |
lers | -0.303 |
Token | disinformation |
Token ID | 45054 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
warr | +0.785 |
Reply | +0.743 |
Interstitial | +0.712 |
mans | +0.696 |
lers | +0.682 |
Neg logit contributions | |
Russ | -0.663 |
oit | -0.645 |
Dems | -0.639 |
andre | -0.599 |
jamin | -0.594 |
Token | and |
Token ID | 290 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
Russ | +3.026 |
Dems | +2.985 |
oit | +2.927 |
andre | +2.740 |
jamin | +2.710 |
Neg logit contributions | |
warr | -2.939 |
Reply | -2.771 |
Interstitial | -2.707 |
mans | -2.555 |
lers | -2.467 |
Token | A |
Token ID | 32 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
warr | +0.456 |
Reply | +0.430 |
Interstitial | +0.409 |
mans | +0.395 |
lers | +0.383 |
Neg logit contributions | |
Russ | -0.547 |
Dems | -0.536 |
oit | -0.534 |
andre | -0.502 |
jamin | -0.498 |
Token | truck |
Token ID | 7779 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
warr | +0.022 |
Reply | +0.021 |
Interstitial | +0.020 |
mans | +0.019 |
lers | +0.019 |
Neg logit contributions | |
Russ | -0.021 |
Dems | -0.020 |
oit | -0.020 |
andre | -0.019 |
jamin | -0.019 |
Token | drives |
Token ID | 10182 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Russ | +0.880 |
Dems | +0.858 |
oit | +0.856 |
andre | +0.801 |
jamin | +0.795 |
Neg logit contributions | |
warr | -0.855 |
Reply | -0.807 |
Interstitial | -0.772 |
mans | -0.747 |
lers | -0.726 |
Token | toward |
Token ID | 3812 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Russ | +1.602 |
Dems | +1.575 |
oit | +1.566 |
andre | +1.455 |
jamin | +1.436 |
Neg logit contributions | |
warr | -1.809 |
Reply | -1.715 |
Interstitial | -1.657 |
mans | -1.590 |
lers | -1.546 |
Token | a |
Token ID | 257 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
Russ | +0.673 |
Dems | +0.655 |
oit | +0.653 |
andre | +0.607 |
jamin | +0.602 |
Neg logit contributions | |
warr | -0.773 |
Reply | -0.733 |
Interstitial | -0.704 |
mans | -0.683 |
lers | -0.666 |
Token | dumping |
Token ID | 30231 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
warr | +0.058 |
Reply | +0.055 |
Interstitial | +0.052 |
mans | +0.051 |
lers | +0.050 |
Neg logit contributions | |
Russ | -0.050 |
Dems | -0.048 |
oit | -0.048 |
andre | -0.045 |
jamin | -0.045 |
Token | area |
Token ID | 1989 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
Russ | +4.476 |
Dems | +4.373 |
oit | +4.330 |
jamin | +3.889 |
andre | +3.886 |
Neg logit contributions | |
warr | -7.150 |
Reply | -6.860 |
Interstitial | -6.684 |
mans | -6.327 |
lers | -6.199 |
Token | at |
Token ID | 379 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
warr | +0.674 |
Reply | +0.636 |
Interstitial | +0.607 |
mans | +0.588 |
lers | +0.572 |
Neg logit contributions | |
Russ | -0.731 |
Dems | -0.712 |
oit | -0.710 |
andre | -0.667 |
jamin | -0.662 |
Token | the |
Token ID | 262 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
warr | +0.626 |
Reply | +0.591 |
Interstitial | +0.566 |
mans | +0.552 |
lers | +0.538 |
Neg logit contributions | |
Russ | -0.574 |
Dems | -0.556 |
oit | -0.555 |
andre | -0.519 |
jamin | -0.514 |
Token | Arrow |
Token ID | 19408 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
Russ | +0.050 |
Dems | +0.049 |
oit | +0.049 |
andre | +0.045 |
jamin | +0.045 |
Neg logit contributions | |
warr | -0.059 |
Reply | -0.056 |
Interstitial | -0.054 |
mans | -0.053 |
lers | -0.051 |
Token | head |
Token ID | 2256 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
warr | +0.895 |
Reply | +0.852 |
Interstitial | +0.816 |
mans | +0.806 |
lers | +0.784 |
Neg logit contributions | |
Russ | -0.746 |
Dems | -0.723 |
oit | -0.715 |
andre | -0.667 |
jamin | -0.663 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Russ | +1.587 |
oit | +1.560 |
Dems | +1.558 |
andre | +1.457 |
jamin | +1.443 |
Neg logit contributions | |
warr | -1.480 |
Reply | -1.408 |
Interstitial | -1.349 |
mans | -1.296 |
lers | -1.251 |
Token | sexy |
Token ID | 17144 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Russ | +0.154 |
Dems | +0.150 |
oit | +0.149 |
andre | +0.139 |
jamin | +0.137 |
Neg logit contributions | |
warr | -0.175 |
Reply | -0.165 |
Interstitial | -0.159 |
mans | -0.154 |
lers | -0.150 |
Token | breast |
Token ID | 9296 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
Russ | +2.045 |
Dems | +2.007 |
oit | +1.994 |
andre | +1.866 |
jamin | +1.836 |
Neg logit contributions | |
warr | -2.144 |
Reply | -2.027 |
Interstitial | -1.975 |
mans | -1.882 |
lers | -1.830 |
Token | - |
Token ID | 12 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
Russ | +0.827 |
Dems | +0.805 |
oit | +0.803 |
andre | +0.749 |
jamin | +0.743 |
Neg logit contributions | |
warr | -0.894 |
Reply | -0.846 |
Interstitial | -0.811 |
mans | -0.787 |
lers | -0.767 |
Token | blood |
Token ID | 18041 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
Russ | +0.096 |
Dems | +0.094 |
oit | +0.094 |
andre | +0.087 |
jamin | +0.087 |
Neg logit contributions | |
warr | -0.095 |
Reply | -0.090 |
Interstitial | -0.086 |
mans | -0.083 |
lers | -0.081 |
Token | spew |
Token ID | 38645 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
Russ | +0.039 |
Dems | +0.038 |
oit | +0.038 |
andre | +0.035 |
jamin | +0.035 |
Neg logit contributions | |
warr | -0.043 |
Reply | -0.041 |
Interstitial | -0.039 |
mans | -0.038 |
lers | -0.037 |
Token | ing |
Token ID | 278 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Russ | +4.446 |
Dems | +4.386 |
oit | +4.350 |
andre | +4.008 |
jamin | +3.905 |
Neg logit contributions | |
warr | -7.006 |
Reply | -6.724 |
Interstitial | -6.514 |
mans | -6.228 |
lers | -5.981 |
Token | Vul |
Token ID | 25442 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Russ | +3.279 |
Dems | +3.250 |
oit | +3.213 |
andre | +2.999 |
jamin | +2.967 |
Neg logit contributions | |
warr | -3.003 |
Reply | -2.870 |
Interstitial | -2.754 |
mans | -2.632 |
lers | -2.533 |
Token | v |
Token ID | 85 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
warr | +1.455 |
Reply | +1.370 |
Interstitial | +1.312 |
mans | +1.274 |
lers | +1.234 |
Neg logit contributions | |
Russ | -1.627 |
Dems | -1.586 |
oit | -1.577 |
andre | -1.483 |
jamin | -1.474 |
Token | atron |
Token ID | 23484 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
warr | +1.066 |
Reply | +1.006 |
Interstitial | +0.959 |
mans | +0.933 |
lers | +0.906 |
Neg logit contributions | |
Russ | -1.176 |
Dems | -1.148 |
oit | -1.142 |
andre | -1.070 |
jamin | -1.065 |
Token | . |
Token ID | 13 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
Russ | +1.525 |
Dems | +1.498 |
oit | +1.498 |
andre | +1.407 |
jamin | +1.390 |
Neg logit contributions | |
warr | -1.398 |
Reply | -1.319 |
Interstitial | -1.251 |
mans | -1.208 |
lers | -1.173 |
Token | of |
Token ID | 286 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
warr | +0.087 |
Reply | +0.083 |
Interstitial | +0.079 |
mans | +0.077 |
lers | +0.075 |
Neg logit contributions | |
Russ | -0.086 |
Dems | -0.083 |
oit | -0.083 |
andre | -0.078 |
jamin | -0.077 |
Token | each |
Token ID | 1123 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
warr | +0.102 |
Reply | +0.096 |
Interstitial | +0.092 |
mans | +0.089 |
lers | +0.087 |
Neg logit contributions | |
Russ | -0.100 |
Dems | -0.097 |
oit | -0.097 |
andre | -0.091 |
jamin | -0.090 |
Token | cell |
Token ID | 2685 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Russ | +0.293 |
Dems | +0.286 |
oit | +0.285 |
andre | +0.267 |
jamin | +0.264 |
Neg logit contributions | |
warr | -0.297 |
Reply | -0.280 |
Interstitial | -0.269 |
mans | -0.260 |
lers | -0.253 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
warr | +1.617 |
Reply | +1.517 |
Interstitial | +1.449 |
mans | +1.408 |
lers | +1.369 |
Neg logit contributions | |
Russ | -1.935 |
oit | -1.888 |
Dems | -1.886 |
andre | -1.779 |
jamin | -1.765 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Russ | +0.288 |
oit | +0.280 |
Dems | +0.279 |
andre | +0.260 |
jamin | +0.258 |
Neg logit contributions | |
warr | -0.322 |
Reply | -0.307 |
Interstitial | -0.295 |
mans | -0.286 |
lers | -0.279 |
Token | EPA |
Token ID | 40906 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
warr | +0.156 |
Reply | +0.146 |
Interstitial | +0.139 |
mans | +0.135 |
lers | +0.131 |
Neg logit contributions | |
Russ | -0.177 |
Dems | -0.172 |
oit | -0.172 |
andre | -0.161 |
jamin | -0.160 |
Token |
|
Token ID | 198 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Dems | +5.594 |
Russ | +5.585 |
oit | +5.394 |
andre | +5.041 |
jamin | +4.940 |
Neg logit contributions | |
warr | -5.609 |
Reply | -5.345 |
Interstitial | -5.248 |
mans | -4.944 |
lers | -4.813 |
Token |
|
Token ID | 198 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
Russ | +0.522 |
Dems | +0.505 |
oit | +0.504 |
andre | +0.465 |
jamin | +0.464 |
Neg logit contributions | |
warr | -0.686 |
Reply | -0.633 |
Interstitial | -0.613 |
mans | -0.592 |
lers | -0.579 |
Token | It |
Token ID | 1026 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
Russ | +0.611 |
Dems | +0.593 |
oit | +0.591 |
andre | +0.555 |
jamin | +0.551 |
Neg logit contributions | |
warr | -0.565 |
Reply | -0.525 |
Interstitial | -0.503 |
mans | -0.486 |
lers | -0.473 |
Token | 's |
Token ID | 338 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Russ | +0.554 |
Dems | +0.544 |
oit | +0.541 |
andre | +0.508 |
jamin | +0.504 |
Neg logit contributions | |
warr | -0.532 |
Reply | -0.503 |
Interstitial | -0.483 |
mans | -0.463 |
lers | -0.450 |
Token | the |
Token ID | 262 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
Russ | +0.267 |
Dems | +0.261 |
oit | +0.259 |
andre | +0.241 |
jamin | +0.240 |
Neg logit contributions | |
warr | -0.279 |
Reply | -0.265 |
Interstitial | -0.254 |
mans | -0.245 |
lers | -0.238 |
Token | response |
Token ID | 2882 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
Russ | +3.858 |
Dems | +3.804 |
oit | +3.797 |
andre | +3.499 |
jamin | +3.475 |
Neg logit contributions | |
warr | -4.721 |
Reply | -4.437 |
Interstitial | -4.412 |
mans | -4.156 |
lers | -4.028 |
Token | plan |
Token ID | 1410 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
warr | +0.895 |
Reply | +0.838 |
Interstitial | +0.786 |
mans | +0.769 |
lers | +0.745 |
Neg logit contributions | |
Russ | -1.165 |
oit | -1.134 |
Dems | -1.133 |
andre | -1.069 |
jamin | -1.062 |
Token | for |
Token ID | 329 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
warr | +0.368 |
Reply | +0.346 |
Interstitial | +0.329 |
mans | +0.318 |
lers | +0.309 |
Neg logit contributions | |
Russ | -0.424 |
Dems | -0.415 |
oit | -0.414 |
andre | -0.388 |
jamin | -0.386 |
Token | their |
Token ID | 511 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
warr | +0.087 |
Reply | +0.082 |
Interstitial | +0.079 |
mans | +0.077 |
lers | +0.075 |
Neg logit contributions | |
Russ | -0.075 |
Dems | -0.073 |
oit | -0.073 |
andre | -0.068 |
jamin | -0.067 |
Token | Arctic |
Token ID | 15723 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Russ | +0.629 |
Dems | +0.612 |
oit | +0.611 |
andre | +0.566 |
jamin | +0.561 |
Neg logit contributions | |
warr | -0.756 |
Reply | -0.718 |
Interstitial | -0.691 |
mans | -0.669 |
lers | -0.653 |
Token | drilling |
Token ID | 19747 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
Russ | +1.856 |
Dems | +1.803 |
oit | +1.801 |
andre | +1.653 |
jamin | +1.637 |
Neg logit contributions | |
warr | -2.610 |
Reply | -2.491 |
Interstitial | -2.404 |
mans | -2.329 |
lers | -2.281 |
Token | operations |
Token ID | 4560 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
Russ | +5.224 |
oit | +5.175 |
Dems | +5.138 |
andre | +4.690 |
jamin | +4.680 |
Neg logit contributions | |
warr | -5.733 |
Reply | -5.533 |
Interstitial | -5.379 |
mans | -4.974 |
lers | -4.917 |
Token | has |
Token ID | 468 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
warr | +0.012 |
Reply | +0.012 |
Interstitial | +0.011 |
mans | +0.011 |
lers | +0.010 |
Neg logit contributions | |
Russ | -0.014 |
Dems | -0.014 |
oit | -0.014 |
andre | -0.013 |
jamin | -0.013 |
Token | just |
Token ID | 655 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
Russ | +0.308 |
Dems | +0.302 |
oit | +0.300 |
andre | +0.281 |
jamin | +0.279 |
Neg logit contributions | |
warr | -0.274 |
Reply | -0.258 |
Interstitial | -0.247 |
mans | -0.237 |
lers | -0.230 |
Token | bree |
Token ID | 20780 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
warr | +0.925 |
Reply | +0.869 |
Interstitial | +0.829 |
mans | +0.799 |
lers | +0.776 |
Neg logit contributions | |
Russ | -1.081 |
Dems | -1.056 |
oit | -1.054 |
andre | -0.990 |
jamin | -0.983 |
Token | zed |
Token ID | 8863 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Russ | +0.262 |
Dems | +0.256 |
oit | +0.255 |
andre | +0.238 |
jamin | +0.237 |
Neg logit contributions | |
warr | -0.256 |
Reply | -0.242 |
Interstitial | -0.231 |
mans | -0.224 |
lers | -0.218 |
Token | make |
Token ID | 787 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
warr | +0.199 |
Reply | +0.187 |
Interstitial | +0.180 |
mans | +0.173 |
lers | +0.168 |
Neg logit contributions | |
Russ | -0.209 |
Dems | -0.204 |
oit | -0.203 |
andre | -0.190 |
jamin | -0.188 |
Token | that |
Token ID | 326 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Russ | +1.068 |
Dems | +1.046 |
oit | +1.033 |
andre | +0.960 |
jamin | +0.951 |
Neg logit contributions | |
warr | -1.280 |
Reply | -1.210 |
Interstitial | -1.178 |
mans | -1.130 |
lers | -1.104 |
Token | happen |
Token ID | 1645 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
warr | +0.447 |
Reply | +0.421 |
Interstitial | +0.403 |
mans | +0.389 |
lers | +0.379 |
Neg logit contributions | |
Russ | -0.470 |
Dems | -0.459 |
oit | -0.458 |
andre | -0.429 |
jamin | -0.425 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Russ | +0.455 |
Dems | +0.444 |
oit | +0.443 |
andre | +0.416 |
jamin | +0.412 |
Neg logit contributions | |
warr | -0.410 |
Reply | -0.386 |
Interstitial | -0.369 |
mans | -0.356 |
lers | -0.346 |
Token | The |
Token ID | 383 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Russ | +0.334 |
Dems | +0.325 |
oit | +0.324 |
andre | +0.300 |
jamin | +0.298 |
Neg logit contributions | |
warr | -0.399 |
Reply | -0.378 |
Interstitial | -0.364 |
mans | -0.353 |
lers | -0.344 |
Token | prov |
Token ID | 899 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
warr | +0.493 |
Reply | +0.470 |
Interstitial | +0.446 |
mans | +0.437 |
lers | +0.425 |
Neg logit contributions | |
Russ | -0.435 |
oit | -0.422 |
Dems | -0.420 |
andre | -0.393 |
jamin | -0.390 |
Token | ocations |
Token ID | 20968 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
Russ | +4.228 |
oit | +4.194 |
Dems | +4.095 |
andre | +3.797 |
jamin | +3.732 |
Neg logit contributions | |
warr | -6.997 |
Reply | -6.557 |
Interstitial | -6.404 |
mans | -6.140 |
lers | -5.950 |
Token | by |
Token ID | 416 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Russ | +1.141 |
Dems | +1.125 |
oit | +1.107 |
andre | +1.035 |
jamin | +1.024 |
Neg logit contributions | |
warr | -1.122 |
Reply | -1.058 |
Interstitial | -1.025 |
mans | -0.975 |
lers | -0.944 |
Token | Russia |
Token ID | 3284 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Russ | +1.297 |
Dems | +1.268 |
oit | +1.254 |
andre | +1.163 |
jamin | +1.153 |
Neg logit contributions | |
warr | -1.636 |
Reply | -1.551 |
Interstitial | -1.499 |
mans | -1.449 |
lers | -1.412 |
Token | need |
Token ID | 761 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
Russ | +2.326 |
Dems | +2.283 |
oit | +2.260 |
andre | +2.126 |
jamin | +2.090 |
Neg logit contributions | |
warr | -2.210 |
Reply | -2.062 |
Interstitial | -1.987 |
mans | -1.905 |
lers | -1.841 |
Token | to |
Token ID | 284 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
warr | +0.114 |
Reply | +0.107 |
Interstitial | +0.102 |
mans | +0.099 |
lers | +0.096 |
Neg logit contributions | |
Russ | -0.135 |
Dems | -0.132 |
oit | -0.131 |
andre | -0.123 |
jamin | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
warr | +0.700 |
Reply | +0.660 |
Interstitial | +0.628 |
mans | +0.607 |
lers | +0.592 |
Neg logit contributions | |
Russ | -0.770 |
Dems | -0.752 |
oit | -0.748 |
andre | -0.703 |
jamin | -0.698 |
Token | � |
Token ID | 447 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
Russ | +0.430 |
Dems | +0.419 |
oit | +0.417 |
andre | +0.388 |
jamin | +0.385 |
Neg logit contributions | |
warr | -0.494 |
Reply | -0.469 |
Interstitial | -0.450 |
mans | -0.437 |
lers | -0.426 |
Token | � |
Token ID | 251 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Russ | +0.539 |
Dems | +0.525 |
oit | +0.524 |
andre | +0.489 |
jamin | +0.484 |
Neg logit contributions | |
warr | -0.566 |
Reply | -0.536 |
Interstitial | -0.513 |
mans | -0.495 |
lers | -0.484 |
Token |
|
Token ID | 198 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
Russ | +0.567 |
Dems | +0.552 |
oit | +0.550 |
andre | +0.511 |
jamin | +0.507 |
Neg logit contributions | |
warr | -0.648 |
Reply | -0.611 |
Interstitial | -0.588 |
mans | -0.570 |
lers | -0.555 |
Token |
|
Token ID | 198 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
Russ | +0.830 |
Dems | +0.805 |
oit | +0.804 |
andre | +0.741 |
jamin | +0.739 |
Neg logit contributions | |
warr | -1.094 |
Reply | -1.008 |
Interstitial | -0.977 |
mans | -0.943 |
lers | -0.922 |
Token | Ge |
Token ID | 10082 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Russ | +0.936 |
oit | +0.905 |
Dems | +0.904 |
andre | +0.850 |
jamin | +0.840 |
Neg logit contributions | |
warr | -0.922 |
Reply | -0.855 |
Interstitial | -0.821 |
mans | -0.795 |
lers | -0.773 |
Token | isel |
Token ID | 36811 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Russ | +4.605 |
oit | +4.546 |
Dems | +4.304 |
jamin | +4.215 |
andre | +4.212 |
Neg logit contributions | |
warr | -6.761 |
Reply | -6.129 |
Interstitial | -5.939 |
mans | -5.576 |
lers | -5.413 |
Token | died |
Token ID | 3724 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Russ | +3.185 |
Dems | +3.143 |
oit | +3.125 |
andre | +2.939 |
jamin | +2.926 |
Neg logit contributions | |
warr | -3.194 |
Reply | -3.003 |
Interstitial | -2.949 |
mans | -2.748 |
lers | -2.657 |
Token | on |
Token ID | 319 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Russ | +0.145 |
Dems | +0.142 |
oit | +0.142 |
andre | +0.133 |
jamin | +0.132 |
Neg logit contributions | |
warr | -0.138 |
Reply | -0.130 |
Interstitial | -0.124 |
mans | -0.119 |
lers | -0.116 |
Token | September |
Token ID | 2693 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
warr | +1.821 |
Reply | +1.723 |
Interstitial | +1.655 |
mans | +1.604 |
lers | +1.563 |
Neg logit contributions | |
Russ | -1.643 |
Dems | -1.601 |
oit | -1.597 |
andre | -1.486 |
jamin | -1.474 |
Token | 24 |
Token ID | 1987 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
warr | +0.449 |
Reply | +0.417 |
Interstitial | +0.405 |
mans | +0.387 |
lers | +0.378 |
Neg logit contributions | |
Russ | -0.412 |
Dems | -0.403 |
oit | -0.401 |
andre | -0.372 |
jamin | -0.372 |
Token | into |
Token ID | 656 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Russ | +1.068 |
Dems | +1.045 |
oit | +1.041 |
andre | +0.972 |
jamin | +0.963 |
Neg logit contributions | |
warr | -1.149 |
Reply | -1.081 |
Interstitial | -1.041 |
mans | -1.006 |
lers | -0.977 |
Token | MP |
Token ID | 4904 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
warr | +1.438 |
Reply | +1.367 |
Interstitial | +1.301 |
mans | +1.264 |
lers | +1.232 |
Neg logit contributions | |
Russ | -1.414 |
oit | -1.377 |
Dems | -1.370 |
andre | -1.286 |
jamin | -1.271 |
Token | 3 |
Token ID | 18 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
warr | +0.152 |
Reply | +0.143 |
Interstitial | +0.135 |
mans | +0.130 |
lers | +0.125 |
Neg logit contributions | |
Russ | -0.219 |
oit | -0.214 |
Dems | -0.214 |
andre | -0.203 |
jamin | -0.201 |
Token | s |
Token ID | 82 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
Russ | +0.046 |
Dems | +0.045 |
oit | +0.045 |
andre | +0.042 |
jamin | +0.042 |
Neg logit contributions | |
warr | -0.038 |
Reply | -0.036 |
Interstitial | -0.034 |
mans | -0.033 |
lers | -0.032 |
Token | — |
Token ID | 960 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
warr | +0.659 |
Reply | +0.622 |
Interstitial | +0.593 |
mans | +0.575 |
lers | +0.559 |
Neg logit contributions | |
Russ | -0.724 |
Dems | -0.705 |
oit | -0.704 |
andre | -0.659 |
jamin | -0.655 |
Token | pse |
Token ID | 7752 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
Russ | +0.980 |
Dems | +0.951 |
oit | +0.949 |
andre | +0.894 |
jamin | +0.885 |
Neg logit contributions | |
warr | -0.891 |
Reply | -0.832 |
Interstitial | -0.796 |
mans | -0.766 |
lers | -0.745 |
Token | udo |
Token ID | 12003 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Russ | +3.587 |
oit | +3.469 |
Dems | +3.409 |
andre | +3.106 |
jamin | +3.058 |
Neg logit contributions | |
warr | -7.492 |
Reply | -7.127 |
Interstitial | -6.933 |
mans | -6.710 |
lers | -6.606 |
Token | - |
Token ID | 12 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Russ | +2.597 |
Dems | +2.514 |
oit | +2.502 |
andre | +2.319 |
jamin | +2.311 |
Neg logit contributions | |
warr | -3.461 |
Reply | -3.280 |
Interstitial | -3.176 |
mans | -3.066 |
lers | -2.998 |
Token | piracy |
Token ID | 8703 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
Russ | +0.214 |
Dems | +0.210 |
oit | +0.209 |
andre | +0.195 |
jamin | +0.193 |
Neg logit contributions | |
warr | -0.220 |
Reply | -0.209 |
Interstitial | -0.200 |
mans | -0.194 |
lers | -0.189 |
Token | committed |
Token ID | 5364 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
warr | +0.703 |
Reply | +0.663 |
Interstitial | +0.632 |
mans | +0.613 |
lers | +0.595 |
Neg logit contributions | |
Russ | -0.773 |
oit | -0.753 |
Dems | -0.752 |
andre | -0.706 |
jamin | -0.700 |
Token | in |
Token ID | 287 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
warr | +1.137 |
Reply | +1.066 |
Interstitial | +1.017 |
mans | +0.986 |
lers | +0.961 |
Neg logit contributions | |
Russ | -1.400 |
Dems | -1.366 |
oit | -1.365 |
andre | -1.284 |
jamin | -1.278 |
Token | . |
Token ID | 13 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
warr | +0.611 |
Reply | +0.576 |
Interstitial | +0.550 |
mans | +0.533 |
lers | +0.518 |
Neg logit contributions | |
Russ | -0.659 |
Dems | -0.643 |
oit | -0.642 |
andre | -0.602 |
jamin | -0.596 |
Token | 80 |
Token ID | 1795 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
warr | +0.723 |
Reply | +0.682 |
Interstitial | +0.649 |
mans | +0.626 |
lers | +0.607 |
Neg logit contributions | |
Russ | -0.877 |
Dems | -0.857 |
oit | -0.856 |
andre | -0.806 |
jamin | -0.799 |
Token | more |
Token ID | 517 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
Russ | +1.373 |
Dems | +1.343 |
oit | +1.333 |
andre | +1.241 |
jamin | +1.240 |
Neg logit contributions | |
warr | -1.358 |
Reply | -1.280 |
Interstitial | -1.225 |
mans | -1.175 |
lers | -1.146 |
Token | than |
Token ID | 621 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Russ | +1.341 |
Dems | +1.315 |
oit | +1.310 |
andre | +1.226 |
jamin | +1.221 |
Neg logit contributions | |
warr | -1.084 |
Reply | -1.017 |
Interstitial | -0.974 |
mans | -0.926 |
lers | -0.896 |
Token | the |
Token ID | 262 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
warr | +0.333 |
Reply | +0.315 |
Interstitial | +0.303 |
mans | +0.293 |
lers | +0.285 |
Neg logit contributions | |
Russ | -0.304 |
Dems | -0.296 |
oit | -0.295 |
andre | -0.275 |
jamin | -0.273 |
Token | pump |
Token ID | 8901 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
Russ | +0.290 |
Dems | +0.284 |
oit | +0.282 |
andre | +0.263 |
jamin | +0.261 |
Neg logit contributions | |
warr | -0.297 |
Reply | -0.281 |
Interstitial | -0.269 |
mans | -0.260 |
lers | -0.253 |
Token | price |
Token ID | 2756 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
Russ | +5.433 |
Dems | +5.328 |
oit | +5.277 |
andre | +4.959 |
jamin | +4.898 |
Neg logit contributions | |
warr | -5.420 |
Reply | -5.155 |
Interstitial | -4.953 |
mans | -4.627 |
lers | -4.506 |
Token | , |
Token ID | 11 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Russ | +1.258 |
Dems | +1.229 |
oit | +1.225 |
andre | +1.142 |
jamin | +1.136 |
Neg logit contributions | |
warr | -1.250 |
Reply | -1.182 |
Interstitial | -1.131 |
mans | -1.091 |
lers | -1.061 |
Token | a |
Token ID | 257 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
Russ | +0.380 |
Dems | +0.372 |
oit | +0.370 |
andre | +0.346 |
jamin | +0.344 |
Neg logit contributions | |
warr | -0.358 |
Reply | -0.338 |
Interstitial | -0.323 |
mans | -0.312 |
lers | -0.303 |
Token | new |
Token ID | 649 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
warr | +0.028 |
Reply | +0.026 |
Interstitial | +0.025 |
mans | +0.024 |
lers | +0.024 |
Neg logit contributions | |
Russ | -0.026 |
Dems | -0.025 |
oit | -0.025 |
andre | -0.023 |
jamin | -0.023 |
Token | Duke |
Token ID | 11083 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
warr | +1.629 |
Reply | +1.531 |
Interstitial | +1.459 |
mans | +1.431 |
lers | +1.387 |
Neg logit contributions | |
Russ | -1.633 |
Dems | -1.582 |
oit | -1.579 |
andre | -1.485 |
jamin | -1.473 |
Token | over |
Token ID | 625 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Russ | +0.564 |
Dems | +0.548 |
oit | +0.547 |
andre | +0.507 |
jamin | +0.503 |
Neg logit contributions | |
warr | -0.678 |
Reply | -0.643 |
Interstitial | -0.618 |
mans | -0.600 |
lers | -0.586 |
Token | : |
Token ID | 25 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
warr | +2.648 |
Reply | +2.464 |
Interstitial | +2.367 |
mans | +2.294 |
lers | +2.245 |
Neg logit contributions | |
Russ | -3.162 |
Dems | -3.098 |
oit | -3.073 |
andre | -2.910 |
jamin | -2.871 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
Russ | +0.450 |
Dems | +0.438 |
oit | +0.437 |
andre | +0.408 |
jamin | +0.404 |
Neg logit contributions | |
warr | -0.483 |
Reply | -0.457 |
Interstitial | -0.438 |
mans | -0.424 |
lers | -0.413 |
Token | mysterious |
Token ID | 11428 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
Russ | +0.016 |
Dems | +0.015 |
oit | +0.015 |
andre | +0.014 |
jamin | +0.014 |
Neg logit contributions | |
warr | -0.017 |
Reply | -0.016 |
Interstitial | -0.016 |
mans | -0.015 |
lers | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Russ | +1.210 |
Dems | +1.179 |
oit | +1.177 |
andre | +1.095 |
jamin | +1.087 |
Neg logit contributions | |
warr | -1.296 |
Reply | -1.228 |
Interstitial | -1.178 |
mans | -1.140 |
lers | -1.108 |
Token | pse |
Token ID | 7752 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
warr | +0.180 |
Reply | +0.171 |
Interstitial | +0.164 |
mans | +0.159 |
lers | +0.154 |
Neg logit contributions | |
Russ | -0.178 |
Dems | -0.175 |
oit | -0.174 |
andre | -0.162 |
jamin | -0.161 |
Token | ud |
Token ID | 463 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Russ | +3.280 |
oit | +3.182 |
Dems | +3.086 |
andre | +2.811 |
jamin | +2.776 |
Neg logit contributions | |
warr | -7.591 |
Reply | -7.205 |
Interstitial | -7.056 |
mans | -6.809 |
lers | -6.718 |
Token | og |
Token ID | 519 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
warr | +0.561 |
Reply | +0.534 |
Interstitial | +0.512 |
mans | +0.501 |
lers | +0.492 |
Neg logit contributions | |
Russ | -0.508 |
Dems | -0.493 |
oit | -0.486 |
andre | -0.453 |
jamin | -0.449 |
Token | ap |
Token ID | 499 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
warr | +0.844 |
Reply | +0.802 |
Interstitial | +0.765 |
mans | +0.747 |
lers | +0.728 |
Neg logit contributions | |
Russ | -0.964 |
Dems | -0.951 |
oit | -0.939 |
andre | -0.883 |
jamin | -0.872 |
Token | " |
Token ID | 1 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
warr | +0.147 |
Reply | +0.140 |
Interstitial | +0.133 |
mans | +0.131 |
lers | +0.128 |
Neg logit contributions | |
Russ | -0.126 |
Dems | -0.123 |
oit | -0.121 |
andre | -0.113 |
jamin | -0.112 |
Token | phase |
Token ID | 7108 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Russ | +0.315 |
Dems | +0.307 |
oit | +0.306 |
andre | +0.287 |
jamin | +0.284 |
Neg logit contributions | |
warr | -0.300 |
Reply | -0.283 |
Interstitial | -0.271 |
mans | -0.262 |
lers | -0.255 |
Token | doubles |
Token ID | 21938 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
warr | +0.589 |
Reply | +0.556 |
Interstitial | +0.533 |
mans | +0.515 |
lers | +0.500 |
Neg logit contributions | |
Russ | -0.597 |
Dems | -0.582 |
oit | -0.580 |
andre | -0.543 |
jamin | -0.539 |
Token | ; |
Token ID | 26 |
Feature activation | -4.53e-03 |
Pos logit contributions | |
warr | +0.162 |
Reply | +0.152 |
Interstitial | +0.145 |
mans | +0.141 |
lers | +0.137 |
Neg logit contributions | |
Russ | -0.181 |
Dems | -0.177 |
oit | -0.176 |
andre | -0.166 |
jamin | -0.164 |
Token | and |
Token ID | 290 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Russ | +0.006 |
oit | +0.006 |
Dems | +0.006 |
andre | +0.005 |
jamin | +0.005 |
Neg logit contributions | |
warr | -0.006 |
Reply | -0.006 |
Interstitial | -0.006 |
mans | -0.005 |
lers | -0.005 |
Token | coal |
Token ID | 5655 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Russ | +0.303 |
Dems | +0.295 |
oit | +0.294 |
andre | +0.274 |
jamin | +0.272 |
Neg logit contributions | |
warr | -0.325 |
Reply | -0.307 |
Interstitial | -0.294 |
mans | -0.286 |
lers | -0.278 |
Token | - |
Token ID | 12 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Russ | +4.547 |
Dems | +4.478 |
oit | +4.456 |
andre | +4.141 |
jamin | +4.130 |
Neg logit contributions | |
warr | -4.509 |
Reply | -4.279 |
Interstitial | -4.103 |
mans | -3.863 |
lers | -3.750 |
Token | fired |
Token ID | 26803 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
Russ | +0.212 |
Dems | +0.209 |
oit | +0.207 |
andre | +0.195 |
jamin | +0.194 |
Neg logit contributions | |
warr | -0.151 |
Reply | -0.142 |
Interstitial | -0.135 |
mans | -0.131 |
lers | -0.126 |
Token | electricity |
Token ID | 8744 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
Dems | +4.153 |
Russ | +4.140 |
oit | +4.050 |
andre | +3.749 |
jamin | +3.692 |
Neg logit contributions | |
warr | -6.397 |
Reply | -6.114 |
Interstitial | -5.928 |
mans | -5.622 |
lers | -5.416 |
Token | more |
Token ID | 517 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
Russ | +1.480 |
Dems | +1.453 |
oit | +1.445 |
andre | +1.364 |
jamin | +1.353 |
Neg logit contributions | |
warr | -1.097 |
Reply | -1.028 |
Interstitial | -0.977 |
mans | -0.934 |
lers | -0.901 |
Token | than |
Token ID | 621 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
Russ | +1.301 |
Dems | +1.278 |
oit | +1.274 |
andre | +1.209 |
jamin | +1.203 |
Neg logit contributions | |
warr | -0.718 |
Reply | -0.662 |
Interstitial | -0.622 |
mans | -0.592 |
lers | -0.567 |
Token | quadru |
Token ID | 40977 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
warr | +0.606 |
Reply | +0.571 |
Interstitial | +0.546 |
mans | +0.532 |
lers | +0.518 |
Neg logit contributions | |
Russ | -0.615 |
oit | -0.599 |
Dems | -0.598 |
andre | -0.559 |
jamin | -0.555 |
Token | ples |
Token ID | 2374 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Russ | +2.335 |
oit | +2.211 |
Dems | +2.193 |
andre | +1.996 |
cess | +1.969 |
Neg logit contributions | |
warr | -4.507 |
Reply | -4.172 |
Interstitial | -4.110 |
mans | -3.865 |
lers | -3.790 |
Token | the |
Token ID | 262 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
Russ | +0.506 |
Dems | +0.493 |
oit | +0.491 |
andre | +0.458 |
jamin | +0.454 |
Neg logit contributions | |
warr | -0.553 |
Reply | -0.523 |
Interstitial | -0.501 |
mans | -0.487 |
lers | -0.474 |
Token | Deep |
Token ID | 10766 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Russ | +0.094 |
Dems | +0.091 |
oit | +0.091 |
andre | +0.084 |
jamin | +0.083 |
Neg logit contributions | |
warr | -0.116 |
Reply | -0.110 |
Interstitial | -0.106 |
mans | -0.103 |
lers | -0.101 |
Token | water |
Token ID | 7050 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Russ | +1.507 |
oit | +1.468 |
Dems | +1.456 |
andre | +1.347 |
jamin | +1.328 |
Neg logit contributions | |
warr | -2.045 |
Reply | -1.933 |
Interstitial | -1.859 |
mans | -1.797 |
lers | -1.752 |
Token | Horizon |
Token ID | 22776 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
Russ | +1.722 |
oit | +1.660 |
Dems | +1.639 |
andre | +1.401 |
jamin | +1.396 |
Neg logit contributions | |
warr | -5.255 |
Reply | -5.065 |
Interstitial | -4.918 |
mans | -4.797 |
lers | -4.724 |
Token | oil |
Token ID | 3056 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Russ | +2.765 |
oit | +2.718 |
Dems | +2.701 |
jamin | +2.488 |
andre | +2.485 |
Neg logit contributions | |
warr | -3.493 |
Reply | -3.316 |
Interstitial | -3.195 |
mans | -3.092 |
lers | -3.019 |
Token | spill |
Token ID | 19431 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
Russ | +2.249 |
oit | +2.181 |
Dems | +2.168 |
andre | +1.984 |
jamin | +1.976 |
Neg logit contributions | |
warr | -3.455 |
Reply | -3.303 |
Interstitial | -3.185 |
mans | -3.087 |
lers | -3.023 |
Token | . |
Token ID | 13 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
Russ | +5.179 |
oit | +5.094 |
Dems | +5.052 |
jamin | +4.704 |
andre | +4.669 |
Neg logit contributions | |
warr | -5.336 |
Reply | -4.984 |
Interstitial | -4.926 |
mans | -4.651 |
lers | -4.454 |
Token | Shell |
Token ID | 17537 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
Russ | +0.495 |
Dems | +0.482 |
oit | +0.479 |
andre | +0.445 |
jamin | +0.442 |
Neg logit contributions | |
warr | -0.565 |
Reply | -0.533 |
Interstitial | -0.513 |
mans | -0.496 |
lers | -0.483 |
Token | is |
Token ID | 318 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
Russ | +4.155 |
oit | +4.074 |
Dems | +4.058 |
andre | +3.826 |
jamin | +3.787 |
Neg logit contributions | |
warr | -3.797 |
Reply | -3.564 |
Interstitial | -3.501 |
mans | -3.256 |
lers | -3.172 |
Token | planning |
Token ID | 5410 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
Russ | +1.055 |
Dems | +1.032 |
oit | +1.024 |
andre | +0.961 |
jamin | +0.954 |
Neg logit contributions | |
warr | -1.005 |
Reply | -0.948 |
Interstitial | -0.910 |
mans | -0.866 |
lers | -0.846 |
Token | to |
Token ID | 284 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Russ | +1.318 |
Dems | +1.286 |
oit | +1.283 |
andre | +1.202 |
jamin | +1.193 |
Neg logit contributions | |
warr | -1.223 |
Reply | -1.152 |
Interstitial | -1.101 |
mans | -1.064 |
lers | -1.035 |
Token | being |
Token ID | 852 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
warr | +1.518 |
Reply | +1.455 |
Interstitial | +1.400 |
mans | +1.361 |
lers | +1.336 |
Neg logit contributions | |
Russ | -1.055 |
oit | -1.018 |
Dems | -1.006 |
andre | -0.932 |
jamin | -0.923 |
Token | . |
Token ID | 13 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
Russ | +1.423 |
Dems | +1.404 |
oit | +1.394 |
andre | +1.311 |
jamin | +1.294 |
Neg logit contributions | |
warr | -1.305 |
Reply | -1.229 |
Interstitial | -1.181 |
mans | -1.130 |
lers | -1.094 |
Token | A |
Token ID | 317 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Russ | +0.341 |
Dems | +0.332 |
oit | +0.331 |
andre | +0.308 |
jamin | +0.306 |
Neg logit contributions | |
warr | -0.375 |
Reply | -0.355 |
Interstitial | -0.341 |
mans | -0.330 |
lers | -0.322 |
Token | left |
Token ID | 1364 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
warr | +0.237 |
Reply | +0.225 |
Interstitial | +0.215 |
mans | +0.209 |
lers | +0.203 |
Neg logit contributions | |
Russ | -0.215 |
oit | -0.209 |
Dems | -0.207 |
andre | -0.194 |
jamin | -0.191 |
Token | that |
Token ID | 326 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Russ | +1.120 |
Dems | +1.097 |
oit | +1.090 |
andre | +1.022 |
jamin | +1.013 |
Neg logit contributions | |
warr | -1.083 |
Reply | -1.018 |
Interstitial | -0.978 |
mans | -0.943 |
lers | -0.916 |
Token | abs |
Token ID | 2352 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
warr | +0.218 |
Reply | +0.205 |
Interstitial | +0.196 |
mans | +0.189 |
lers | +0.183 |
Neg logit contributions | |
Russ | -0.253 |
Dems | -0.248 |
oit | -0.247 |
andre | -0.232 |
jamin | -0.230 |
Token | ented |
Token ID | 4714 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
Russ | +1.616 |
oit | +1.608 |
Dems | +1.579 |
andre | +1.301 |
cess | +1.266 |
Neg logit contributions | |
warr | -8.896 |
Reply | -8.601 |
Interstitial | -8.411 |
mans | -8.070 |
lers | -8.003 |
Token | itself |
Token ID | 2346 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
warr | +0.699 |
Reply | +0.668 |
Interstitial | +0.642 |
mans | +0.629 |
lers | +0.616 |
Neg logit contributions | |
Russ | -0.455 |
oit | -0.439 |
Dems | -0.434 |
andre | -0.401 |
jamin | -0.398 |
Token | from |
Token ID | 422 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
warr | +0.976 |
Reply | +0.921 |
Interstitial | +0.870 |
mans | +0.850 |
lers | +0.834 |
Neg logit contributions | |
Russ | -1.134 |
oit | -1.100 |
Dems | -1.098 |
andre | -1.032 |
jamin | -1.027 |
Token | the |
Token ID | 262 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
Russ | +0.499 |
Dems | +0.483 |
oit | +0.483 |
andre | +0.448 |
jamin | +0.444 |
Neg logit contributions | |
warr | -0.602 |
Reply | -0.572 |
Interstitial | -0.549 |
mans | -0.534 |
lers | -0.521 |
Token | dirty |
Token ID | 11841 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Russ | +0.127 |
Dems | +0.124 |
oit | +0.124 |
andre | +0.115 |
jamin | +0.114 |
Neg logit contributions | |
warr | -0.154 |
Reply | -0.147 |
Interstitial | -0.141 |
mans | -0.137 |
lers | -0.134 |
Token | blow |
Token ID | 6611 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
warr | +0.318 |
Reply | +0.301 |
Interstitial | +0.290 |
mans | +0.283 |
lers | +0.277 |
Neg logit contributions | |
Russ | -0.230 |
Dems | -0.222 |
oit | -0.220 |
andre | -0.205 |
jamin | -0.202 |
Token | out |
Token ID | 448 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Russ | +0.779 |
Dems | +0.761 |
oit | +0.756 |
andre | +0.706 |
jamin | +0.699 |
Neg logit contributions | |
warr | -0.890 |
Reply | -0.845 |
Interstitial | -0.809 |
mans | -0.788 |
lers | -0.768 |
Token | late |
Token ID | 2739 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
Russ | +0.430 |
Dems | +0.420 |
oit | +0.418 |
andre | +0.393 |
jamin | +0.390 |
Neg logit contributions | |
warr | -0.393 |
Reply | -0.370 |
Interstitial | -0.353 |
mans | -0.342 |
lers | -0.332 |
Token | in |
Token ID | 287 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
Russ | +0.905 |
Dems | +0.884 |
oit | +0.882 |
andre | +0.825 |
jamin | +0.819 |
Neg logit contributions | |
warr | -0.852 |
Reply | -0.804 |
Interstitial | -0.767 |
mans | -0.741 |
lers | -0.721 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Russ | +0.812 |
Dems | +0.791 |
oit | +0.788 |
andre | +0.736 |
jamin | +0.729 |
Neg logit contributions | |
warr | -0.881 |
Reply | -0.834 |
Interstitial | -0.798 |
mans | -0.775 |
lers | -0.755 |
Token | drilling |
Token ID | 19747 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
Russ | +0.212 |
Dems | +0.205 |
oit | +0.205 |
andre | +0.189 |
jamin | +0.187 |
Neg logit contributions | |
warr | -0.289 |
Reply | -0.275 |
Interstitial | -0.265 |
mans | -0.258 |
lers | -0.252 |
Token | season |
Token ID | 1622 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Russ | +4.782 |
Dems | +4.665 |
oit | +4.613 |
jamin | +4.289 |
andre | +4.254 |
Neg logit contributions | |
warr | -5.596 |
Reply | -5.415 |
Interstitial | -5.247 |
mans | -4.970 |
lers | -4.900 |
Token | , |
Token ID | 11 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
Russ | +1.642 |
Dems | +1.604 |
oit | +1.600 |
andre | +1.500 |
jamin | +1.485 |
Neg logit contributions | |
warr | -1.552 |
Reply | -1.461 |
Interstitial | -1.399 |
mans | -1.348 |
lers | -1.308 |
Token | just |
Token ID | 655 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
Russ | +0.059 |
Dems | +0.057 |
oit | +0.057 |
andre | +0.053 |
jamin | +0.053 |
Neg logit contributions | |
warr | -0.058 |
Reply | -0.054 |
Interstitial | -0.052 |
mans | -0.050 |
lers | -0.049 |
Token | before |
Token ID | 878 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
warr | +0.973 |
Reply | +0.913 |
Interstitial | +0.868 |
mans | +0.838 |
lers | +0.812 |
Neg logit contributions | |
Russ | -1.201 |
Dems | -1.173 |
oit | -1.171 |
andre | -1.102 |
jamin | -1.095 |
Token | ice |
Token ID | 4771 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
Russ | +0.937 |
Dems | +0.912 |
oit | +0.910 |
andre | +0.848 |
jamin | +0.841 |
Neg logit contributions | |
warr | -1.025 |
Reply | -0.970 |
Interstitial | -0.931 |
mans | -0.903 |
lers | -0.880 |
Token | liter |
Token ID | 17201 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
Russ | +0.387 |
Dems | +0.380 |
oit | +0.379 |
andre | +0.360 |
jamin | +0.357 |
Neg logit contributions | |
warr | -0.227 |
Reply | -0.210 |
Interstitial | -0.197 |
mans | -0.188 |
lers | -0.181 |
Token | Eco |
Token ID | 38719 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
warr | +0.049 |
Reply | +0.046 |
Interstitial | +0.044 |
mans | +0.043 |
lers | +0.041 |
Neg logit contributions | |
Russ | -0.046 |
Dems | -0.044 |
oit | -0.044 |
andre | -0.041 |
jamin | -0.041 |
Token | Boost |
Token ID | 45686 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Russ | +2.224 |
oit | +2.169 |
Dems | +2.160 |
andre | +2.052 |
jamin | +2.033 |
Neg logit contributions | |
warr | -1.379 |
Reply | -1.225 |
Interstitial | -1.174 |
mans | -1.111 |
lers | -1.069 |
Token | is |
Token ID | 318 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Russ | +1.871 |
Dems | +1.829 |
oit | +1.827 |
andre | +1.697 |
jamin | +1.682 |
Neg logit contributions | |
warr | -2.006 |
Reply | -1.905 |
Interstitial | -1.832 |
mans | -1.763 |
lers | -1.717 |
Token | a |
Token ID | 257 |
Feature activation | +7.29e-03 |
Pos logit contributions | |
Russ | +0.186 |
Dems | +0.181 |
oit | +0.181 |
andre | +0.169 |
jamin | +0.168 |
Neg logit contributions | |
warr | -0.185 |
Reply | -0.175 |
Interstitial | -0.167 |
mans | -0.162 |
lers | -0.158 |
Token | Rapt |
Token ID | 21301 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
warr | +0.010 |
Reply | +0.010 |
Interstitial | +0.009 |
mans | +0.009 |
lers | +0.009 |
Neg logit contributions | |
Russ | -0.009 |
Dems | -0.009 |
oit | -0.009 |
andre | -0.008 |
jamin | -0.008 |
Token | or |
Token ID | 273 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Russ | +4.086 |
oit | +4.073 |
Dems | +3.870 |
andre | +3.654 |
jamin | +3.569 |
Neg logit contributions | |
warr | -6.610 |
Reply | -6.033 |
Interstitial | -5.976 |
mans | -5.590 |
lers | -5.549 |
Token | exclusive |
Token ID | 8568 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Russ | +0.179 |
Dems | +0.174 |
oit | +0.174 |
andre | +0.162 |
jamin | +0.161 |
Neg logit contributions | |
warr | -0.185 |
Reply | -0.175 |
Interstitial | -0.167 |
mans | -0.162 |
lers | -0.158 |
Token | in |
Token ID | 287 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
Russ | +2.132 |
oit | +2.096 |
Dems | +2.091 |
andre | +1.947 |
jamin | +1.935 |
Neg logit contributions | |
warr | -1.994 |
Reply | -1.903 |
Interstitial | -1.821 |
mans | -1.741 |
lers | -1.695 |
Token | the |
Token ID | 262 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Russ | +0.377 |
oit | +0.363 |
Dems | +0.362 |
andre | +0.338 |
jamin | +0.336 |
Neg logit contributions | |
warr | -0.426 |
Reply | -0.402 |
Interstitial | -0.384 |
mans | -0.377 |
lers | -0.367 |
Token | F |
Token ID | 376 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
warr | +0.323 |
Reply | +0.306 |
Interstitial | +0.293 |
mans | +0.286 |
lers | +0.279 |
Neg logit contributions | |
Russ | -0.278 |
oit | -0.270 |
Dems | -0.269 |
andre | -0.251 |
jamin | -0.249 |
Token |
|
Token ID | 198 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Russ | +0.093 |
Dems | +0.090 |
oit | +0.090 |
andre | +0.083 |
jamin | +0.083 |
Neg logit contributions | |
warr | -0.113 |
Reply | -0.107 |
Interstitial | -0.103 |
mans | -0.100 |
lers | -0.098 |
Token | The |
Token ID | 464 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Russ | +0.307 |
Dems | +0.299 |
oit | +0.298 |
andre | +0.280 |
jamin | +0.278 |
Neg logit contributions | |
warr | -0.266 |
Reply | -0.249 |
Interstitial | -0.238 |
mans | -0.229 |
lers | -0.223 |
Token | all |
Token ID | 477 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
warr | +0.434 |
Reply | +0.411 |
Interstitial | +0.393 |
mans | +0.382 |
lers | +0.372 |
Neg logit contributions | |
Russ | -0.395 |
Dems | -0.385 |
oit | -0.384 |
andre | -0.358 |
jamin | -0.355 |
Token | - |
Token ID | 12 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
Russ | +0.932 |
Dems | +0.905 |
oit | +0.902 |
andre | +0.837 |
jamin | +0.831 |
Neg logit contributions | |
warr | -1.217 |
Reply | -1.157 |
Interstitial | -1.110 |
mans | -1.088 |
lers | -1.060 |
Token | new |
Token ID | 3605 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Russ | +0.513 |
Dems | +0.500 |
oit | +0.498 |
andre | +0.457 |
jamin | +0.455 |
Neg logit contributions | |
warr | -0.711 |
Reply | -0.679 |
Interstitial | -0.653 |
mans | -0.639 |
lers | -0.622 |
Token | Rapt |
Token ID | 21301 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
warr | +0.257 |
Reply | +0.245 |
Interstitial | +0.237 |
mans | +0.232 |
lers | +0.227 |
Neg logit contributions | |
Russ | -0.147 |
Dems | -0.142 |
oit | -0.141 |
andre | -0.128 |
jamin | -0.127 |
Token | or |
Token ID | 273 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
oit | +3.993 |
Russ | +3.975 |
Dems | +3.753 |
andre | +3.539 |
jamin | +3.447 |
Neg logit contributions | |
warr | -6.758 |
Reply | -6.070 |
Interstitial | -6.052 |
mans | -5.616 |
lers | -5.528 |
Token | also |
Token ID | 635 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Russ | +0.452 |
Dems | +0.443 |
oit | +0.441 |
andre | +0.414 |
jamin | +0.410 |
Neg logit contributions | |
warr | -0.405 |
Reply | -0.382 |
Interstitial | -0.366 |
mans | -0.351 |
lers | -0.341 |
Token | boasts |
Token ID | 22103 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
warr | +0.465 |
Reply | +0.436 |
Interstitial | +0.414 |
mans | +0.397 |
lers | +0.385 |
Neg logit contributions | |
Russ | -0.619 |
Dems | -0.606 |
oit | -0.604 |
andre | -0.569 |
jamin | -0.566 |
Token | its |
Token ID | 663 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Russ | +1.958 |
Dems | +1.918 |
oit | +1.895 |
andre | +1.770 |
jamin | +1.746 |
Neg logit contributions | |
warr | -2.217 |
Reply | -2.115 |
Interstitial | -2.039 |
mans | -1.962 |
lers | -1.906 |
Token | first |
Token ID | 717 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Russ | +0.257 |
Dems | +0.251 |
oit | +0.250 |
andre | +0.235 |
jamin | +0.233 |
Neg logit contributions | |
warr | -0.218 |
Reply | -0.205 |
Interstitial | -0.196 |
mans | -0.189 |
lers | -0.183 |
Token | Police |
Token ID | 9039 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
warr | +0.638 |
Reply | +0.606 |
Interstitial | +0.577 |
mans | +0.557 |
lers | +0.540 |
Neg logit contributions | |
Russ | -0.725 |
Dems | -0.712 |
oit | -0.709 |
andre | -0.664 |
jamin | -0.660 |
Token | have |
Token ID | 423 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Russ | +0.692 |
Dems | +0.678 |
oit | +0.674 |
andre | +0.631 |
jamin | +0.625 |
Neg logit contributions | |
warr | -0.591 |
Reply | -0.556 |
Interstitial | -0.537 |
mans | -0.512 |
lers | -0.496 |
Token | also |
Token ID | 635 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
warr | +0.228 |
Reply | +0.214 |
Interstitial | +0.205 |
mans | +0.197 |
lers | +0.191 |
Neg logit contributions | |
Russ | -0.271 |
Dems | -0.265 |
oit | -0.264 |
andre | -0.248 |
jamin | -0.247 |
Token | seized |
Token ID | 12000 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
warr | +0.377 |
Reply | +0.354 |
Interstitial | +0.339 |
mans | +0.326 |
lers | +0.316 |
Neg logit contributions | |
Russ | -0.437 |
Dems | -0.427 |
oit | -0.427 |
andre | -0.400 |
jamin | -0.398 |
Token | two |
Token ID | 734 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
warr | +0.807 |
Reply | +0.764 |
Interstitial | +0.730 |
mans | +0.711 |
lers | +0.693 |
Neg logit contributions | |
Russ | -0.739 |
Dems | -0.718 |
oit | -0.716 |
andre | -0.667 |
jamin | -0.662 |
Token | dump |
Token ID | 10285 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
Russ | +1.284 |
Dems | +1.255 |
oit | +1.249 |
andre | +1.166 |
jamin | +1.157 |
Neg logit contributions | |
warr | -1.268 |
Reply | -1.197 |
Interstitial | -1.154 |
mans | -1.105 |
lers | -1.075 |
Token | ers |
Token ID | 364 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Russ | +4.560 |
Dems | +4.409 |
oit | +4.408 |
andre | +4.057 |
jamin | +4.000 |
Neg logit contributions | |
warr | -5.957 |
Reply | -5.660 |
Interstitial | -5.501 |
mans | -5.152 |
lers | -4.958 |
Token | and |
Token ID | 290 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
Russ | +0.235 |
Dems | +0.229 |
oit | +0.228 |
andre | +0.214 |
jamin | +0.212 |
Neg logit contributions | |
warr | -0.219 |
Reply | -0.206 |
Interstitial | -0.197 |
mans | -0.190 |
lers | -0.185 |
Token | arrested |
Token ID | 5169 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
Russ | +0.058 |
Dems | +0.056 |
oit | +0.056 |
andre | +0.052 |
jamin | +0.052 |
Neg logit contributions | |
warr | -0.065 |
Reply | -0.062 |
Interstitial | -0.059 |
mans | -0.057 |
lers | -0.056 |
Token | d |
Token ID | 288 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
warr | +0.972 |
Reply | +0.920 |
Interstitial | +0.878 |
mans | +0.861 |
lers | +0.841 |
Neg logit contributions | |
Russ | -0.835 |
Dems | -0.810 |
oit | -0.810 |
andre | -0.752 |
jamin | -0.746 |
Token | umper |
Token ID | 15829 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
Russ | +0.513 |
Dems | +0.500 |
oit | +0.499 |
andre | +0.468 |
jamin | +0.465 |
Neg logit contributions | |
warr | -0.485 |
Reply | -0.455 |
Interstitial | -0.436 |
mans | -0.420 |
lers | -0.408 |
Token | . |
Token ID | 13 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
Russ | +0.419 |
Dems | +0.409 |
oit | +0.408 |
andre | +0.383 |
jamin | +0.380 |
Neg logit contributions | |
warr | -0.379 |
Reply | -0.357 |
Interstitial | -0.341 |
mans | -0.330 |
lers | -0.321 |
Token |
|
Token ID | 198 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Russ | +0.120 |
Dems | +0.116 |
oit | +0.116 |
andre | +0.109 |
jamin | +0.108 |
Neg logit contributions | |
warr | -0.133 |
Reply | -0.126 |
Interstitial | -0.121 |
mans | -0.118 |
lers | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Russ | +0.300 |
Dems | +0.292 |
oit | +0.291 |
andre | +0.270 |
jamin | +0.268 |
Neg logit contributions | |
warr | -0.375 |
Reply | -0.352 |
Interstitial | -0.339 |
mans | -0.329 |
lers | -0.321 |
Token | The |
Token ID | 464 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Russ | +0.531 |
Dems | +0.515 |
oit | +0.515 |
andre | +0.484 |
jamin | +0.479 |
Neg logit contributions | |
warr | -0.466 |
Reply | -0.433 |
Interstitial | -0.414 |
mans | -0.400 |
lers | -0.388 |
Token | new |
Token ID | 649 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
warr | +0.351 |
Reply | +0.332 |
Interstitial | +0.317 |
mans | +0.308 |
lers | +0.300 |
Neg logit contributions | |
Russ | -0.337 |
Dems | -0.328 |
oit | -0.327 |
andre | -0.306 |
jamin | -0.303 |
Token | Rapt |
Token ID | 21301 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
warr | +1.567 |
Reply | +1.484 |
Interstitial | +1.418 |
mans | +1.387 |
lers | +1.351 |
Neg logit contributions | |
Russ | -1.460 |
Dems | -1.420 |
oit | -1.415 |
andre | -1.319 |
jamin | -1.316 |
Token | or |
Token ID | 273 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
oit | +3.971 |
Russ | +3.948 |
Dems | +3.672 |
andre | +3.496 |
iary | +3.421 |
Neg logit contributions | |
warr | -6.882 |
Interstitial | -6.113 |
Reply | -6.104 |
mans | -5.632 |
Schwar | -5.559 |
Token | features |
Token ID | 3033 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Russ | +0.534 |
Dems | +0.522 |
oit | +0.520 |
andre | +0.487 |
jamin | +0.483 |
Neg logit contributions | |
warr | -0.494 |
Reply | -0.466 |
Interstitial | -0.447 |
mans | -0.429 |
lers | -0.418 |
Token | calibration |
Token ID | 36537 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
warr | +1.416 |
Reply | +1.332 |
Interstitial | +1.267 |
mans | +1.242 |
lers | +1.215 |
Neg logit contributions | |
Russ | -1.328 |
oit | -1.294 |
Dems | -1.285 |
andre | -1.200 |
jamin | -1.199 |
Token | changes |
Token ID | 2458 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
Russ | +1.142 |
Dems | +1.116 |
oit | +1.111 |
andre | +1.039 |
jamin | +1.030 |
Neg logit contributions | |
warr | -1.117 |
Reply | -1.056 |
Interstitial | -1.011 |
mans | -0.976 |
lers | -0.948 |
Token | to |
Token ID | 284 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
warr | +2.272 |
Reply | +2.116 |
Interstitial | +2.021 |
mans | +1.974 |
lers | +1.928 |
Neg logit contributions | |
Russ | -2.710 |
Dems | -2.638 |
oit | -2.630 |
andre | -2.475 |
jamin | -2.468 |
Token | , |
Token ID | 11 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
warr | +2.546 |
Reply | +2.425 |
Interstitial | +2.268 |
mans | +2.245 |
lers | +2.162 |
Neg logit contributions | |
Russ | -3.069 |
oit | -2.970 |
Dems | -2.969 |
andre | -2.801 |
jamin | -2.787 |
Token | Jam |
Token ID | 9986 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
warr | +1.233 |
Reply | +1.167 |
Interstitial | +1.111 |
mans | +1.080 |
lers | +1.049 |
Neg logit contributions | |
Russ | -1.254 |
Dems | -1.220 |
oit | -1.218 |
andre | -1.140 |
jamin | -1.131 |
Token | n |
Token ID | 77 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
warr | +0.761 |
Reply | +0.715 |
Interstitial | +0.675 |
mans | +0.661 |
lers | +0.633 |
Neg logit contributions | |
Russ | -1.135 |
oit | -1.111 |
Dems | -1.110 |
andre | -1.042 |
jamin | -1.040 |
Token | agar |
Token ID | 32452 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
warr | +1.251 |
Reply | +1.179 |
Interstitial | +1.110 |
mans | +1.069 |
lers | +1.037 |
Neg logit contributions | |
Russ | -2.093 |
Dems | -2.050 |
oit | -2.027 |
andre | -1.919 |
jamin | -1.918 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
warr | +4.167 |
Reply | +4.073 |
Interstitial | +3.760 |
mans | +3.702 |
lers | +3.543 |
Neg logit contributions | |
Russ | -5.163 |
oit | -4.986 |
Dems | -4.971 |
andre | -4.704 |
jamin | -4.669 |
Token | Gujarat |
Token ID | 30311 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
warr | +1.485 |
Reply | +1.413 |
Interstitial | +1.346 |
mans | +1.313 |
lers | +1.275 |
Neg logit contributions | |
Russ | -1.341 |
oit | -1.299 |
Dems | -1.297 |
andre | -1.211 |
jamin | -1.199 |
Token | 36 |
Token ID | 4570 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
warr | +4.733 |
Reply | +4.617 |
Interstitial | +4.320 |
mans | +4.222 |
lers | +4.162 |
Neg logit contributions | |
Russ | -5.163 |
oit | -5.017 |
Dems | -4.935 |
andre | -4.705 |
jamin | -4.622 |
Token | 1001 |
Token ID | 47705 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
warr | +1.116 |
Reply | +1.063 |
Interstitial | +1.003 |
mans | +0.964 |
lers | +0.933 |
Neg logit contributions | |
Russ | -1.607 |
Dems | -1.579 |
oit | -1.573 |
andre | -1.487 |
jamin | -1.474 |
Token | , |
Token ID | 11 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Russ | +1.553 |
Dems | +1.518 |
oit | +1.512 |
andre | +1.409 |
jamin | +1.405 |
Neg logit contributions | |
warr | -1.555 |
Reply | -1.459 |
Interstitial | -1.395 |
mans | -1.354 |
lers | -1.325 |
Token | India |
Token ID | 3794 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
warr | +1.200 |
Reply | +1.135 |
Interstitial | +1.060 |
mans | +1.038 |
lers | +0.996 |
Neg logit contributions | |
Russ | -1.403 |
oit | -1.358 |
Dems | -1.352 |
andre | -1.281 |
jamin | -1.260 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
warr | +2.655 |
Reply | +2.520 |
Interstitial | +2.416 |
mans | +2.337 |
lers | +2.265 |
Neg logit contributions | |
Russ | -2.516 |
Dems | -2.444 |
oit | -2.436 |
andre | -2.289 |
jamin | -2.250 |
Token | connecting |
Token ID | 14320 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
Russ | +0.871 |
Dems | +0.851 |
oit | +0.848 |
andre | +0.792 |
jamin | +0.787 |
Neg logit contributions | |
warr | -0.855 |
Reply | -0.804 |
Interstitial | -0.781 |
mans | -0.743 |
lers | -0.727 |
Token | Roh |
Token ID | 32694 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
warr | +0.117 |
Reply | +0.110 |
Interstitial | +0.106 |
mans | +0.101 |
lers | +0.098 |
Neg logit contributions | |
Russ | -0.130 |
Dems | -0.127 |
oit | -0.126 |
andre | -0.119 |
jamin | -0.118 |
Token | t |
Token ID | 83 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
warr | +4.717 |
Reply | +4.476 |
mans | +4.286 |
lers | +4.210 |
Interstitial | +4.117 |
Neg logit contributions | |
Russ | -6.108 |
Dems | -5.849 |
oit | -5.747 |
jamin | -5.524 |
andre | -5.409 |
Token | ak |
Token ID | 461 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
warr | +1.445 |
Reply | +1.372 |
Interstitial | +1.304 |
mans | +1.284 |
lers | +1.245 |
Neg logit contributions | |
Russ | -1.822 |
Dems | -1.776 |
oit | -1.763 |
andre | -1.652 |
jamin | -1.646 |
Token | to |
Token ID | 284 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
warr | +0.266 |
Reply | +0.250 |
Interstitial | +0.239 |
mans | +0.231 |
lers | +0.224 |
Neg logit contributions | |
Russ | -0.300 |
Dems | -0.293 |
oit | -0.292 |
andre | -0.274 |
jamin | -0.272 |
Token | Delhi |
Token ID | 12517 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
Russ | +0.353 |
Dems | +0.346 |
oit | +0.345 |
andre | +0.323 |
jamin | +0.321 |
Neg logit contributions | |
warr | -0.316 |
Reply | -0.297 |
Interstitial | -0.286 |
mans | -0.274 |
lers | -0.266 |
Token | . |
Token ID | 13 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
warr | +4.204 |
Reply | +4.038 |
Interstitial | +3.751 |
mans | +3.733 |
lers | +3.594 |
Neg logit contributions | |
Russ | -4.849 |
Dems | -4.709 |
oit | -4.693 |
andre | -4.413 |
jamin | -4.383 |
Token | After |
Token ID | 2293 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
warr | +1.055 |
Reply | +1.011 |
Interstitial | +0.968 |
mans | +0.938 |
lers | +0.914 |
Neg logit contributions | |
Russ | -0.962 |
oit | -0.939 |
Dems | -0.936 |
andre | -0.874 |
jamin | -0.863 |
Token | this |
Token ID | 428 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
warr | +0.079 |
Reply | +0.075 |
Interstitial | +0.072 |
mans | +0.069 |
lers | +0.067 |
Neg logit contributions | |
Russ | -0.077 |
Dems | -0.075 |
oit | -0.075 |
andre | -0.070 |
jamin | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
warr | +0.218 |
Reply | +0.206 |
Interstitial | +0.197 |
mans | +0.190 |
lers | +0.185 |
Neg logit contributions | |
Russ | -0.234 |
Dems | -0.228 |
oit | -0.227 |
andre | -0.213 |
jamin | -0.212 |
Token | the |
Token ID | 262 |
Feature activation | -5.08e-03 |
Pos logit contributions | |
Russ | +0.071 |
Dems | +0.069 |
oit | +0.069 |
andre | +0.064 |
jamin | +0.064 |
Neg logit contributions | |
warr | -0.081 |
Reply | -0.076 |
Interstitial | -0.073 |
mans | -0.071 |
lers | -0.069 |
Token | as |
Token ID | 355 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Russ | +0.545 |
Dems | +0.532 |
oit | +0.531 |
andre | +0.495 |
jamin | +0.491 |
Neg logit contributions | |
warr | -0.574 |
Reply | -0.544 |
Interstitial | -0.522 |
mans | -0.503 |
lers | -0.490 |
Token | true |
Token ID | 2081 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Russ | +0.562 |
Dems | +0.546 |
oit | +0.544 |
andre | +0.501 |
jamin | +0.496 |
Neg logit contributions | |
warr | -0.793 |
Reply | -0.757 |
Interstitial | -0.729 |
mans | -0.712 |
lers | -0.697 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Russ | +2.382 |
Dems | +2.332 |
oit | +2.320 |
andre | +2.161 |
jamin | +2.146 |
Neg logit contributions | |
warr | -2.657 |
Reply | -2.524 |
Interstitial | -2.433 |
mans | -2.329 |
lers | -2.269 |
Token | allegation |
Token ID | 24389 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Russ | +0.161 |
Dems | +0.156 |
oit | +0.155 |
andre | +0.144 |
jamin | +0.143 |
Neg logit contributions | |
warr | -0.210 |
Reply | -0.201 |
Interstitial | -0.192 |
mans | -0.188 |
lers | -0.183 |
Token | that |
Token ID | 326 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Russ | +0.532 |
Dems | +0.519 |
oit | +0.517 |
andre | +0.483 |
jamin | +0.480 |
Neg logit contributions | |
warr | -0.534 |
Reply | -0.504 |
Interstitial | -0.484 |
mans | -0.467 |
lers | -0.454 |
Token | Brah |
Token ID | 36415 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
warr | +0.271 |
Reply | +0.257 |
Interstitial | +0.247 |
mans | +0.238 |
lers | +0.232 |
Neg logit contributions | |
Russ | -0.247 |
Dems | -0.241 |
oit | -0.240 |
andre | -0.224 |
jamin | -0.222 |
Token | ms |
Token ID | 907 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
warr | +3.072 |
Reply | +2.897 |
Interstitial | +2.705 |
mans | +2.667 |
lers | +2.526 |
Neg logit contributions | |
Russ | -5.432 |
Dems | -5.318 |
oit | -5.312 |
andre | -5.049 |
jamin | -5.012 |
Token | slaughtered |
Token ID | 33850 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
Russ | +0.390 |
Dems | +0.381 |
oit | +0.381 |
andre | +0.358 |
jamin | +0.355 |
Neg logit contributions | |
warr | -0.339 |
Reply | -0.319 |
Interstitial | -0.304 |
mans | -0.293 |
lers | -0.284 |
Token | fel |
Token ID | 10756 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
Russ | +0.684 |
Dems | +0.669 |
oit | +0.665 |
andre | +0.618 |
jamin | +0.611 |
Neg logit contributions | |
warr | -0.766 |
Reply | -0.726 |
Interstitial | -0.699 |
mans | -0.671 |
lers | -0.654 |
Token | ines |
Token ID | 1127 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
warr | +0.631 |
Reply | +0.579 |
Interstitial | +0.535 |
mans | +0.505 |
lers | +0.483 |
Neg logit contributions | |
Russ | -1.303 |
Dems | -1.279 |
oit | -1.277 |
andre | -1.216 |
jamin | -1.208 |
Token | , |
Token ID | 11 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
Russ | +0.513 |
Dems | +0.503 |
oit | +0.501 |
andre | +0.470 |
jamin | +0.464 |
Neg logit contributions | |
warr | -0.477 |
Reply | -0.448 |
Interstitial | -0.433 |
mans | -0.410 |
lers | -0.398 |
Token | of |
Token ID | 286 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Russ | +0.746 |
Dems | +0.726 |
oit | +0.725 |
andre | +0.675 |
jamin | +0.669 |
Neg logit contributions | |
warr | -0.822 |
Reply | -0.778 |
Interstitial | -0.747 |
mans | -0.724 |
lers | -0.706 |
Token | O |
Token ID | 440 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
warr | +0.485 |
Reply | +0.458 |
Interstitial | +0.438 |
mans | +0.425 |
lers | +0.413 |
Neg logit contributions | |
Russ | -0.486 |
Dems | -0.473 |
oit | -0.473 |
andre | -0.442 |
jamin | -0.438 |
Token | . |
Token ID | 13 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
warr | +0.961 |
Reply | +0.904 |
Interstitial | +0.864 |
mans | +0.834 |
lers | +0.811 |
Neg logit contributions | |
Russ | -1.041 |
Dems | -1.016 |
oit | -1.013 |
andre | -0.950 |
jamin | -0.943 |
Token | J |
Token ID | 41 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
warr | +0.833 |
Reply | +0.758 |
Interstitial | +0.721 |
mans | +0.685 |
lers | +0.661 |
Neg logit contributions | |
Russ | -1.348 |
Dems | -1.316 |
oit | -1.314 |
andre | -1.244 |
jamin | -1.241 |
Token | . |
Token ID | 13 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
Russ | +1.074 |
Dems | +1.047 |
oit | +1.044 |
andre | +0.978 |
jamin | +0.970 |
Neg logit contributions | |
warr | -1.017 |
Reply | -0.958 |
Interstitial | -0.915 |
mans | -0.886 |
lers | -0.861 |
Token | Simpson |
Token ID | 20531 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
warr | +1.312 |
Reply | +1.244 |
Interstitial | +1.186 |
mans | +1.157 |
lers | +1.126 |
Neg logit contributions | |
Russ | -1.244 |
oit | -1.210 |
Dems | -1.208 |
andre | -1.126 |
jamin | -1.117 |
Token | � |
Token ID | 447 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
warr | +3.636 |
Reply | +3.502 |
Interstitial | +3.284 |
mans | +3.225 |
lers | +3.142 |
Neg logit contributions | |
Russ | -3.852 |
oit | -3.774 |
Dems | -3.712 |
andre | -3.501 |
jamin | -3.452 |
Token | � |
Token ID | 247 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Russ | +0.455 |
Dems | +0.446 |
oit | +0.443 |
andre | +0.419 |
jamin | +0.416 |
Neg logit contributions | |
warr | -0.353 |
Reply | -0.329 |
Interstitial | -0.313 |
mans | -0.302 |
lers | -0.292 |
Token | s |
Token ID | 82 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
warr | +0.588 |
Reply | +0.553 |
Interstitial | +0.525 |
mans | +0.508 |
lers | +0.491 |
Neg logit contributions | |
Russ | -0.752 |
oit | -0.736 |
Dems | -0.735 |
andre | -0.691 |
jamin | -0.686 |
Token | trial |
Token ID | 4473 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
warr | +0.347 |
Reply | +0.327 |
Interstitial | +0.313 |
mans | +0.303 |
lers | +0.295 |
Neg logit contributions | |
Russ | -0.354 |
Dems | -0.345 |
oit | -0.344 |
andre | -0.322 |
jamin | -0.320 |
Token | for |
Token ID | 329 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
warr | +0.078 |
Reply | +0.074 |
Interstitial | +0.070 |
mans | +0.068 |
lers | +0.066 |
Neg logit contributions | |
Russ | -0.075 |
Dems | -0.073 |
oit | -0.073 |
andre | -0.068 |
jamin | -0.068 |
Token | in |
Token ID | 259 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
warr | +0.705 |
Reply | +0.666 |
Interstitial | +0.620 |
mans | +0.615 |
lers | +0.590 |
Neg logit contributions | |
Russ | -0.984 |
Dems | -0.977 |
oit | -0.965 |
andre | -0.909 |
jamin | -0.909 |
Token | - |
Token ID | 12 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
Russ | +0.493 |
Dems | +0.477 |
oit | +0.477 |
andre | +0.439 |
jamin | +0.435 |
Neg logit contributions | |
warr | -0.714 |
Reply | -0.676 |
Interstitial | -0.653 |
mans | -0.634 |
lers | -0.620 |
Token | law |
Token ID | 6270 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
warr | +0.653 |
Reply | +0.628 |
Interstitial | +0.598 |
mans | +0.585 |
lers | +0.568 |
Neg logit contributions | |
Russ | -0.641 |
Dems | -0.630 |
oit | -0.623 |
andre | -0.582 |
jamin | -0.578 |
Token | Raj |
Token ID | 13308 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Russ | +0.193 |
Dems | +0.189 |
oit | +0.188 |
andre | +0.176 |
jamin | +0.175 |
Neg logit contributions | |
warr | -0.188 |
Reply | -0.177 |
Interstitial | -0.170 |
mans | -0.163 |
lers | -0.159 |
Token | nik |
Token ID | 17187 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
warr | +3.030 |
Reply | +2.853 |
Interstitial | +2.695 |
mans | +2.662 |
lers | +2.560 |
Neg logit contributions | |
Russ | -4.025 |
Dems | -3.923 |
oit | -3.891 |
andre | -3.670 |
jamin | -3.653 |
Token | anth |
Token ID | 29313 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
Russ | +0.088 |
Dems | +0.086 |
oit | +0.085 |
andre | +0.080 |
jamin | +0.080 |
Neg logit contributions | |
warr | -0.076 |
Reply | -0.071 |
Interstitial | -0.068 |
mans | -0.065 |
lers | -0.063 |
Token | Singh |
Token ID | 14403 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
warr | +4.004 |
Reply | +3.808 |
Interstitial | +3.554 |
mans | +3.542 |
lers | +3.399 |
Neg logit contributions | |
Russ | -4.630 |
Dems | -4.491 |
oit | -4.463 |
andre | -4.191 |
jamin | -4.174 |
Token | and |
Token ID | 290 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
warr | +4.952 |
Reply | +4.735 |
mans | +4.401 |
Interstitial | +4.383 |
lers | +4.239 |
Neg logit contributions | |
Russ | -5.923 |
Dems | -5.786 |
oit | -5.746 |
jamin | -5.361 |
andre | -5.342 |
Token | five |
Token ID | 1936 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
warr | +0.693 |
Reply | +0.656 |
Interstitial | +0.627 |
mans | +0.610 |
lers | +0.594 |
Neg logit contributions | |
Russ | -0.637 |
Dems | -0.620 |
oit | -0.619 |
andre | -0.576 |
jamin | -0.572 |
Token | others |
Token ID | 1854 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Russ | +0.318 |
Dems | +0.308 |
oit | +0.307 |
andre | +0.284 |
jamin | +0.281 |
Neg logit contributions | |
warr | -0.421 |
Reply | -0.400 |
Interstitial | -0.385 |
mans | -0.375 |
lers | -0.366 |
Token | for |
Token ID | 329 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
Russ | +0.672 |
Dems | +0.657 |
oit | +0.654 |
andre | +0.614 |
jamin | +0.610 |
Neg logit contributions | |
warr | -0.617 |
Reply | -0.578 |
Interstitial | -0.559 |
mans | -0.528 |
lers | -0.513 |
Token | its |
Token ID | 663 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Russ | +0.216 |
Dems | +0.211 |
oit | +0.210 |
andre | +0.196 |
jamin | +0.194 |
Neg logit contributions | |
warr | -0.225 |
Reply | -0.213 |
Interstitial | -0.205 |
mans | -0.198 |
lers | -0.192 |
Token | return |
Token ID | 1441 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
warr | +0.515 |
Reply | +0.487 |
Interstitial | +0.467 |
mans | +0.454 |
lers | +0.442 |
Neg logit contributions | |
Russ | -0.470 |
oit | -0.455 |
Dems | -0.455 |
andre | -0.425 |
jamin | -0.422 |
Token | to |
Token ID | 284 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
warr | +0.419 |
Reply | +0.395 |
Interstitial | +0.377 |
mans | +0.364 |
lers | +0.354 |
Neg logit contributions | |
Russ | -0.477 |
Dems | -0.463 |
oit | -0.462 |
andre | -0.435 |
jamin | -0.432 |
Token | approve |
Token ID | 14762 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
Russ | +0.243 |
Dems | +0.237 |
oit | +0.236 |
andre | +0.219 |
jamin | +0.218 |
Neg logit contributions | |
warr | -0.275 |
Reply | -0.260 |
Interstitial | -0.250 |
mans | -0.242 |
lers | -0.236 |
Token | spending |
Token ID | 4581 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
warr | +0.117 |
Reply | +0.110 |
Interstitial | +0.106 |
mans | +0.103 |
lers | +0.100 |
Neg logit contributions | |
Russ | -0.110 |
Dems | -0.107 |
oit | -0.107 |
andre | -0.100 |
jamin | -0.099 |
Token | measures |
Token ID | 5260 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
warr | +0.184 |
Reply | +0.172 |
Interstitial | +0.164 |
mans | +0.158 |
lers | +0.153 |
Neg logit contributions | |
Russ | -0.227 |
Dems | -0.222 |
oit | -0.221 |
andre | -0.208 |
jamin | -0.207 |
Token | to |
Token ID | 284 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
warr | +1.472 |
Reply | +1.386 |
Interstitial | +1.320 |
mans | +1.278 |
lers | +1.241 |
Neg logit contributions | |
Russ | -1.660 |
Dems | -1.619 |
oit | -1.616 |
andre | -1.518 |
jamin | -1.506 |
Token | keep |
Token ID | 1394 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Russ | +0.383 |
Dems | +0.376 |
oit | +0.373 |
andre | +0.349 |
jamin | +0.347 |
Neg logit contributions | |
warr | -0.345 |
Reply | -0.325 |
Interstitial | -0.310 |
mans | -0.299 |
lers | -0.290 |
Token | the |
Token ID | 262 |
Feature activation | +8.10e-03 |
Pos logit contributions | |
warr | +1.711 |
Reply | +1.611 |
Interstitial | +1.536 |
mans | +1.504 |
lers | +1.472 |
Neg logit contributions | |
Russ | -1.686 |
oit | -1.645 |
Dems | -1.621 |
andre | -1.537 |
jamin | -1.509 |
Token | government |
Token ID | 1230 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
warr | +0.012 |
Reply | +0.011 |
Interstitial | +0.011 |
mans | +0.010 |
lers | +0.010 |
Neg logit contributions | |
Russ | -0.010 |
Dems | -0.010 |
oit | -0.010 |
andre | -0.009 |
jamin | -0.009 |
Token | open |
Token ID | 1280 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Russ | +1.151 |
Dems | +1.139 |
oit | +1.122 |
andre | +1.043 |
jamin | +1.038 |
Neg logit contributions | |
warr | -1.382 |
Reply | -1.314 |
Interstitial | -1.266 |
mans | -1.217 |
lers | -1.187 |
Token | because |
Token ID | 780 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
warr | +1.325 |
Reply | +1.243 |
Interstitial | +1.183 |
mans | +1.142 |
lers | +1.107 |
Neg logit contributions | |
Russ | -1.625 |
Dems | -1.587 |
oit | -1.583 |
andre | -1.490 |
jamin | -1.480 |
Token | of |
Token ID | 286 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
Russ | +0.820 |
Dems | +0.803 |
oit | +0.794 |
andre | +0.735 |
jamin | +0.732 |
Neg logit contributions | |
warr | -0.873 |
Reply | -0.828 |
Interstitial | -0.800 |
mans | -0.766 |
lers | -0.743 |
Token | the |
Token ID | 262 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
warr | +0.112 |
Reply | +0.106 |
Interstitial | +0.102 |
mans | +0.099 |
lers | +0.096 |
Neg logit contributions | |
Russ | -0.103 |
Dems | -0.101 |
oit | -0.101 |
andre | -0.094 |
jamin | -0.093 |
Token | faster |
Token ID | 5443 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Russ | +0.305 |
Dems | +0.297 |
oit | +0.297 |
andre | +0.276 |
jamin | +0.274 |
Neg logit contributions | |
warr | -0.311 |
Reply | -0.295 |
Interstitial | -0.284 |
mans | -0.273 |
lers | -0.266 |
Token | approach |
Token ID | 3164 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
warr | +1.523 |
Reply | +1.435 |
Interstitial | +1.363 |
mans | +1.328 |
lers | +1.289 |
Neg logit contributions | |
Russ | -1.647 |
Dems | -1.600 |
oit | -1.594 |
andre | -1.501 |
jamin | -1.488 |
Token | speeds |
Token ID | 12055 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
warr | +0.506 |
Reply | +0.472 |
Interstitial | +0.448 |
mans | +0.431 |
lers | +0.417 |
Neg logit contributions | |
Russ | -0.694 |
Dems | -0.678 |
oit | -0.676 |
andre | -0.639 |
jamin | -0.635 |
Token | ; |
Token ID | 26 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
warr | +0.811 |
Reply | +0.764 |
Interstitial | +0.731 |
mans | +0.706 |
lers | +0.686 |
Neg logit contributions | |
Russ | -0.873 |
Dems | -0.853 |
oit | -0.851 |
andre | -0.797 |
jamin | -0.791 |
Token | additionally |
Token ID | 36527 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Russ | +0.222 |
Dems | +0.216 |
oit | +0.215 |
andre | +0.201 |
jamin | +0.199 |
Neg logit contributions | |
warr | -0.226 |
Reply | -0.214 |
Interstitial | -0.206 |
mans | -0.198 |
lers | -0.193 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Russ | +0.166 |
Dems | +0.162 |
oit | +0.161 |
andre | +0.152 |
jamin | +0.150 |
Neg logit contributions | |
warr | -0.142 |
Reply | -0.134 |
Interstitial | -0.127 |
mans | -0.123 |
lers | -0.119 |
Token | I |
Token ID | 314 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Russ | +0.166 |
Dems | +0.162 |
oit | +0.161 |
andre | +0.150 |
jamin | +0.149 |
Neg logit contributions | |
warr | -0.167 |
Reply | -0.159 |
Interstitial | -0.153 |
mans | -0.147 |
lers | -0.142 |
Token | had |
Token ID | 550 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
warr | +0.145 |
Reply | +0.136 |
Interstitial | +0.130 |
mans | +0.125 |
lers | +0.122 |
Neg logit contributions | |
Russ | -0.158 |
Dems | -0.154 |
oit | -0.154 |
andre | -0.144 |
jamin | -0.143 |
Token | 98 |
Token ID | 4089 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
warr | +0.279 |
Reply | +0.259 |
Interstitial | +0.247 |
mans | +0.237 |
lers | +0.229 |
Neg logit contributions | |
Russ | -0.354 |
oit | -0.347 |
Dems | -0.346 |
andre | -0.327 |
jamin | -0.324 |
Token | b |
Token ID | 65 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Russ | +0.337 |
oit | +0.332 |
Dems | +0.329 |
andre | +0.312 |
jamin | +0.309 |
Neg logit contributions | |
warr | -0.276 |
Reply | -0.255 |
Interstitial | -0.244 |
mans | -0.232 |
lers | -0.225 |
Token | 63 |
Token ID | 5066 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
warr | +1.396 |
Reply | +1.309 |
Interstitial | +1.243 |
mans | +1.198 |
lers | +1.160 |
Neg logit contributions | |
Russ | -1.821 |
Dems | -1.780 |
oit | -1.776 |
andre | -1.673 |
jamin | -1.662 |
Token | e |
Token ID | 68 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
warr | +0.258 |
Reply | +0.241 |
Interstitial | +0.230 |
mans | +0.221 |
lers | +0.215 |
Neg logit contributions | |
Russ | -0.308 |
oit | -0.301 |
Dems | -0.301 |
andre | -0.283 |
jamin | -0.281 |
Token | 15 |
Token ID | 1314 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Russ | +0.507 |
oit | +0.499 |
Dems | +0.495 |
andre | +0.470 |
jamin | +0.465 |
Neg logit contributions | |
warr | -0.403 |
Reply | -0.372 |
Interstitial | -0.356 |
mans | -0.340 |
lers | -0.329 |
Token | bb |
Token ID | 11848 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
warr | +0.483 |
Reply | +0.451 |
Interstitial | +0.430 |
mans | +0.413 |
lers | +0.401 |
Neg logit contributions | |
Russ | -0.592 |
oit | -0.579 |
Dems | -0.579 |
andre | -0.544 |
jamin | -0.540 |
Token | 57 |
Token ID | 3553 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
warr | +2.273 |
Reply | +2.153 |
Interstitial | +2.038 |
mans | +1.978 |
lers | +1.918 |
Neg logit contributions | |
Russ | -3.039 |
Dems | -2.966 |
oit | -2.944 |
andre | -2.781 |
jamin | -2.763 |
Token | e |
Token ID | 68 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
warr | +0.128 |
Reply | +0.119 |
Interstitial | +0.114 |
mans | +0.109 |
lers | +0.106 |
Neg logit contributions | |
Russ | -0.157 |
oit | -0.153 |
Dems | -0.153 |
andre | -0.144 |
jamin | -0.143 |
Token | 920 |
Token ID | 37128 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Russ | +0.372 |
Dems | +0.364 |
oit | +0.364 |
andre | +0.343 |
jamin | +0.340 |
Neg logit contributions | |
warr | -0.289 |
Reply | -0.268 |
Interstitial | -0.256 |
mans | -0.246 |
lers | -0.238 |
Token | a |
Token ID | 64 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
warr | +1.486 |
Reply | +1.409 |
Interstitial | +1.332 |
mans | +1.293 |
lers | +1.252 |
Neg logit contributions | |
Russ | -1.819 |
Dems | -1.772 |
oit | -1.766 |
andre | -1.665 |
jamin | -1.655 |
Token | 9 |
Token ID | 24 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
warr | +0.310 |
Reply | +0.291 |
Interstitial | +0.277 |
mans | +0.267 |
lers | +0.259 |
Neg logit contributions | |
Russ | -0.374 |
Dems | -0.365 |
oit | -0.364 |
andre | -0.343 |
jamin | -0.340 |
Token | since |
Token ID | 1201 |
Feature activation | +3.41e-03 |
Pos logit contributions | |
Russ | +0.630 |
Dems | +0.619 |
oit | +0.618 |
andre | +0.586 |
jamin | +0.582 |
Neg logit contributions | |
warr | -0.352 |
Reply | -0.324 |
Interstitial | -0.305 |
mans | -0.290 |
lers | -0.278 |
Token | I |
Token ID | 314 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
warr | +0.005 |
Reply | +0.005 |
Interstitial | +0.005 |
mans | +0.005 |
lers | +0.004 |
Neg logit contributions | |
Russ | -0.004 |
Dems | -0.004 |
oit | -0.004 |
andre | -0.004 |
jamin | -0.004 |
Token | received |
Token ID | 2722 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
warr | +0.114 |
Reply | +0.106 |
Interstitial | +0.100 |
mans | +0.097 |
lers | +0.093 |
Neg logit contributions | |
Russ | -0.153 |
Dems | -0.150 |
oit | -0.149 |
andre | -0.141 |
jamin | -0.140 |
Token | the |
Token ID | 262 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
warr | +0.237 |
Reply | +0.224 |
Interstitial | +0.215 |
mans | +0.209 |
lers | +0.203 |
Neg logit contributions | |
Russ | -0.210 |
Dems | -0.205 |
oit | -0.204 |
andre | -0.190 |
jamin | -0.188 |
Token | Mel |
Token ID | 5616 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
warr | +0.227 |
Reply | +0.215 |
Interstitial | +0.206 |
mans | +0.200 |
lers | +0.195 |
Neg logit contributions | |
Russ | -0.215 |
Dems | -0.210 |
oit | -0.209 |
andre | -0.195 |
jamin | -0.193 |
Token | ch |
Token ID | 354 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
warr | +0.295 |
Reply | +0.280 |
Interstitial | +0.267 |
mans | +0.261 |
lers | +0.253 |
Neg logit contributions | |
Russ | -0.293 |
Dems | -0.285 |
oit | -0.283 |
andre | -0.264 |
jamin | -0.263 |
Token | ized |
Token ID | 1143 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
warr | +0.578 |
Reply | +0.549 |
Interstitial | +0.528 |
mans | +0.514 |
lers | +0.502 |
Neg logit contributions | |
Russ | -0.471 |
Dems | -0.457 |
oit | -0.455 |
andre | -0.421 |
jamin | -0.418 |
Token | ek |
Token ID | 988 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
Russ | +0.694 |
oit | +0.678 |
Dems | +0.673 |
andre | +0.615 |
jamin | +0.605 |
Neg logit contributions | |
warr | -1.227 |
Reply | -1.180 |
Interstitial | -1.144 |
mans | -1.105 |
lers | -1.079 |
Token | priesthood |
Token ID | 33060 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
Russ | +0.319 |
Dems | +0.312 |
oit | +0.311 |
andre | +0.292 |
jamin | +0.290 |
Neg logit contributions | |
warr | -0.293 |
Reply | -0.276 |
Interstitial | -0.264 |
mans | -0.254 |
lers | -0.247 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
warr | +0.629 |
Reply | +0.592 |
Interstitial | +0.566 |
mans | +0.547 |
lers | +0.532 |
Neg logit contributions | |
Russ | -0.683 |
Dems | -0.667 |
oit | -0.665 |
andre | -0.623 |
jamin | -0.619 |
Token | and |
Token ID | 290 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
warr | +0.137 |
Reply | +0.130 |
Interstitial | +0.124 |
mans | +0.120 |
lers | +0.117 |
Neg logit contributions | |
Russ | -0.136 |
Dems | -0.132 |
oit | -0.132 |
andre | -0.123 |
jamin | -0.122 |
Token | ster |
Token ID | 1706 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
Russ | +0.369 |
Dems | +0.359 |
oit | +0.359 |
andre | +0.335 |
jamin | +0.332 |
Neg logit contributions | |
warr | -0.377 |
Reply | -0.356 |
Interstitial | -0.342 |
mans | -0.330 |
lers | -0.321 |
Token | ," |
Token ID | 553 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
Russ | +1.139 |
Dems | +1.113 |
oit | +1.110 |
andre | +1.030 |
jamin | +1.025 |
Neg logit contributions | |
warr | -1.224 |
Reply | -1.157 |
Interstitial | -1.109 |
mans | -1.067 |
lers | -1.042 |
Token | from |
Token ID | 422 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Russ | +0.526 |
Dems | +0.513 |
oit | +0.510 |
andre | +0.478 |
jamin | +0.474 |
Neg logit contributions | |
warr | -0.511 |
Reply | -0.481 |
Interstitial | -0.459 |
mans | -0.443 |
lers | -0.430 |
Token | 1971 |
Token ID | 16382 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Russ | +0.281 |
Dems | +0.274 |
oit | +0.273 |
andre | +0.255 |
jamin | +0.253 |
Neg logit contributions | |
warr | -0.292 |
Reply | -0.276 |
Interstitial | -0.265 |
mans | -0.256 |
lers | -0.249 |
Token | 's |
Token ID | 338 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
warr | +2.419 |
Reply | +2.270 |
Interstitial | +2.159 |
mans | +2.106 |
lers | +2.049 |
Neg logit contributions | |
Russ | -2.773 |
oit | -2.710 |
Dems | -2.693 |
andre | -2.546 |
jamin | -2.520 |
Token | Electric |
Token ID | 13944 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
warr | +1.950 |
Reply | +1.843 |
Interstitial | +1.765 |
mans | +1.717 |
lers | +1.675 |
Neg logit contributions | |
Russ | -1.806 |
oit | -1.757 |
Dems | -1.755 |
andre | -1.639 |
jamin | -1.629 |
Token | Warrior |
Token ID | 14019 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
warr | +0.913 |
Reply | +0.865 |
Interstitial | +0.830 |
mans | +0.809 |
lers | +0.787 |
Neg logit contributions | |
Russ | -0.885 |
oit | -0.858 |
Dems | -0.858 |
andre | -0.803 |
jamin | -0.799 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
warr | +1.055 |
Reply | +0.997 |
Interstitial | +0.952 |
mans | +0.920 |
lers | +0.893 |
Neg logit contributions | |
Russ | -1.188 |
oit | -1.159 |
Dems | -1.157 |
andre | -1.088 |
jamin | -1.080 |
Token | Not |
Token ID | 1892 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
warr | +0.419 |
Reply | +0.399 |
Interstitial | +0.382 |
mans | +0.371 |
lers | +0.361 |
Neg logit contributions | |
Russ | -0.380 |
oit | -0.370 |
Dems | -0.370 |
andre | -0.345 |
jamin | -0.341 |
Token | metal |
Token ID | 6147 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
warr | +0.351 |
Reply | +0.332 |
Interstitial | +0.317 |
mans | +0.308 |
lers | +0.300 |
Neg logit contributions | |
Russ | -0.348 |
Dems | -0.340 |
oit | -0.339 |
andre | -0.316 |
jamin | -0.314 |
Token | but |
Token ID | 475 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
warr | +0.591 |
Reply | +0.556 |
Interstitial | +0.531 |
mans | +0.514 |
lers | +0.499 |
Neg logit contributions | |
Russ | -0.669 |
Dems | -0.653 |
oit | -0.652 |
andre | -0.612 |
jamin | -0.608 |
Token | M |
Token ID | 44 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
warr | +0.634 |
Reply | +0.591 |
Interstitial | +0.566 |
mans | +0.547 |
lers | +0.532 |
Neg logit contributions | |
Russ | -0.696 |
Dems | -0.676 |
oit | -0.676 |
andre | -0.633 |
jamin | -0.629 |
Token | mmm |
Token ID | 27532 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Russ | +0.811 |
Dems | +0.793 |
oit | +0.791 |
andre | +0.745 |
jamin | +0.740 |
Neg logit contributions | |
warr | -0.644 |
Reply | -0.604 |
Interstitial | -0.575 |
mans | -0.553 |
lers | -0.536 |
Token | …" |
Token ID | 9962 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Russ | +0.167 |
oit | +0.163 |
Dems | +0.163 |
andre | +0.153 |
jamin | +0.152 |
Neg logit contributions | |
warr | -0.157 |
Reply | -0.147 |
Interstitial | -0.142 |
mans | -0.136 |
lers | -0.132 |
Token | I |
Token ID | 314 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
Russ | +2.320 |
Dems | +2.268 |
oit | +2.251 |
andre | +2.088 |
jamin | +2.087 |
Neg logit contributions | |
warr | -2.751 |
Reply | -2.596 |
Interstitial | -2.508 |
mans | -2.424 |
lers | -2.366 |
Token | moan |
Token ID | 44567 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
warr | +0.695 |
Reply | +0.658 |
Interstitial | +0.631 |
mans | +0.611 |
lers | +0.596 |
Neg logit contributions | |
Russ | -0.647 |
Dems | -0.630 |
oit | -0.628 |
andre | -0.586 |
jamin | -0.581 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
warr | +0.058 |
Reply | +0.055 |
Interstitial | +0.053 |
mans | +0.051 |
lers | +0.049 |
Neg logit contributions | |
Russ | -0.064 |
Dems | -0.062 |
oit | -0.062 |
andre | -0.058 |
jamin | -0.058 |
Token | She |
Token ID | 1375 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
warr | +0.185 |
Reply | +0.176 |
Interstitial | +0.169 |
mans | +0.164 |
lers | +0.160 |
Neg logit contributions | |
Russ | -0.157 |
Dems | -0.153 |
oit | -0.153 |
andre | -0.142 |
jamin | -0.140 |
Token | pulls |
Token ID | 16194 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
warr | +0.032 |
Reply | +0.030 |
Interstitial | +0.029 |
mans | +0.027 |
lers | +0.027 |
Neg logit contributions | |
Russ | -0.034 |
Dems | -0.034 |
oit | -0.034 |
andre | -0.031 |
jamin | -0.031 |
Token | away |
Token ID | 1497 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Russ | +0.277 |
Dems | +0.270 |
oit | +0.269 |
andre | +0.249 |
jamin | +0.247 |
Neg logit contributions | |
warr | -0.337 |
Reply | -0.320 |
Interstitial | -0.307 |
mans | -0.298 |
lers | -0.291 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
warr | +2.362 |
Reply | +2.231 |
Interstitial | +2.098 |
mans | +2.041 |
lers | +1.987 |
Neg logit contributions | |
Russ | -2.950 |
oit | -2.872 |
Dems | -2.868 |
andre | -2.713 |
jamin | -2.676 |
Token | I |
Token ID | 314 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Russ | +0.163 |
Dems | +0.161 |
oit | +0.159 |
andre | +0.148 |
jamin | +0.148 |
Neg logit contributions | |
warr | -0.170 |
Reply | -0.160 |
Interstitial | -0.155 |
mans | -0.148 |
lers | -0.144 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
warr | +1.092 |
Reply | +1.032 |
Interstitial | +0.985 |
mans | +0.955 |
lers | +0.929 |
Neg logit contributions | |
Russ | -1.224 |
Dems | -1.192 |
oit | -1.185 |
andre | -1.115 |
jamin | -1.103 |
Token | California |
Token ID | 3442 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
warr | +0.316 |
Reply | +0.299 |
Interstitial | +0.287 |
mans | +0.279 |
lers | +0.272 |
Neg logit contributions | |
Russ | -0.278 |
Dems | -0.270 |
oit | -0.270 |
andre | -0.251 |
jamin | -0.248 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
warr | +0.150 |
Reply | +0.141 |
Interstitial | +0.134 |
mans | +0.129 |
lers | +0.126 |
Neg logit contributions | |
Russ | -0.183 |
Dems | -0.179 |
oit | -0.178 |
andre | -0.168 |
jamin | -0.166 |
Token | Tor |
Token ID | 4022 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
warr | +0.259 |
Reply | +0.245 |
Interstitial | +0.235 |
mans | +0.227 |
lers | +0.222 |
Neg logit contributions | |
Russ | -0.244 |
Dems | -0.237 |
oit | -0.237 |
andre | -0.221 |
jamin | -0.219 |
Token | i |
Token ID | 72 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
warr | +2.241 |
Reply | +2.134 |
Interstitial | +2.032 |
mans | +1.977 |
lers | +1.922 |
Neg logit contributions | |
Russ | -2.396 |
Dems | -2.338 |
oit | -2.325 |
andre | -2.175 |
jamin | -2.160 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
warr | +0.154 |
Reply | +0.145 |
Interstitial | +0.139 |
mans | +0.134 |
lers | +0.130 |
Neg logit contributions | |
Russ | -0.170 |
Dems | -0.166 |
oit | -0.166 |
andre | -0.156 |
jamin | -0.155 |
Token | hub |
Token ID | 12575 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
warr | +0.208 |
Reply | +0.196 |
Interstitial | +0.189 |
mans | +0.181 |
lers | +0.176 |
Neg logit contributions | |
Russ | -0.210 |
Dems | -0.205 |
oit | -0.203 |
andre | -0.190 |
jamin | -0.189 |
Token | by |
Token ID | 1525 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
warr | +0.140 |
Reply | +0.129 |
Interstitial | +0.120 |
mans | +0.115 |
lers | +0.111 |
Neg logit contributions | |
Russ | -0.264 |
Dems | -0.259 |
oit | -0.259 |
andre | -0.246 |
jamin | -0.244 |
Token | Dean |
Token ID | 11325 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Russ | +2.079 |
Dems | +2.029 |
oit | +2.022 |
andre | +1.889 |
jamin | +1.876 |
Neg logit contributions | |
warr | -2.152 |
Reply | -2.031 |
Interstitial | -1.951 |
mans | -1.876 |
lers | -1.821 |
Token | McD |
Token ID | 23394 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Russ | +2.254 |
oit | +2.205 |
Dems | +2.200 |
andre | +2.073 |
jamin | +2.057 |
Neg logit contributions | |
warr | -2.315 |
Reply | -2.189 |
Interstitial | -2.087 |
mans | -1.995 |
lers | -1.945 |
Token | ermott |
Token ID | 46187 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Russ | +0.586 |
Dems | +0.574 |
oit | +0.573 |
andre | +0.541 |
jamin | +0.538 |
Neg logit contributions | |
warr | -0.403 |
Reply | -0.375 |
Interstitial | -0.355 |
mans | -0.341 |
lers | -0.329 |
Token | � |
Token ID | 250 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Russ | +0.488 |
Dems | +0.478 |
oit | +0.476 |
andre | +0.447 |
jamin | +0.446 |
Neg logit contributions | |
warr | -0.434 |
Reply | -0.402 |
Interstitial | -0.384 |
mans | -0.374 |
lers | -0.361 |
Token | Teen |
Token ID | 45639 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Russ | +0.517 |
Dems | +0.504 |
oit | +0.502 |
andre | +0.472 |
jamin | +0.469 |
Neg logit contributions | |
warr | -0.447 |
Reply | -0.417 |
Interstitial | -0.399 |
mans | -0.385 |
lers | -0.374 |
Token | agers |
Token ID | 10321 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Russ | +1.992 |
Dems | +1.940 |
oit | +1.934 |
andre | +1.804 |
jamin | +1.788 |
Neg logit contributions | |
warr | -2.149 |
Reply | -2.034 |
Interstitial | -1.952 |
mans | -1.891 |
lers | -1.842 |
Token | are |
Token ID | 389 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
warr | +1.387 |
Reply | +1.294 |
Interstitial | +1.222 |
mans | +1.184 |
lers | +1.148 |
Neg logit contributions | |
Russ | -1.863 |
Dems | -1.823 |
oit | -1.822 |
andre | -1.718 |
jamin | -1.709 |
Token | often |
Token ID | 1690 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
warr | +0.051 |
Reply | +0.048 |
Interstitial | +0.046 |
mans | +0.045 |
lers | +0.043 |
Neg logit contributions | |
Russ | -0.053 |
Dems | -0.052 |
oit | -0.051 |
andre | -0.048 |
jamin | -0.048 |
Token | known |
Token ID | 1900 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
warr | +0.660 |
Reply | +0.622 |
Interstitial | +0.593 |
mans | +0.575 |
lers | +0.560 |
Neg logit contributions | |
Russ | -0.744 |
oit | -0.728 |
Dems | -0.727 |
andre | -0.681 |
jamin | -0.676 |
Token | for |
Token ID | 329 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
Russ | +0.339 |
Dems | +0.331 |
oit | +0.331 |
andre | +0.310 |
jamin | +0.309 |
Neg logit contributions | |
warr | -0.280 |
Reply | -0.262 |
Interstitial | -0.249 |
mans | -0.242 |
lers | -0.236 |
Token | their |
Token ID | 511 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
warr | +0.574 |
Reply | +0.539 |
Interstitial | +0.513 |
mans | +0.500 |
lers | +0.485 |
Neg logit contributions | |
Russ | -0.643 |
oit | -0.629 |
Dems | -0.627 |
andre | -0.589 |
jamin | -0.584 |
Token | lack |
Token ID | 3092 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
Russ | +0.247 |
Dems | +0.240 |
oit | +0.240 |
andre | +0.223 |
jamin | +0.221 |
Neg logit contributions | |
warr | -0.270 |
Reply | -0.255 |
Interstitial | -0.245 |
mans | -0.238 |
lers | -0.232 |
Token | of |
Token ID | 286 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
warr | +0.121 |
Reply | +0.114 |
Interstitial | +0.110 |
mans | +0.107 |
lers | +0.104 |
Neg logit contributions | |
Russ | -0.101 |
Dems | -0.098 |
oit | -0.098 |
andre | -0.091 |
jamin | -0.090 |
Token | judgment |
Token ID | 8492 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
warr | +0.184 |
Reply | +0.174 |
Interstitial | +0.167 |
mans | +0.162 |
lers | +0.158 |
Neg logit contributions | |
Russ | -0.169 |
oit | -0.164 |
Dems | -0.164 |
andre | -0.153 |
jamin | -0.151 |
Token | is |
Token ID | 318 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
warr | +0.860 |
Reply | +0.808 |
Interstitial | +0.768 |
mans | +0.745 |
lers | +0.724 |
Neg logit contributions | |
Russ | -1.006 |
Dems | -0.981 |
oit | -0.979 |
andre | -0.920 |
jamin | -0.914 |
Token | unemployed |
Token ID | 21021 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Russ | +0.590 |
Dems | +0.575 |
oit | +0.572 |
andre | +0.535 |
jamin | +0.530 |
Neg logit contributions | |
warr | -0.609 |
Reply | -0.575 |
Interstitial | -0.553 |
mans | -0.532 |
lers | -0.517 |
Token | , |
Token ID | 11 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
Russ | +2.691 |
Dems | +2.637 |
oit | +2.633 |
andre | +2.455 |
jamin | +2.440 |
Neg logit contributions | |
warr | -2.594 |
Reply | -2.447 |
Interstitial | -2.350 |
mans | -2.250 |
lers | -2.186 |
Token | starving |
Token ID | 34253 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Russ | +0.100 |
Dems | +0.098 |
oit | +0.098 |
andre | +0.091 |
jamin | +0.091 |
Neg logit contributions | |
warr | -0.098 |
Reply | -0.092 |
Interstitial | -0.088 |
mans | -0.085 |
lers | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
Russ | +2.959 |
Dems | +2.906 |
oit | +2.871 |
andre | +2.693 |
jamin | +2.659 |
Neg logit contributions | |
warr | -2.902 |
Reply | -2.726 |
Interstitial | -2.612 |
mans | -2.507 |
lers | -2.442 |
Token | and |
Token ID | 290 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Russ | +0.107 |
Dems | +0.105 |
oit | +0.104 |
andre | +0.097 |
jamin | +0.097 |
Neg logit contributions | |
warr | -0.105 |
Reply | -0.099 |
Interstitial | -0.095 |
mans | -0.092 |
lers | -0.089 |
Token | / |
Token ID | 14 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
warr | +0.203 |
Reply | +0.191 |
Interstitial | +0.183 |
mans | +0.176 |
lers | +0.171 |
Neg logit contributions | |
Russ | -0.228 |
Dems | -0.224 |
oit | -0.222 |
andre | -0.209 |
jamin | -0.207 |
Token | or |
Token ID | 273 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
Russ | +0.351 |
oit | +0.341 |
Dems | +0.339 |
andre | +0.315 |
jamin | +0.311 |
Neg logit contributions | |
warr | -0.460 |
Reply | -0.430 |
Interstitial | -0.414 |
mans | -0.402 |
lers | -0.391 |
Token | stark |
Token ID | 19278 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
warr | +1.161 |
Reply | +1.092 |
Interstitial | +1.042 |
mans | +1.011 |
lers | +0.983 |
Neg logit contributions | |
Russ | -1.272 |
oit | -1.238 |
Dems | -1.238 |
andre | -1.163 |
jamin | -1.154 |
Token | - |
Token ID | 12 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
warr | +1.844 |
Reply | +1.746 |
Interstitial | +1.665 |
mans | +1.619 |
lers | +1.584 |
Neg logit contributions | |
Russ | -2.060 |
Dems | -2.008 |
oit | -2.004 |
andre | -1.883 |
jamin | -1.872 |
Token | ra |
Token ID | 430 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
warr | +0.229 |
Reply | +0.217 |
Interstitial | +0.208 |
mans | +0.201 |
lers | +0.196 |
Neg logit contributions | |
Russ | -0.224 |
Dems | -0.219 |
oit | -0.218 |
andre | -0.204 |
jamin | -0.202 |
Token | Target |
Token ID | 12744 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Russ | +1.938 |
Dems | +1.910 |
oit | +1.887 |
andre | +1.767 |
jamin | +1.764 |
Neg logit contributions | |
warr | -1.863 |
Reply | -1.728 |
Interstitial | -1.661 |
mans | -1.612 |
lers | -1.561 |
Token | ing |
Token ID | 278 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Russ | +1.445 |
Dems | +1.411 |
oit | +1.403 |
andre | +1.302 |
jamin | +1.293 |
Neg logit contributions | |
warr | -1.731 |
Reply | -1.636 |
Interstitial | -1.574 |
mans | -1.527 |
lers | -1.487 |
Token | System |
Token ID | 4482 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Russ | +2.469 |
Dems | +2.443 |
oit | +2.417 |
andre | +2.258 |
jamin | +2.243 |
Neg logit contributions | |
warr | -2.215 |
Reply | -2.050 |
Interstitial | -1.976 |
mans | -1.902 |
lers | -1.839 |
Token | , |
Token ID | 11 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
warr | +0.341 |
Reply | +0.322 |
Interstitial | +0.308 |
mans | +0.297 |
lers | +0.289 |
Neg logit contributions | |
Russ | -0.365 |
Dems | -0.356 |
oit | -0.355 |
andre | -0.333 |
jamin | -0.330 |
Token | � |
Token ID | 447 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Russ | +0.297 |
Dems | +0.290 |
oit | +0.289 |
andre | +0.270 |
jamin | +0.268 |
Neg logit contributions | |
warr | -0.301 |
Reply | -0.285 |
Interstitial | -0.273 |
mans | -0.264 |
lers | -0.256 |
Token | � |
Token ID | 251 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
Russ | +0.754 |
Dems | +0.737 |
oit | +0.735 |
andre | +0.691 |
jamin | +0.686 |
Neg logit contributions | |
warr | -0.646 |
Reply | -0.607 |
Interstitial | -0.579 |
mans | -0.558 |
lers | -0.542 |
Token | which |
Token ID | 543 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
Russ | +1.242 |
Dems | +1.216 |
oit | +1.214 |
andre | +1.136 |
jamin | +1.127 |
Neg logit contributions | |
warr | -1.191 |
Reply | -1.120 |
Interstitial | -1.078 |
mans | -1.031 |
lers | -0.997 |
Token | tracks |
Token ID | 8339 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
warr | +0.698 |
Reply | +0.656 |
Interstitial | +0.626 |
mans | +0.604 |
lers | +0.586 |
Neg logit contributions | |
Russ | -0.820 |
Dems | -0.801 |
oit | -0.799 |
andre | -0.751 |
jamin | -0.745 |
Token | information |
Token ID | 1321 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Russ | +0.360 |
Dems | +0.352 |
oit | +0.350 |
andre | +0.327 |
jamin | +0.325 |
Neg logit contributions | |
warr | -0.361 |
Reply | -0.341 |
Interstitial | -0.326 |
mans | -0.315 |
lers | -0.307 |
Token | on |
Token ID | 319 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
Russ | +0.255 |
Dems | +0.250 |
oit | +0.249 |
andre | +0.234 |
jamin | +0.233 |
Neg logit contributions | |
warr | -0.206 |
Reply | -0.193 |
Interstitial | -0.184 |
mans | -0.177 |
lers | -0.171 |
Token | international |
Token ID | 3230 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
warr | +0.972 |
Reply | +0.918 |
Interstitial | +0.878 |
mans | +0.852 |
lers | +0.828 |
Neg logit contributions | |
Russ | -0.979 |
Dems | -0.954 |
oit | -0.953 |
andre | -0.891 |
jamin | -0.883 |
Token | ] |
Token ID | 60 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
warr | +0.168 |
Reply | +0.160 |
Interstitial | +0.152 |
mans | +0.147 |
lers | +0.143 |
Neg logit contributions | |
Russ | -0.192 |
Dems | -0.188 |
oit | -0.187 |
andre | -0.176 |
jamin | -0.174 |
Token |
|
Token ID | 198 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Russ | +0.318 |
oit | +0.309 |
Dems | +0.309 |
andre | +0.288 |
jamin | +0.285 |
Neg logit contributions | |
warr | -0.360 |
Reply | -0.342 |
Interstitial | -0.328 |
mans | -0.319 |
lers | -0.310 |
Token |
|
Token ID | 198 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
Russ | +0.646 |
Dems | +0.625 |
oit | +0.624 |
andre | +0.575 |
jamin | +0.573 |
Neg logit contributions | |
warr | -0.858 |
Reply | -0.786 |
Interstitial | -0.763 |
mans | -0.737 |
lers | -0.722 |
Token | Australia |
Token ID | 27429 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Russ | +0.750 |
Dems | +0.727 |
oit | +0.726 |
andre | +0.683 |
jamin | +0.678 |
Neg logit contributions | |
warr | -0.660 |
Reply | -0.611 |
Interstitial | -0.584 |
mans | -0.564 |
lers | -0.550 |
Token | 's |
Token ID | 338 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
Russ | +1.668 |
Dems | +1.641 |
oit | +1.629 |
andre | +1.530 |
jamin | +1.521 |
Neg logit contributions | |
warr | -1.591 |
Reply | -1.493 |
Interstitial | -1.434 |
mans | -1.379 |
lers | -1.346 |
Token | electoral |
Token ID | 13901 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
warr | +0.950 |
Reply | +0.902 |
Interstitial | +0.869 |
mans | +0.845 |
lers | +0.824 |
Neg logit contributions | |
Russ | -0.748 |
oit | -0.724 |
Dems | -0.722 |
andre | -0.670 |
jamin | -0.663 |
Token | system |
Token ID | 1080 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Russ | +3.058 |
Dems | +3.017 |
oit | +2.981 |
andre | +2.785 |
jamin | +2.754 |
Neg logit contributions | |
warr | -3.384 |
Reply | -3.196 |
Interstitial | -3.087 |
mans | -2.985 |
lers | -2.911 |
Token | uses |
Token ID | 3544 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Russ | +0.242 |
Dems | +0.238 |
oit | +0.237 |
andre | +0.223 |
jamin | +0.221 |
Neg logit contributions | |
warr | -0.214 |
Reply | -0.201 |
Interstitial | -0.192 |
mans | -0.184 |
lers | -0.179 |
Token | preferential |
Token ID | 47136 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Russ | +0.723 |
Dems | +0.701 |
oit | +0.701 |
andre | +0.651 |
jamin | +0.646 |
Neg logit contributions | |
warr | -0.829 |
Reply | -0.786 |
Interstitial | -0.754 |
mans | -0.733 |
lers | -0.714 |
Token | voting |
Token ID | 6709 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
warr | +0.542 |
Reply | +0.519 |
Interstitial | +0.496 |
mans | +0.487 |
lers | +0.475 |
Neg logit contributions | |
Russ | -0.381 |
oit | -0.368 |
Dems | -0.366 |
andre | -0.339 |
jamin | -0.334 |
Token | for |
Token ID | 329 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Dems | +4.098 |
Russ | +4.090 |
oit | +4.005 |
andre | +3.740 |
jamin | +3.692 |
Neg logit contributions | |
warr | -4.024 |
Reply | -3.803 |
Interstitial | -3.694 |
mans | -3.472 |
lers | -3.412 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
warr | +0.216 |
Reply | +0.205 |
Interstitial | +0.197 |
mans | +0.191 |
lers | +0.186 |
Neg logit contributions | |
Russ | -0.192 |
Dems | -0.186 |
oit | -0.186 |
andre | -0.173 |
jamin | -0.172 |
Token |
|
Token ID | 198 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Russ | +0.250 |
Dems | +0.243 |
oit | +0.243 |
andre | +0.224 |
jamin | +0.223 |
Neg logit contributions | |
warr | -0.314 |
Reply | -0.294 |
Interstitial | -0.284 |
mans | -0.275 |
lers | -0.268 |
Token | Figure |
Token ID | 11337 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
Russ | +0.351 |
Dems | +0.343 |
oit | +0.342 |
andre | +0.322 |
jamin | +0.320 |
Neg logit contributions | |
warr | -0.283 |
Reply | -0.263 |
Interstitial | -0.251 |
mans | -0.242 |
lers | -0.235 |
Token | 1 |
Token ID | 352 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
warr | +1.071 |
Reply | +1.020 |
Interstitial | +0.973 |
mans | +0.951 |
lers | +0.925 |
Neg logit contributions | |
Russ | -0.956 |
oit | -0.928 |
Dems | -0.928 |
andre | -0.865 |
jamin | -0.858 |
Token | : |
Token ID | 25 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
Russ | +0.380 |
Dems | +0.370 |
oit | +0.369 |
andre | +0.344 |
jamin | +0.341 |
Neg logit contributions | |
warr | -0.399 |
Reply | -0.377 |
Interstitial | -0.361 |
mans | -0.350 |
lers | -0.341 |
Token | Drill |
Token ID | 46350 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
Russ | +0.458 |
Dems | +0.447 |
oit | +0.444 |
andre | +0.414 |
jamin | +0.411 |
Neg logit contributions | |
warr | -0.495 |
Reply | -0.468 |
Interstitial | -0.449 |
mans | -0.435 |
lers | -0.424 |
Token | through |
Token ID | 832 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Russ | +3.935 |
Dems | +3.848 |
oit | +3.833 |
andre | +3.517 |
jamin | +3.516 |
Neg logit contributions | |
warr | -4.715 |
Reply | -4.443 |
Interstitial | -4.282 |
mans | -4.135 |
lers | -4.020 |
Token | capability |
Token ID | 12971 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
warr | +0.181 |
Reply | +0.171 |
Interstitial | +0.164 |
mans | +0.159 |
lers | +0.155 |
Neg logit contributions | |
Russ | -0.175 |
Dems | -0.170 |
oit | -0.170 |
andre | -0.159 |
jamin | -0.158 |
Token | example |
Token ID | 1672 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Russ | +1.431 |
Dems | +1.406 |
oit | +1.397 |
andre | +1.308 |
jamin | +1.296 |
Neg logit contributions | |
warr | -1.335 |
Reply | -1.255 |
Interstitial | -1.205 |
mans | -1.163 |
lers | -1.127 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Russ | +0.534 |
Dems | +0.523 |
oit | +0.520 |
andre | +0.486 |
jamin | +0.482 |
Neg logit contributions | |
warr | -0.532 |
Reply | -0.502 |
Interstitial | -0.482 |
mans | -0.466 |
lers | -0.453 |
Token |
|
Token ID | 198 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
warr | +0.318 |
Reply | +0.302 |
Interstitial | +0.290 |
mans | +0.282 |
lers | +0.275 |
Neg logit contributions | |
Russ | -0.264 |
Dems | -0.257 |
oit | -0.256 |
andre | -0.238 |
jamin | -0.236 |
Token |
|
Token ID | 198 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
Russ | +0.497 |
Dems | +0.484 |
oit | +0.482 |
andre | +0.448 |
jamin | +0.444 |
Neg logit contributions | |
warr | -0.565 |
Reply | -0.533 |
Interstitial | -0.512 |
mans | -0.497 |
lers | -0.485 |
Token |
|
Token ID | 198 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
Russ | +0.787 |
Dems | +0.763 |
oit | +0.762 |
andre | +0.702 |
jamin | +0.701 |
Neg logit contributions | |
warr | -1.045 |
Reply | -0.961 |
Interstitial | -0.931 |
mans | -0.899 |
lers | -0.879 |
Token | The |
Token ID | 464 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Russ | +0.969 |
oit | +0.937 |
Dems | +0.932 |
andre | +0.884 |
jamin | +0.871 |
Neg logit contributions | |
warr | -0.843 |
Reply | -0.769 |
Interstitial | -0.737 |
mans | -0.713 |
lers | -0.694 |
Token | integrated |
Token ID | 11521 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
warr | +0.277 |
Reply | +0.262 |
Interstitial | +0.251 |
mans | +0.243 |
lers | +0.237 |
Neg logit contributions | |
Russ | -0.254 |
Dems | -0.247 |
oit | -0.247 |
andre | -0.230 |
jamin | -0.228 |
Token | Lean |
Token ID | 45661 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Russ | +0.475 |
oit | +0.463 |
Dems | +0.462 |
andre | +0.431 |
jamin | +0.426 |
Neg logit contributions | |
warr | -0.534 |
Reply | -0.505 |
Interstitial | -0.487 |
mans | -0.469 |
lers | -0.457 |
Token | Six |
Token ID | 9699 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
Russ | +1.991 |
oit | +1.947 |
Dems | +1.947 |
andre | +1.819 |
jamin | +1.797 |
Neg logit contributions | |
warr | -2.036 |
Reply | -1.920 |
Interstitial | -1.847 |
mans | -1.770 |
lers | -1.727 |
Token | Sigma |
Token ID | 31669 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Russ | +3.450 |
oit | +3.378 |
Dems | +3.365 |
jamin | +3.141 |
andre | +3.139 |
Neg logit contributions | |
warr | -3.359 |
Reply | -3.181 |
Interstitial | -3.076 |
mans | -2.901 |
lers | -2.848 |
Token | management |
Token ID | 4542 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
Russ | +2.853 |
oit | +2.815 |
Dems | +2.814 |
andre | +2.634 |
jamin | +2.585 |
Neg logit contributions | |
warr | -2.803 |
Reply | -2.647 |
Interstitial | -2.565 |
mans | -2.438 |
lers | -2.377 |
Token | approach |
Token ID | 3164 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Russ | +0.669 |
Dems | +0.654 |
oit | +0.653 |
andre | +0.614 |
jamin | +0.608 |
Neg logit contributions | |
warr | -0.570 |
Reply | -0.535 |
Interstitial | -0.513 |
mans | -0.491 |
lers | -0.477 |
Token | is |
Token ID | 318 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
warr | +0.392 |
Reply | +0.368 |
Interstitial | +0.352 |
mans | +0.338 |
lers | +0.328 |
Neg logit contributions | |
Russ | -0.459 |
Dems | -0.449 |
oit | -0.448 |
andre | -0.422 |
jamin | -0.418 |
Token | being |
Token ID | 852 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
Russ | +0.346 |
Dems | +0.338 |
oit | +0.337 |
andre | +0.316 |
jamin | +0.313 |
Neg logit contributions | |
warr | -0.323 |
Reply | -0.304 |
Interstitial | -0.291 |
mans | -0.281 |
lers | -0.273 |
Token | The |
Token ID | 383 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
Russ | +0.222 |
Dems | +0.216 |
oit | +0.216 |
andre | +0.201 |
jamin | +0.199 |
Neg logit contributions | |
warr | -0.251 |
Reply | -0.238 |
Interstitial | -0.228 |
mans | -0.222 |
lers | -0.216 |
Token | teacher |
Token ID | 4701 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
warr | +0.755 |
Reply | +0.716 |
Interstitial | +0.688 |
mans | +0.668 |
lers | +0.651 |
Neg logit contributions | |
Russ | -0.639 |
Dems | -0.622 |
oit | -0.620 |
andre | -0.576 |
jamin | -0.571 |
Token | allegedly |
Token ID | 7910 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Russ | +1.399 |
Dems | +1.382 |
oit | +1.365 |
andre | +1.277 |
jamin | +1.268 |
Neg logit contributions | |
warr | -1.303 |
Reply | -1.230 |
Interstitial | -1.182 |
mans | -1.123 |
lers | -1.092 |
Token | claimed |
Token ID | 4752 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Russ | +2.022 |
Dems | +2.003 |
oit | +1.984 |
andre | +1.864 |
jamin | +1.847 |
Neg logit contributions | |
warr | -1.741 |
Reply | -1.639 |
Interstitial | -1.573 |
mans | -1.491 |
lers | -1.439 |
Token | that |
Token ID | 326 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
Russ | +1.522 |
Dems | +1.492 |
oit | +1.484 |
andre | +1.383 |
jamin | +1.368 |
Neg logit contributions | |
warr | -1.561 |
Reply | -1.476 |
Interstitial | -1.413 |
mans | -1.366 |
lers | -1.322 |
Token | President |
Token ID | 1992 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Russ | +0.063 |
Dems | +0.061 |
oit | +0.061 |
andre | +0.057 |
jamin | +0.056 |
Neg logit contributions | |
warr | -0.066 |
Reply | -0.063 |
Interstitial | -0.060 |
mans | -0.058 |
lers | -0.057 |
Token | Obama |
Token ID | 2486 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Russ | +2.302 |
Dems | +2.242 |
oit | +2.215 |
andre | +2.028 |
jamin | +2.017 |
Neg logit contributions | |
warr | -3.775 |
Reply | -3.613 |
Interstitial | -3.489 |
mans | -3.368 |
lers | -3.292 |
Token | is |
Token ID | 318 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
Russ | +2.521 |
Dems | +2.492 |
oit | +2.459 |
andre | +2.313 |
jamin | +2.293 |
Neg logit contributions | |
warr | -2.327 |
Reply | -2.175 |
Interstitial | -2.086 |
mans | -2.001 |
lers | -1.934 |
Token | not |
Token ID | 407 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Russ | +0.855 |
Dems | +0.839 |
oit | +0.829 |
andre | +0.774 |
jamin | +0.766 |
Neg logit contributions | |
warr | -0.981 |
Reply | -0.926 |
Interstitial | -0.890 |
mans | -0.862 |
lers | -0.838 |
Token | a |
Token ID | 257 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
warr | +0.433 |
Reply | +0.409 |
Interstitial | +0.393 |
mans | +0.380 |
lers | +0.370 |
Neg logit contributions | |
Russ | -0.396 |
Dems | -0.387 |
oit | -0.385 |
andre | -0.359 |
jamin | -0.357 |
Token | Christian |
Token ID | 4302 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
Russ | +0.086 |
Dems | +0.083 |
oit | +0.083 |
andre | +0.076 |
jamin | +0.075 |
Neg logit contributions | |
warr | -0.118 |
Reply | -0.112 |
Interstitial | -0.108 |
mans | -0.105 |
lers | -0.103 |
Token | elson |
Token ID | 10151 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
warr | +0.790 |
Reply | +0.759 |
Interstitial | +0.737 |
mans | +0.720 |
lers | +0.707 |
Neg logit contributions | |
Russ | -0.294 |
Dems | -0.280 |
oit | -0.279 |
andre | -0.244 |
jamin | -0.240 |
Token | - |
Token ID | 12 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
warr | +2.048 |
Reply | +1.950 |
Interstitial | +1.839 |
mans | +1.820 |
lers | +1.750 |
Neg logit contributions | |
Russ | -2.286 |
oit | -2.248 |
Dems | -2.186 |
andre | -2.112 |
jamin | -2.080 |
Token | funded |
Token ID | 18246 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
warr | +0.247 |
Reply | +0.236 |
Interstitial | +0.226 |
mans | +0.220 |
lers | +0.215 |
Neg logit contributions | |
Russ | -0.213 |
Dems | -0.208 |
oit | -0.208 |
andre | -0.193 |
jamin | -0.191 |
Token | Washington |
Token ID | 2669 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Russ | +1.420 |
Dems | +1.400 |
oit | +1.380 |
andre | +1.276 |
jamin | +1.266 |
Neg logit contributions | |
warr | -1.721 |
Reply | -1.630 |
Interstitial | -1.578 |
mans | -1.524 |
lers | -1.481 |
Token | Free |
Token ID | 3232 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
Russ | +1.219 |
Dems | +1.187 |
oit | +1.182 |
andre | +1.097 |
jamin | +1.087 |
Neg logit contributions | |
warr | -1.472 |
Reply | -1.396 |
Interstitial | -1.342 |
mans | -1.303 |
lers | -1.271 |
Token | Beacon |
Token ID | 29729 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
warr | +0.650 |
Reply | +0.618 |
Interstitial | +0.592 |
mans | +0.576 |
lers | +0.559 |
Neg logit contributions | |
Russ | -0.640 |
oit | -0.624 |
Dems | -0.620 |
andre | -0.585 |
jamin | -0.579 |
Token | leading |
Token ID | 3756 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Russ | +3.223 |
Dems | +3.174 |
oit | +3.116 |
jamin | +2.925 |
andre | +2.913 |
Neg logit contributions | |
warr | -3.095 |
Reply | -2.904 |
Interstitial | -2.810 |
mans | -2.663 |
lers | -2.587 |
Token | the |
Token ID | 262 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Russ | +0.636 |
oit | +0.618 |
Dems | +0.617 |
andre | +0.576 |
jamin | +0.571 |
Neg logit contributions | |
warr | -0.671 |
Reply | -0.634 |
Interstitial | -0.607 |
mans | -0.589 |
lers | -0.575 |
Token | charge |
Token ID | 3877 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Russ | +0.255 |
oit | +0.246 |
Dems | +0.245 |
andre | +0.226 |
jamin | +0.224 |
Neg logit contributions | |
warr | -0.383 |
Reply | -0.365 |
Interstitial | -0.351 |
mans | -0.343 |
lers | -0.335 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
warr | +0.371 |
Reply | +0.351 |
Interstitial | +0.332 |
mans | +0.323 |
lers | +0.314 |
Neg logit contributions | |
Russ | -0.446 |
oit | -0.435 |
Dems | -0.434 |
andre | -0.408 |
jamin | -0.406 |
Token | this |
Token ID | 428 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
Russ | +0.311 |
Dems | +0.303 |
oit | +0.302 |
andre | +0.282 |
jamin | +0.280 |
Neg logit contributions | |
warr | -0.331 |
Reply | -0.313 |
Interstitial | -0.300 |
mans | -0.291 |
lers | -0.283 |