TOP ACTIVATIONS
MAX = 1.294

issue informal guidance and policy memor anda intended to help minority
* - 6 Sean Con nery films , 1962 - 1971
atch a blue - painted box before it touches the ground
text or empty Example : /* vim : set a i
{ 1 , 6 } < -> { 1 , 7
{{ 1 , 6 } < -> { 1 , 6
Oh , and forget about memor izing times tables or mastering
, books , and other memor abilia . About
with former Cuban President Fidel Castro , Cuban dissidents who advocate
dens er than zinc sulf ate , the zinc solution floated
The Dice Tower http :// www . board game
[[ # , 1 ]] < -> graph List [[ #
Ru iz , who had memor ized all of the winners
{ 1 , 6 } < -> { 1 , 7
added . Because copper sulf ate is dens er than zinc
in the background , Survivor memor abilia throughout the queue and
the name a teenage boy memor ably gives his penis in
/ 10 " http :// the hook journal .
{ 1 , 6 } < -> { 2 , 6
distinct flavor and slightly green color and is easier to make

MIN ACTIVATIONS
MIN = -1.328

joke , and the steep incl ines can be treacherous with
a 1 , 000 ft incl ine over 1 . 3
equivalent of an Olympic gymn astics routine for the speaker
quickly came to a steep incl ine at mile 16 .
year was last year ," Stevens said . " I don
resemble symptoms of schizophrenia called derail ment and delusion . In
C elt ics coach Brad Stevens isn 't sure if any
Pennsylvania 's Th add eus Stevens , who represented the mining
www . bel fast te legraph . co . uk /
House of Representatives ( the lower house ) has 150 members
basketball won out . A court was set up , concrete
goals or hitting cross - court winners when a child .
: 13 PH OTOS Donald Trump 's potential running
www . bel fast te legraph . co . uk /
and ore refinement machinery , Stevens related , and it was
the prime challenge Belfast Te legraph . co . uk Dis
like public izing mar ath ons to promote j ogging
well . Con clusions Arthur Sch open
ends stand over an empty court . The goals
played on a half - court in the yard , with

INTERVAL 0.638 - 1.294
CONTAINS 0.352%

Pre y https :// kill ert of ure c
You can pick a maths teacher , a mental capacity
DPR Korea lose their last match against the Philippines in Manila
address of system ] | < -- stack pointer + --------------------
technology : https :// www . eff . org

INTERVAL -0.017 - 0.638
CONTAINS 55.667%

he 's notorious about stealing players from other team such as
: Carly Fiorina 's political career Fiorina speaks during a forum
and Every Time the Sun Comes Up
video that I have never seen or does not exist .
and white ? Although the color of the device has a

INTERVAL -0.673 - -0.017
CONTAINS 43.726%

and two touchdowns through the air . Per Football Outs iders
ured loans . The three men own five additional Kh ark
who was following her upstairs , got crushed under her weight
sp ark ed even more anger . Two
knew from the start I could never become Na of umi

INTERVAL -1.328 - -0.673
CONTAINS 0.255%

s Event Qu ests and
C ute video Aj it Aren
for tuition and boasts a high success rate in getting its
has a fo os ball table , and it saw action
tools provided to gather inf erences and observations on the team
Token issue
Token ID2071
Feature activation-2.31e-01

Pos logit contributions
 AST+0.099
elaide+0.095
igree+0.094
ovember+0.093
outh+0.093
Neg logit contributions
wash-0.124
-0.122
pak-0.116
gross-0.113
kat-0.113
Token informal
Token ID22176
Feature activation-1.87e-01

Pos logit contributions
 AST+0.376
elaide+0.356
igree+0.352
outh+0.352
ovember+0.349
Neg logit contributions
wash-0.459
-0.453
pak-0.431
kat-0.421
gross-0.419
Token guidance
Token ID11154
Feature activation+1.30e-01

Pos logit contributions
 AST+0.312
elaide+0.298
igree+0.294
outh+0.294
ovember+0.292
Neg logit contributions
wash-0.361
-0.357
pak-0.339
kat-0.330
gross-0.329
Token and
Token ID290
Feature activation-1.29e-02

Pos logit contributions
wash+0.241
+0.237
pak+0.226
kat+0.219
gross+0.219
Neg logit contributions
 AST-0.227
elaide-0.217
igree-0.214
outh-0.214
ovember-0.213
Token policy
Token ID2450
Feature activation-1.67e-01

Pos logit contributions
 AST+0.022
elaide+0.021
igree+0.021
outh+0.021
ovember+0.021
Neg logit contributions
wash-0.025
-0.024
pak-0.023
kat-0.023
gross-0.022
Token memor
Token ID16181
Feature activation+1.29e+00

Pos logit contributions
 AST+0.298
elaide+0.284
igree+0.281
outh+0.281
ovember+0.279
Neg logit contributions
wash-0.305
-0.301
pak-0.286
kat-0.277
gross-0.277
Tokenanda
Token ID5282
Feature activation+2.34e-01

Pos logit contributions
wash+2.479
+2.429
pak+2.316
kat+2.265
gross+2.244
Neg logit contributions
 AST-2.179
elaide-2.107
igree-2.059
outh-2.050
ovember-2.049
Token intended
Token ID5292
Feature activation+2.14e-01

Pos logit contributions
wash+0.427
+0.420
pak+0.399
kat+0.387
gross+0.386
Neg logit contributions
 AST-0.418
elaide-0.400
igree-0.395
outh-0.395
ovember-0.393
Token to
Token ID284
Feature activation+5.46e-02

Pos logit contributions
wash+0.349
+0.343
pak+0.323
kat+0.313
gross+0.312
Neg logit contributions
 AST-0.425
elaide-0.408
igree-0.403
outh-0.403
ovember-0.401
Token help
Token ID1037
Feature activation+2.06e-01

Pos logit contributions
wash+0.113
+0.112
pak+0.107
kat+0.104
gross+0.104
Neg logit contributions
 AST-0.083
elaide-0.080
igree-0.079
outh-0.078
ovember-0.078
Token minority
Token ID9137
Feature activation-1.67e-01

Pos logit contributions
wash+0.382
+0.377
pak+0.357
kat+0.347
gross+0.346
Neg logit contributions
 AST-0.359
elaide-0.346
igree-0.342
outh-0.340
ovember-0.340
Token *
Token ID1635
Feature activation+5.08e-01

Pos logit contributions
 AST+0.333
elaide+0.317
outh+0.313
igree+0.313
ovember+0.311
Neg logit contributions
wash-0.369
-0.364
pak-0.345
kat-0.336
gross-0.335
Token-
Token ID12
Feature activation+1.27e-01

Pos logit contributions
wash+0.917
+0.902
pak+0.855
kat+0.831
gross+0.830
Neg logit contributions
 AST-0.914
elaide-0.881
igree-0.872
outh-0.866
ovember-0.865
Token 6
Token ID718
Feature activation+2.55e-02

Pos logit contributions
wash+0.237
+0.233
pak+0.221
kat+0.215
gross+0.215
Neg logit contributions
 AST-0.221
elaide-0.213
igree-0.210
outh-0.209
ovember-0.209
Token Sean
Token ID11465
Feature activation+9.58e-02

Pos logit contributions
wash+0.046
+0.045
pak+0.043
kat+0.042
gross+0.041
Neg logit contributions
 AST-0.046
elaide-0.044
igree-0.044
outh-0.043
ovember-0.043
Token Con
Token ID1482
Feature activation-2.36e-01

Pos logit contributions
wash+0.200
+0.198
pak+0.189
kat+0.184
gross+0.184
Neg logit contributions
 AST-0.145
elaide-0.137
igree-0.136
outh-0.136
ovember-0.135
Tokennery
Token ID35865
Feature activation+1.28e+00

Pos logit contributions
 AST+0.522
elaide+0.504
igree+0.499
outh+0.498
ovember+0.497
Neg logit contributions
wash-0.328
-0.322
pak-0.300
kat-0.289
gross-0.288
Token films
Token ID7328
Feature activation+6.88e-02

Pos logit contributions
wash+2.485
+2.440
pak+2.332
kat+2.263
gross+2.262
Neg logit contributions
 AST-2.102
elaide-2.050
igree-2.021
ovember-2.001
outh-2.001
Token,
Token ID11
Feature activation-9.04e-02

Pos logit contributions
wash+0.131
+0.130
pak+0.123
kat+0.120
gross+0.119
Neg logit contributions
 AST-0.117
elaide-0.112
igree-0.110
outh-0.110
ovember-0.109
Token 1962
Token ID20033
Feature activation+2.06e-01

Pos logit contributions
 AST+0.156
elaide+0.148
igree+0.146
outh+0.146
ovember+0.145
Neg logit contributions
wash-0.171
-0.169
pak-0.160
kat-0.156
gross-0.155
Token-
Token ID12
Feature activation+2.87e-02

Pos logit contributions
wash+0.427
+0.422
pak+0.403
kat+0.393
gross+0.391
Neg logit contributions
 AST-0.317
elaide-0.301
outh-0.296
igree-0.296
ovember-0.294
Token1971
Token ID41208
Feature activation+8.44e-02

Pos logit contributions
wash+0.036
+0.035
pak+0.032
kat+0.031
gross+0.031
Neg logit contributions
 AST-0.068
elaide-0.065
outh-0.064
ovember-0.064
igree-0.064
Tokenatch
Token ID963
Feature activation+5.43e-01

Pos logit contributions
wash+0.447
+0.441
pak+0.417
kat+0.405
gross+0.404
Neg logit contributions
 AST-0.462
elaide-0.442
outh-0.437
igree-0.437
ovember-0.434
Token a
Token ID257
Feature activation+1.01e-01

Pos logit contributions
wash+1.121
+1.104
pak+1.059
kat+1.029
gross+1.024
Neg logit contributions
 AST-0.832
elaide-0.795
igree-0.786
ovember-0.779
outh-0.778
Token blue
Token ID4171
Feature activation+4.33e-01

Pos logit contributions
wash+0.205
+0.203
pak+0.193
kat+0.188
gross+0.188
Neg logit contributions
 AST-0.158
elaide-0.151
igree-0.148
outh-0.148
ovember-0.147
Token-
Token ID12
Feature activation+1.12e-01

Pos logit contributions
wash+0.897
+0.884
pak+0.844
kat+0.822
gross+0.820
Neg logit contributions
 AST-0.665
elaide-0.634
igree-0.624
outh-0.623
ovember-0.620
Tokenpainted
Token ID47351
Feature activation+1.61e-01

Pos logit contributions
wash+0.189
+0.187
pak+0.175
kat+0.171
gross+0.170
Neg logit contributions
 AST-0.214
elaide-0.206
igree-0.204
outh-0.204
ovember-0.202
Token box
Token ID3091
Feature activation+1.19e+00

Pos logit contributions
wash+0.329
+0.324
pak+0.310
kat+0.302
gross+0.300
Neg logit contributions
 AST-0.249
elaide-0.239
igree-0.235
outh-0.234
ovember-0.234
Token before
Token ID878
Feature activation+3.18e-01

Pos logit contributions
wash+2.333
+2.281
pak+2.183
kat+2.133
gross+2.107
Neg logit contributions
 AST-1.940
elaide-1.884
igree-1.842
ovember-1.833
outh-1.821
Token it
Token ID340
Feature activation+2.23e-01

Pos logit contributions
wash+0.614
+0.606
pak+0.576
kat+0.560
gross+0.558
Neg logit contributions
 AST-0.532
elaide-0.512
igree-0.504
outh-0.502
ovember-0.500
Token touches
Token ID18105
Feature activation+6.42e-01

Pos logit contributions
wash+0.378
+0.372
pak+0.351
kat+0.341
gross+0.340
Neg logit contributions
 AST-0.427
elaide-0.408
igree-0.404
outh-0.404
ovember-0.402
Token the
Token ID262
Feature activation+2.68e-01

Pos logit contributions
wash+1.366
+1.350
pak+1.288
kat+1.254
gross+1.248
Neg logit contributions
 AST-0.942
elaide-0.903
outh-0.887
igree-0.885
ovember-0.884
Token ground
Token ID2323
Feature activation+5.28e-01

Pos logit contributions
wash+0.607
+0.601
pak+0.576
kat+0.562
gross+0.560
Neg logit contributions
 AST-0.356
elaide-0.340
igree-0.333
outh-0.332
ovember-0.331
Token text
Token ID2420
Feature activation+1.93e-01

Pos logit contributions
wash+0.227
+0.225
pak+0.213
kat+0.208
gross+0.206
Neg logit contributions
 AST-0.202
elaide-0.195
igree-0.192
outh-0.192
ovember-0.191
Token or
Token ID393
Feature activation+8.06e-02

Pos logit contributions
wash+0.366
+0.362
pak+0.343
kat+0.335
gross+0.333
Neg logit contributions
 AST-0.327
elaide-0.314
igree-0.310
outh-0.309
ovember-0.308
Token empty
Token ID6565
Feature activation+5.26e-01

Pos logit contributions
wash+0.144
+0.142
pak+0.134
kat+0.131
gross+0.130
Neg logit contributions
 AST-0.146
elaide-0.141
igree-0.139
outh-0.139
ovember-0.138
Token Example
Token ID17934
Feature activation+1.97e-01

Pos logit contributions
wash+1.109
+1.102
pak+1.046
kat+1.023
gross+1.011
Neg logit contributions
 AST-0.774
elaide-0.751
igree-0.736
ovember-0.732
outh-0.729
Token:
Token ID25
Feature activation-9.48e-02

Pos logit contributions
wash+0.337
+0.333
pak+0.314
kat+0.304
gross+0.303
Neg logit contributions
 AST-0.373
elaide-0.360
igree-0.355
outh-0.354
ovember-0.353
Token /*
Token ID11900
Feature activation+1.15e+00

Pos logit contributions
 AST+0.128
elaide+0.121
igree+0.119
outh+0.119
ovember+0.118
Neg logit contributions
wash-0.213
-0.211
pak-0.202
kat-0.198
gross-0.197
Token vim
Token ID43907
Feature activation+1.30e-01

Pos logit contributions
wash+2.281
+2.264
pak+2.132
kat+2.085
gross+2.072
Neg logit contributions
 AST-1.861
elaide-1.798
igree-1.767
ovember-1.747
outh-1.741
Token:
Token ID25
Feature activation-1.34e-01

Pos logit contributions
wash+0.229
+0.226
pak+0.214
kat+0.208
gross+0.207
Neg logit contributions
 AST-0.238
elaide-0.228
outh-0.225
igree-0.225
ovember-0.224
Token set
Token ID900
Feature activation-2.99e-01

Pos logit contributions
 AST+0.251
elaide+0.240
outh+0.237
igree+0.237
ovember+0.236
Neg logit contributions
wash-0.233
-0.229
pak-0.217
kat-0.211
gross-0.211
Token a
Token ID257
Feature activation-9.10e-02

Pos logit contributions
 AST+0.512
elaide+0.489
igree+0.483
outh+0.482
ovember+0.480
Neg logit contributions
wash-0.565
-0.558
pak-0.530
kat-0.516
gross-0.514
Tokeni
Token ID72
Feature activation-1.36e-01

Pos logit contributions
 AST+0.141
elaide+0.135
igree+0.133
outh+0.132
ovember+0.132
Neg logit contributions
wash-0.187
-0.185
pak-0.176
kat-0.172
gross-0.171
Token{
Token ID90
Feature activation+2.04e-01

Pos logit contributions
 AST+0.165
elaide+0.159
igree+0.157
outh+0.157
ovember+0.156
Neg logit contributions
wash-0.142
-0.140
pak-0.131
kat-0.127
gross-0.127
Token1
Token ID16
Feature activation+8.00e-02

Pos logit contributions
wash+0.389
+0.386
pak+0.365
kat+0.356
gross+0.355
Neg logit contributions
 AST-0.345
elaide-0.330
igree-0.326
outh-0.325
ovember-0.325
Token,
Token ID11
Feature activation-1.21e-01

Pos logit contributions
wash+0.164
+0.163
pak+0.155
kat+0.151
gross+0.151
Neg logit contributions
 AST-0.123
elaide-0.118
igree-0.116
outh-0.116
ovember-0.115
Token 6
Token ID718
Feature activation+1.44e-01

Pos logit contributions
 AST+0.230
elaide+0.220
outh+0.218
igree+0.218
ovember+0.217
Neg logit contributions
wash-0.206
-0.202
pak-0.191
kat-0.185
gross-0.185
Token}
Token ID92
Feature activation-5.06e-01

Pos logit contributions
wash+0.263
+0.259
pak+0.245
kat+0.239
gross+0.238
Neg logit contributions
 AST-0.256
elaide-0.245
igree-0.242
outh-0.241
ovember-0.241
Token <
Token ID1279
Feature activation+1.14e+00

Pos logit contributions
 AST+0.853
elaide+0.808
igree+0.800
outh+0.799
ovember+0.795
Neg logit contributions
wash-0.975
-0.956
pak-0.914
kat-0.890
gross-0.888
Token->
Token ID3784
Feature activation+3.41e-01

Pos logit contributions
+1.984
wash+1.975
pak+1.846
kat+1.785
gross+1.779
Neg logit contributions
 AST-2.106
elaide-2.059
ovember-2.014
igree-2.012
outh-2.009
Token {
Token ID1391
Feature activation+2.41e-01

Pos logit contributions
wash+0.695
+0.691
pak+0.655
kat+0.639
gross+0.637
Neg logit contributions
 AST-0.529
elaide-0.509
igree-0.500
ovember-0.499
outh-0.498
Token1
Token ID16
Feature activation+9.29e-02

Pos logit contributions
wash+0.368
+0.363
pak+0.339
kat+0.328
gross+0.327
Neg logit contributions
 AST-0.501
elaide-0.484
igree-0.479
outh-0.478
ovember-0.476
Token,
Token ID11
Feature activation-1.32e-01

Pos logit contributions
wash+0.196
+0.193
pak+0.185
kat+0.180
gross+0.180
Neg logit contributions
 AST-0.140
elaide-0.131
outh-0.130
igree-0.130
ovember-0.129
Token 7
Token ID767
Feature activation-2.24e-02

Pos logit contributions
 AST+0.239
elaide+0.228
outh+0.226
igree+0.225
ovember+0.224
Neg logit contributions
wash-0.236
-0.232
pak-0.220
kat-0.214
gross-0.213
Token{{
Token ID27007
Feature activation+4.57e-01

Pos logit contributions
 AST+0.261
elaide+0.252
igree+0.249
outh+0.249
ovember+0.248
Neg logit contributions
wash-0.203
-0.200
pak-0.188
kat-0.182
gross-0.181
Token1
Token ID16
Feature activation+1.08e-01

Pos logit contributions
wash+0.712
+0.706
pak+0.656
gross+0.636
kat+0.635
Neg logit contributions
 AST-0.935
elaide-0.902
igree-0.894
ovember-0.889
outh-0.888
Token,
Token ID11
Feature activation-1.14e-01

Pos logit contributions
wash+0.224
+0.221
pak+0.211
kat+0.206
gross+0.205
Neg logit contributions
 AST-0.164
elaide-0.156
igree-0.154
outh-0.154
ovember-0.153
Token 6
Token ID718
Feature activation+1.54e-01

Pos logit contributions
 AST+0.208
elaide+0.199
igree+0.196
outh+0.196
ovember+0.195
Neg logit contributions
wash-0.205
-0.201
pak-0.191
kat-0.186
gross-0.185
Token}
Token ID92
Feature activation-4.16e-01

Pos logit contributions
wash+0.276
+0.272
pak+0.257
kat+0.250
gross+0.250
Neg logit contributions
 AST-0.280
elaide-0.268
igree-0.265
outh-0.264
ovember-0.263
Token <
Token ID1279
Feature activation+1.14e+00

Pos logit contributions
 AST+0.679
elaide+0.643
outh+0.635
igree+0.635
ovember+0.630
Neg logit contributions
wash-0.824
-0.808
pak-0.774
kat-0.755
gross-0.753
Token->
Token ID3784
Feature activation+3.64e-01

Pos logit contributions
wash+1.543
+1.540
pak+1.421
kat+1.371
gross+1.336
Neg logit contributions
 AST-2.551
elaide-2.478
igree-2.446
outh-2.439
ovember-2.432
Token {
Token ID1391
Feature activation+2.18e-01

Pos logit contributions
wash+0.801
+0.796
pak+0.757
kat+0.741
gross+0.739
Neg logit contributions
 AST-0.503
elaide-0.481
igree-0.472
outh-0.471
ovember-0.471
Token1
Token ID16
Feature activation+8.89e-02

Pos logit contributions
wash+0.320
+0.314
pak+0.294
kat+0.283
gross+0.282
Neg logit contributions
 AST-0.466
elaide-0.449
igree-0.445
outh-0.444
ovember-0.442
Token,
Token ID11
Feature activation-1.45e-01

Pos logit contributions
wash+0.190
+0.186
pak+0.179
gross+0.175
kat+0.174
Neg logit contributions
 AST-0.131
outh-0.122
elaide-0.122
igree-0.120
 Monarch-0.120
Token 6
Token ID718
Feature activation+1.57e-01

Pos logit contributions
 AST+0.265
elaide+0.254
igree+0.251
outh+0.250
ovember+0.249
Neg logit contributions
wash-0.259
-0.255
pak-0.241
kat-0.234
gross-0.234
TokenOh
Token ID5812
Feature activation-2.85e-01

Pos logit contributions
 AST+0.048
elaide+0.046
igree+0.046
outh+0.046
ovember+0.045
Neg logit contributions
wash-0.041
-0.040
pak-0.038
kat-0.036
gross-0.036
Token,
Token ID11
Feature activation+2.10e-02

Pos logit contributions
 AST+0.459
elaide+0.438
igree+0.432
outh+0.431
ovember+0.429
Neg logit contributions
wash-0.569
-0.561
pak-0.535
kat-0.521
gross-0.520
Token and
Token ID290
Feature activation+5.47e-02

Pos logit contributions
wash+0.042
+0.041
pak+0.039
kat+0.038
gross+0.038
Neg logit contributions
 AST-0.034
elaide-0.032
igree-0.032
outh-0.032
ovember-0.031
Token forget
Token ID6044
Feature activation+1.75e-01

Pos logit contributions
wash+0.109
+0.107
pak+0.102
kat+0.099
gross+0.099
Neg logit contributions
 AST-0.088
elaide-0.085
igree-0.084
outh-0.083
ovember-0.083
Token about
Token ID546
Feature activation-1.98e-02

Pos logit contributions
wash+0.346
+0.342
pak+0.325
kat+0.317
gross+0.316
Neg logit contributions
 AST-0.285
elaide-0.273
igree-0.269
outh-0.268
ovember-0.267
Token memor
Token ID16181
Feature activation+1.14e+00

Pos logit contributions
 AST+0.031
elaide+0.030
igree+0.029
outh+0.029
ovember+0.029
Neg logit contributions
wash-0.040
-0.040
pak-0.038
kat-0.037
gross-0.037
Tokenizing
Token ID2890
Feature activation+3.82e-02

Pos logit contributions
wash+2.100
+2.069
pak+1.962
kat+1.910
gross+1.900
Neg logit contributions
 AST-2.000
elaide-1.926
igree-1.894
outh-1.893
ovember-1.877
Token times
Token ID1661
Feature activation+9.83e-02

Pos logit contributions
wash+0.076
+0.075
pak+0.071
kat+0.070
gross+0.069
Neg logit contributions
 AST-0.062
elaide-0.059
igree-0.058
outh-0.058
ovember-0.058
Token tables
Token ID8893
Feature activation-8.34e-01

Pos logit contributions
wash+0.190
+0.187
pak+0.178
kat+0.173
gross+0.173
Neg logit contributions
 AST-0.165
elaide-0.157
igree-0.155
outh-0.155
ovember-0.154
Token or
Token ID393
Feature activation+6.06e-02

Pos logit contributions
 AST+1.350
elaide+1.284
outh+1.273
igree+1.261
ovember+1.254
Neg logit contributions
wash-1.649
-1.629
pak-1.550
kat-1.515
gross-1.509
Token mastering
Token ID45116
Feature activation+1.93e-01

Pos logit contributions
wash+0.119
+0.118
pak+0.112
kat+0.109
gross+0.109
Neg logit contributions
 AST-0.099
elaide-0.095
igree-0.094
outh-0.093
ovember-0.093
Token,
Token ID11
Feature activation+1.40e-01

Pos logit contributions
 AST+0.416
elaide+0.395
igree+0.390
outh+0.389
ovember+0.387
Neg logit contributions
wash-0.545
-0.539
pak-0.514
kat-0.500
gross-0.500
Token books
Token ID3835
Feature activation+4.31e-01

Pos logit contributions
wash+0.285
+0.282
pak+0.268
kat+0.262
gross+0.261
Neg logit contributions
 AST-0.220
elaide-0.210
igree-0.207
outh-0.206
ovember-0.205
Token,
Token ID11
Feature activation+1.24e-01

Pos logit contributions
wash+0.841
+0.830
pak+0.789
kat+0.772
gross+0.768
Neg logit contributions
 AST-0.709
elaide-0.680
igree-0.671
outh-0.669
ovember-0.666
Token and
Token ID290
Feature activation+7.81e-02

Pos logit contributions
wash+0.229
+0.226
pak+0.215
kat+0.209
gross+0.208
Neg logit contributions
 AST-0.216
elaide-0.207
igree-0.204
outh-0.204
ovember-0.203
Token other
Token ID584
Feature activation+1.84e-01

Pos logit contributions
wash+0.150
+0.148
pak+0.141
kat+0.137
gross+0.137
Neg logit contributions
 AST-0.131
elaide-0.125
igree-0.124
outh-0.123
ovember-0.123
Token memor
Token ID16181
Feature activation+1.12e+00

Pos logit contributions
wash+0.330
+0.324
pak+0.307
kat+0.299
gross+0.298
Neg logit contributions
 AST-0.335
elaide-0.321
igree-0.317
outh-0.316
ovember-0.315
Tokenabilia
Token ID48249
Feature activation-5.94e-02

Pos logit contributions
wash+2.763
+2.735
pak+2.635
kat+2.588
gross+2.573
Neg logit contributions
 AST-1.253
elaide-1.181
outh-1.150
igree-1.145
ovember-1.145
Token.
Token ID13
Feature activation+1.32e-01

Pos logit contributions
 AST+0.097
elaide+0.092
igree+0.091
outh+0.091
ovember+0.090
Neg logit contributions
wash-0.117
-0.115
pak-0.110
gross-0.107
kat-0.107
Token
Token ID198
Feature activation+1.35e-01

Pos logit contributions
wash+0.250
+0.247
pak+0.234
kat+0.228
gross+0.227
Neg logit contributions
 AST-0.227
elaide-0.218
igree-0.215
outh-0.214
ovember-0.214
Token
Token ID198
Feature activation+1.23e-01

Pos logit contributions
wash+0.264
+0.259
pak+0.248
gross+0.242
kat+0.241
Neg logit contributions
 AST-0.223
outh-0.210
elaide-0.206
 Monarch-0.206
 ADHD-0.205
TokenAbout
Token ID8585
Feature activation+5.50e-02

Pos logit contributions
wash+0.208
+0.204
pak+0.193
kat+0.187
gross+0.187
Neg logit contributions
 AST-0.235
elaide-0.225
outh-0.224
igree-0.223
ovember-0.222
Token with
Token ID351
Feature activation+7.70e-02

Pos logit contributions
wash+0.271
+0.268
pak+0.255
kat+0.249
gross+0.248
Neg logit contributions
 AST-0.212
elaide-0.202
igree-0.199
outh-0.199
ovember-0.198
Token former
Token ID1966
Feature activation-2.73e-01

Pos logit contributions
wash+0.158
+0.156
pak+0.149
kat+0.146
gross+0.145
Neg logit contributions
 AST-0.119
elaide-0.113
igree-0.112
outh-0.111
ovember-0.111
Token Cuban
Token ID18147
Feature activation+3.47e-01

Pos logit contributions
 AST+0.436
elaide+0.408
 Monarch+0.406
outh+0.404
igree+0.401
Neg logit contributions
wash-0.553
-0.545
pak-0.517
kat-0.507
gross-0.506
Token President
Token ID1992
Feature activation+1.45e-02

Pos logit contributions
wash+0.680
+0.672
pak+0.641
kat+0.623
gross+0.622
Neg logit contributions
 AST-0.565
elaide-0.546
igree-0.539
ovember-0.536
outh-0.533
Token Fidel
Token ID42320
Feature activation+7.33e-01

Pos logit contributions
wash+0.029
+0.029
pak+0.027
kat+0.027
gross+0.027
Neg logit contributions
 AST-0.023
elaide-0.022
igree-0.022
ovember-0.022
outh-0.022
Token Castro
Token ID21193
Feature activation+1.12e+00

Pos logit contributions
wash+1.361
+1.345
pak+1.276
kat+1.241
gross+1.236
Neg logit contributions
 AST-1.274
elaide-1.225
igree-1.209
ovember-1.205
outh-1.203
Token,
Token ID11
Feature activation+1.46e-01

Pos logit contributions
wash+2.196
+2.175
pak+2.066
kat+2.024
gross+2.004
Neg logit contributions
 AST-1.797
elaide-1.715
igree-1.708
ovember-1.700
outh-1.687
Token Cuban
Token ID18147
Feature activation+4.04e-01

Pos logit contributions
wash+0.297
+0.294
pak+0.280
gross+0.272
kat+0.272
Neg logit contributions
 AST-0.226
elaide-0.218
igree-0.215
ovember-0.214
outh-0.213
Token dissidents
Token ID49913
Feature activation+4.83e-01

Pos logit contributions
wash+0.743
+0.733
pak+0.700
Net+0.679
gross+0.677
Neg logit contributions
 AST-0.696
elaide-0.680
igree-0.674
ovember-0.667
outh-0.657
Token who
Token ID508
Feature activation+1.01e-01

Pos logit contributions
wash+0.913
+0.900
pak+0.856
kat+0.833
gross+0.831
Neg logit contributions
 AST-0.824
elaide-0.792
igree-0.781
outh-0.777
ovember-0.776
Token advocate
Token ID12811
Feature activation+5.52e-01

Pos logit contributions
wash+0.181
+0.179
pak+0.169
kat+0.164
gross+0.164
Neg logit contributions
 AST-0.184
elaide-0.177
igree-0.175
outh-0.174
ovember-0.173
Token dens
Token ID29509
Feature activation+3.74e-01

Pos logit contributions
wash+0.100
+0.098
pak+0.094
kat+0.091
gross+0.091
Neg logit contributions
 AST-0.090
elaide-0.085
igree-0.084
outh-0.084
ovember-0.084
Tokener
Token ID263
Feature activation-2.03e-01

Pos logit contributions
wash+0.779
+0.770
pak+0.735
kat+0.718
gross+0.716
Neg logit contributions
 AST-0.569
elaide-0.542
igree-0.532
outh-0.532
ovember-0.531
Token than
Token ID621
Feature activation+3.03e-01

Pos logit contributions
 AST+0.334
elaide+0.318
igree+0.314
outh+0.313
ovember+0.311
Neg logit contributions
wash-0.399
-0.394
pak-0.375
kat-0.366
gross-0.364
Token zinc
Token ID31861
Feature activation-4.41e-02

Pos logit contributions
wash+0.611
+0.603
pak+0.574
kat+0.561
gross+0.558
Neg logit contributions
 AST-0.479
elaide-0.461
igree-0.452
outh-0.452
ovember-0.451
Token sulf
Token ID22443
Feature activation+4.98e-01

Pos logit contributions
 AST+0.068
elaide+0.065
igree+0.064
ovember+0.063
outh+0.063
Neg logit contributions
wash-0.091
-0.090
pak-0.086
kat-0.084
gross-0.083
Tokenate
Token ID378
Feature activation+1.10e+00

Pos logit contributions
wash+0.669
+0.648
pak+0.605
kat+0.584
gross+0.578
Neg logit contributions
 AST-1.130
elaide-1.096
igree-1.083
ovember-1.079
outh-1.075
Token,
Token ID11
Feature activation+3.60e-02

Pos logit contributions
wash+2.152
+2.137
pak+2.024
kat+1.966
gross+1.934
Neg logit contributions
 AST-1.772
elaide-1.733
ovember-1.698
igree-1.693
outh-1.677
Token the
Token ID262
Feature activation+8.60e-02

Pos logit contributions
wash+0.076
+0.075
pak+0.072
kat+0.070
gross+0.070
Neg logit contributions
 AST-0.054
elaide-0.051
igree-0.050
outh-0.050
ovember-0.050
Token zinc
Token ID31861
Feature activation-9.21e-02

Pos logit contributions
wash+0.173
+0.170
pak+0.162
kat+0.158
gross+0.158
Neg logit contributions
 AST-0.138
elaide-0.130
igree-0.129
outh-0.129
ovember-0.128
Token solution
Token ID4610
Feature activation-3.89e-01

Pos logit contributions
 AST+0.136
elaide+0.130
igree+0.128
outh+0.127
ovember+0.127
Neg logit contributions
wash-0.195
-0.193
pak-0.184
kat-0.180
gross-0.179
Token floated
Token ID29742
Feature activation+4.35e-01

Pos logit contributions
 AST+0.682
elaide+0.648
outh+0.641
igree+0.641
ovember+0.635
Neg logit contributions
wash-0.721
-0.711
pak-0.676
kat-0.657
gross-0.654
Token The
Token ID383
Feature activation-1.28e-01

Pos logit contributions
wash+0.285
+0.281
pak+0.268
kat+0.262
gross+0.261
Neg logit contributions
 AST-0.219
elaide-0.209
igree-0.206
outh-0.205
ovember-0.205
Token Dice
Token ID34381
Feature activation+3.19e-01

Pos logit contributions
 AST+0.196
elaide+0.186
igree+0.183
outh+0.183
ovember+0.182
Neg logit contributions
wash-0.264
-0.261
pak-0.249
kat-0.243
gross-0.242
Token Tower
Token ID8765
Feature activation+6.77e-01

Pos logit contributions
wash+0.643
+0.635
pak+0.606
kat+0.591
gross+0.588
Neg logit contributions
 AST-0.506
elaide-0.483
igree-0.476
outh-0.474
ovember-0.473
Token
Token ID198
Feature activation+9.63e-02

Pos logit contributions
wash+1.287
+1.271
pak+1.206
kat+1.175
gross+1.169
Neg logit contributions
 AST-1.151
elaide-1.105
igree-1.090
outh-1.085
ovember-1.083
Token
Token ID198
Feature activation+5.13e-02

Pos logit contributions
wash+0.190
+0.186
pak+0.179
gross+0.175
kat+0.174
Neg logit contributions
 AST-0.157
outh-0.147
 Monarch-0.144
 ADHD-0.144
 Lyme-0.144
Tokenhttp
Token ID4023
Feature activation+1.10e+00

Pos logit contributions
wash+0.086
+0.085
pak+0.080
kat+0.077
gross+0.077
Neg logit contributions
 AST-0.098
elaide-0.094
outh-0.093
igree-0.093
ovember-0.093
Token://
Token ID1378
Feature activation+9.23e-01

Pos logit contributions
wash+1.785
+1.763
pak+1.657
kat+1.608
gross+1.596
Neg logit contributions
 AST-2.160
elaide-2.094
igree-2.070
ovember-2.051
outh-2.049
Tokenwww
Token ID2503
Feature activation+3.03e-01

Pos logit contributions
wash+1.182
+1.145
pak+1.070
kat+1.031
gross+1.024
Neg logit contributions
 AST-2.155
elaide-2.085
igree-2.056
ovember-2.051
outh-2.050
Token.
Token ID13
Feature activation+1.76e-02

Pos logit contributions
wash+0.592
+0.583
pak+0.556
gross+0.542
kat+0.540
Neg logit contributions
 AST-0.499
outh-0.470
elaide-0.469
igree-0.463
ovember-0.462
Tokenboard
Token ID3526
Feature activation+1.95e-01

Pos logit contributions
wash+0.029
+0.028
pak+0.027
kat+0.026
gross+0.026
Neg logit contributions
 AST-0.034
elaide-0.033
igree-0.033
outh-0.033
ovember-0.033
Tokengame
Token ID6057
Feature activation+3.70e-01

Pos logit contributions
wash+0.411
+0.405
pak+0.386
kat+0.380
gross+0.378
Neg logit contributions
 AST-0.291
elaide-0.278
igree-0.273
outh-0.272
ovember-0.270
Token[[
Token ID30109
Feature activation+4.56e-01

Pos logit contributions
 AST+0.065
elaide+0.062
igree+0.062
outh+0.061
ovember+0.061
Neg logit contributions
wash-0.083
-0.082
pak-0.078
kat-0.076
gross-0.076
Token#
Token ID2
Feature activation+2.45e-01

Pos logit contributions
wash+0.806
+0.797
pak+0.751
kat+0.728
gross+0.728
Neg logit contributions
 AST-0.836
elaide-0.805
igree-0.795
outh-0.789
ovember-0.789
Token,
Token ID11
Feature activation-1.35e-01

Pos logit contributions
wash+0.484
+0.480
pak+0.455
kat+0.444
gross+0.442
Neg logit contributions
 AST-0.399
elaide-0.383
igree-0.378
outh-0.375
ovember-0.374
Token 1
Token ID352
Feature activation+5.57e-02

Pos logit contributions
 AST+0.231
elaide+0.221
igree+0.218
outh+0.218
ovember+0.217
Neg logit contributions
wash-0.257
-0.253
pak-0.241
kat-0.234
gross-0.234
Token]]
Token ID11907
Feature activation-2.96e-01

Pos logit contributions
wash+0.122
+0.121
pak+0.116
kat+0.113
gross+0.113
Neg logit contributions
 AST-0.078
elaide-0.074
igree-0.073
outh-0.073
ovember-0.072
Token <
Token ID1279
Feature activation+1.09e+00

Pos logit contributions
 AST+0.425
elaide+0.403
igree+0.397
outh+0.396
ovember+0.394
Neg logit contributions
wash-0.642
-0.634
pak-0.606
kat-0.592
gross-0.591
Token->
Token ID3784
Feature activation+2.44e-01

Pos logit contributions
+1.805
wash+1.803
pak+1.686
kat+1.622
gross+1.612
Neg logit contributions
 AST-2.101
elaide-2.050
igree-2.013
ovember-2.004
outh-1.991
Token graph
Token ID4823
Feature activation-4.35e-02

Pos logit contributions
wash+0.490
+0.487
pak+0.461
kat+0.449
gross+0.448
Neg logit contributions
 AST-0.384
elaide-0.372
igree-0.365
ovember-0.363
outh-0.363
TokenList
Token ID8053
Feature activation-8.18e-02

Pos logit contributions
 AST+0.076
elaide+0.072
igree+0.072
outh+0.071
ovember+0.071
Neg logit contributions
wash-0.081
-0.080
pak-0.076
kat-0.074
gross-0.074
Token[[
Token ID30109
Feature activation+3.61e-01

Pos logit contributions
 AST+0.206
elaide+0.200
igree+0.199
outh+0.198
ovember+0.198
Neg logit contributions
wash-0.088
-0.087
pak-0.079
kat-0.075
gross-0.074
Token#
Token ID2
Feature activation+1.47e-01

Pos logit contributions
wash+0.736
+0.728
pak+0.692
kat+0.675
gross+0.674
Neg logit contributions
 AST-0.565
elaide-0.538
igree-0.531
outh-0.527
ovember-0.525
Token Ru
Token ID11667
Feature activation-3.71e-01

Pos logit contributions
 AST+0.089
elaide+0.082
igree+0.081
outh+0.081
ovember+0.080
Neg logit contributions
wash-0.196
-0.194
pak-0.187
kat-0.183
gross-0.182
Tokeniz
Token ID528
Feature activation+4.27e-01

Pos logit contributions
 AST+0.754
outh+0.741
elaide+0.733
ovember+0.726
igree+0.725
Neg logit contributions
-0.554
wash-0.552
pak-0.518
gross-0.493
kat-0.490
Token,
Token ID11
Feature activation-3.67e-02

Pos logit contributions
wash+0.754
+0.744
pak+0.702
kat+0.683
gross+0.681
Neg logit contributions
 AST-0.786
elaide-0.756
igree-0.746
outh-0.743
ovember-0.741
Token who
Token ID508
Feature activation-7.37e-02

Pos logit contributions
 AST+0.063
elaide+0.060
igree+0.059
outh+0.059
ovember+0.059
Neg logit contributions
wash-0.070
-0.069
pak-0.065
kat-0.063
gross-0.063
Token had
Token ID550
Feature activation+1.82e-01

Pos logit contributions
 AST+0.134
elaide+0.128
igree+0.126
outh+0.126
ovember+0.126
Neg logit contributions
wash-0.132
-0.130
pak-0.124
kat-0.120
gross-0.120
Token memor
Token ID16181
Feature activation+1.09e+00

Pos logit contributions
wash+0.337
+0.332
pak+0.315
kat+0.307
gross+0.306
Neg logit contributions
 AST-0.316
elaide-0.304
igree-0.300
outh-0.299
ovember-0.298
Tokenized
Token ID1143
Feature activation-1.49e-01

Pos logit contributions
wash+1.780
+1.753
pak+1.649
kat+1.603
gross+1.594
Neg logit contributions
 AST-2.128
elaide-2.065
outh-2.035
igree-2.033
ovember-2.025
Token all
Token ID477
Feature activation+4.32e-03

Pos logit contributions
 AST+0.219
elaide+0.207
igree+0.205
outh+0.204
ovember+0.203
Neg logit contributions
wash-0.317
-0.313
pak-0.300
kat-0.293
gross-0.292
Token of
Token ID286
Feature activation-7.22e-02

Pos logit contributions
wash+0.009
+0.009
pak+0.009
kat+0.008
gross+0.008
Neg logit contributions
 AST-0.006
elaide-0.006
igree-0.006
outh-0.006
ovember-0.006
Token the
Token ID262
Feature activation-4.80e-02

Pos logit contributions
 AST+0.103
elaide+0.097
igree+0.096
outh+0.096
ovember+0.095
Neg logit contributions
wash-0.157
-0.155
pak-0.149
kat-0.145
gross-0.145
Token winners
Token ID14591
Feature activation-3.35e-02

Pos logit contributions
 AST+0.087
elaide+0.082
igree+0.082
outh+0.081
 Monarch+0.081
Neg logit contributions
wash-0.087
-0.085
pak-0.081
kat-0.079
gross-0.078
Token {
Token ID1391
Feature activation+1.89e-01

Pos logit contributions
 AST+0.268
elaide+0.251
igree+0.247
outh+0.246
ovember+0.244
Neg logit contributions
wash-0.464
-0.457
pak-0.440
kat-0.430
gross-0.429
Token1
Token ID16
Feature activation+8.72e-02

Pos logit contributions
wash+0.279
+0.274
pak+0.257
kat+0.248
gross+0.247
Neg logit contributions
 AST-0.400
elaide-0.386
igree-0.382
outh-0.382
ovember-0.380
Token,
Token ID11
Feature activation-1.24e-01

Pos logit contributions
wash+0.187
+0.183
pak+0.176
gross+0.172
kat+0.171
Neg logit contributions
 AST-0.128
outh-0.119
elaide-0.118
igree-0.117
 Monarch-0.117
Token 6
Token ID718
Feature activation+1.99e-01

Pos logit contributions
 AST+0.226
elaide+0.216
igree+0.213
outh+0.213
ovember+0.212
Neg logit contributions
wash-0.222
-0.218
pak-0.206
kat-0.201
gross-0.200
Token}
Token ID92
Feature activation-4.84e-01

Pos logit contributions
wash+0.411
+0.405
pak+0.387
kat+0.378
gross+0.377
Neg logit contributions
 AST-0.306
elaide-0.289
igree-0.286
outh-0.286
ovember-0.284
Token <
Token ID1279
Feature activation+1.06e+00

Pos logit contributions
 AST+0.763
elaide+0.721
igree+0.711
outh+0.710
ovember+0.704
Neg logit contributions
wash-0.988
-0.967
pak-0.928
kat-0.907
gross-0.903
Token->
Token ID3784
Feature activation+2.94e-01

Pos logit contributions
wash+1.473
+1.458
pak+1.353
kat+1.305
gross+1.284
Neg logit contributions
 AST-2.335
elaide-2.274
igree-2.247
outh-2.230
ovember-2.229
Token {
Token ID1391
Feature activation+1.24e-01

Pos logit contributions
wash+0.681
+0.673
pak+0.646
kat+0.632
gross+0.631
Neg logit contributions
 AST-0.380
elaide-0.357
igree-0.351
outh-0.351
ovember-0.348
Token1
Token ID16
Feature activation+1.02e-01

Pos logit contributions
wash+0.179
+0.176
pak+0.164
kat+0.158
gross+0.158
Neg logit contributions
 AST-0.267
elaide-0.258
igree-0.255
outh-0.255
ovember-0.254
Token,
Token ID11
Feature activation-1.49e-01

Pos logit contributions
wash+0.218
+0.214
pak+0.205
gross+0.201
kat+0.200
Neg logit contributions
 AST-0.150
outh-0.140
elaide-0.140
igree-0.138
 Monarch-0.138
Token 7
Token ID767
Feature activation+1.72e-02

Pos logit contributions
 AST+0.272
elaide+0.260
igree+0.257
outh+0.256
ovember+0.255
Neg logit contributions
wash-0.264
-0.260
pak-0.246
kat-0.239
gross-0.239
Token added
Token ID2087
Feature activation+1.93e-01

Pos logit contributions
wash+0.032
+0.031
pak+0.029
kat+0.029
gross+0.028
Neg logit contributions
 AST-0.031
elaide-0.030
igree-0.030
outh-0.030
ovember-0.030
Token.
Token ID13
Feature activation-1.18e-01

Pos logit contributions
wash+0.343
+0.337
pak+0.319
kat+0.310
gross+0.309
Neg logit contributions
 AST-0.353
elaide-0.339
igree-0.335
outh-0.333
ovember-0.333
Token Because
Token ID4362
Feature activation-2.20e-01

Pos logit contributions
 AST+0.202
elaide+0.192
outh+0.190
igree+0.190
ovember+0.189
Neg logit contributions
wash-0.224
-0.221
pak-0.210
kat-0.205
gross-0.204
Token copper
Token ID15317
Feature activation-4.64e-02

Pos logit contributions
 AST+0.325
elaide+0.306
igree+0.303
outh+0.302
ovember+0.300
Neg logit contributions
wash-0.468
-0.463
pak-0.442
kat-0.433
gross-0.431
Token sulf
Token ID22443
Feature activation+4.04e-01

Pos logit contributions
 AST+0.068
elaide+0.065
igree+0.064
outh+0.064
ovember+0.063
Neg logit contributions
wash-0.099
-0.098
pak-0.093
kat-0.091
gross-0.091
Tokenate
Token ID378
Feature activation+1.06e+00

Pos logit contributions
wash+0.555
+0.546
pak+0.508
kat+0.488
gross+0.487
Neg logit contributions
 AST-0.900
elaide-0.869
igree-0.861
outh-0.861
ovember-0.857
Token is
Token ID318
Feature activation+5.25e-02

Pos logit contributions
wash+1.889
+1.870
pak+1.751
kat+1.705
gross+1.687
Neg logit contributions
 AST-1.896
elaide-1.854
ovember-1.824
igree-1.822
outh-1.810
Token dens
Token ID29509
Feature activation+3.74e-01

Pos logit contributions
wash+0.100
+0.098
pak+0.094
kat+0.091
gross+0.091
Neg logit contributions
 AST-0.090
elaide-0.085
igree-0.084
outh-0.084
ovember-0.084
Tokener
Token ID263
Feature activation-2.03e-01

Pos logit contributions
wash+0.779
+0.770
pak+0.735
kat+0.718
gross+0.716
Neg logit contributions
 AST-0.569
elaide-0.542
igree-0.532
outh-0.532
ovember-0.531
Token than
Token ID621
Feature activation+3.03e-01

Pos logit contributions
 AST+0.334
elaide+0.318
igree+0.314
outh+0.313
ovember+0.311
Neg logit contributions
wash-0.399
-0.394
pak-0.375
kat-0.366
gross-0.364
Token zinc
Token ID31861
Feature activation-4.41e-02

Pos logit contributions
wash+0.611
+0.603
pak+0.574
kat+0.561
gross+0.558
Neg logit contributions
 AST-0.479
elaide-0.461
igree-0.452
outh-0.452
ovember-0.451
Token in
Token ID287
Feature activation+7.62e-02

Pos logit contributions
 AST+0.361
elaide+0.344
igree+0.339
outh+0.339
ovember+0.337
Neg logit contributions
wash-0.431
-0.426
pak-0.405
kat-0.395
gross-0.395
Token the
Token ID262
Feature activation+4.48e-02

Pos logit contributions
wash+0.161
+0.159
pak+0.152
kat+0.149
gross+0.148
Neg logit contributions
 AST-0.114
elaide-0.108
igree-0.106
outh-0.106
ovember-0.106
Token background
Token ID4469
Feature activation+3.45e-01

Pos logit contributions
wash+0.072
+0.071
pak+0.067
gross+0.065
kat+0.064
Neg logit contributions
 AST-0.089
elaide-0.086
igree-0.085
outh-0.085
ovember-0.084
Token,
Token ID11
Feature activation+6.97e-02

Pos logit contributions
wash+0.666
+0.656
pak+0.624
kat+0.607
gross+0.606
Neg logit contributions
 AST-0.578
elaide-0.552
igree-0.546
outh-0.543
ovember-0.542
Token Survivor
Token ID23740
Feature activation+1.86e-01

Pos logit contributions
wash+0.133
+0.131
pak+0.125
kat+0.121
gross+0.121
Neg logit contributions
 AST-0.118
elaide-0.113
igree-0.111
outh-0.111
ovember-0.111
Token memor
Token ID16181
Feature activation+1.05e+00

Pos logit contributions
wash+0.363
+0.358
pak+0.340
kat+0.331
gross+0.331
Neg logit contributions
 AST-0.307
elaide-0.293
igree-0.289
outh-0.288
ovember-0.287
Tokenabilia
Token ID48249
Feature activation-1.97e-01

Pos logit contributions
wash+2.587
+2.559
pak+2.459
kat+2.412
gross+2.399
Neg logit contributions
 AST-1.191
elaide-1.123
outh-1.091
igree-1.089
ovember-1.084
Token throughout
Token ID3690
Feature activation-5.54e-02

Pos logit contributions
 AST+0.308
elaide+0.292
igree+0.288
outh+0.288
ovember+0.286
Neg logit contributions
wash-0.404
-0.398
pak-0.380
gross-0.371
kat-0.370
Token the
Token ID262
Feature activation+8.27e-02

Pos logit contributions
 AST+0.081
elaide+0.077
igree+0.075
outh+0.075
ovember+0.075
Neg logit contributions
wash-0.119
-0.117
pak-0.112
kat-0.110
gross-0.109
Token queue
Token ID16834
Feature activation-1.95e-01

Pos logit contributions
wash+0.177
+0.175
pak+0.167
kat+0.163
gross+0.163
Neg logit contributions
 AST-0.122
elaide-0.115
igree-0.113
outh-0.113
ovember-0.112
Token and
Token ID290
Feature activation+7.49e-02

Pos logit contributions
 AST+0.296
elaide+0.282
igree+0.277
outh+0.277
ovember+0.274
Neg logit contributions
wash-0.406
-0.401
pak-0.384
gross-0.374
kat-0.374
Token the
Token ID262
Feature activation+9.38e-02

Pos logit contributions
wash+0.088
+0.087
pak+0.083
kat+0.081
gross+0.080
Neg logit contributions
 AST-0.070
elaide-0.067
igree-0.066
outh-0.066
ovember-0.066
Token name
Token ID1438
Feature activation+1.35e-01

Pos logit contributions
wash+0.184
+0.181
pak+0.172
kat+0.168
gross+0.167
Neg logit contributions
 AST-0.155
elaide-0.147
igree-0.145
outh-0.145
ovember-0.144
Token a
Token ID257
Feature activation+3.88e-02

Pos logit contributions
wash+0.265
+0.262
pak+0.250
kat+0.243
gross+0.242
Neg logit contributions
 AST-0.220
elaide-0.209
igree-0.207
outh-0.206
ovember-0.205
Token teenage
Token ID16330
Feature activation+6.82e-02

Pos logit contributions
wash+0.078
+0.077
pak+0.073
kat+0.071
gross+0.071
Neg logit contributions
 AST-0.062
elaide-0.059
igree-0.058
outh-0.058
ovember-0.058
Token boy
Token ID2933
Feature activation-4.94e-01

Pos logit contributions
wash+0.157
+0.155
pak+0.149
kat+0.145
gross+0.145
Neg logit contributions
 AST-0.089
elaide-0.085
igree-0.083
ovember-0.082
outh-0.082
Token memor
Token ID16181
Feature activation+1.04e+00

Pos logit contributions
 AST+0.860
elaide+0.818
outh+0.814
igree+0.809
ovember+0.805
Neg logit contributions
wash-0.913
-0.904
pak-0.857
gross-0.832
kat-0.827
Tokenably
Token ID1346
Feature activation+2.39e-01

Pos logit contributions
wash+1.470
+1.439
pak+1.343
kat+1.300
gross+1.291
Neg logit contributions
 AST-2.261
elaide-2.186
outh-2.162
igree-2.161
ovember-2.152
Token gives
Token ID3607
Feature activation+5.00e-03

Pos logit contributions
wash+0.436
+0.430
pak+0.407
kat+0.396
gross+0.395
Neg logit contributions
 AST-0.426
elaide-0.407
outh-0.402
igree-0.402
ovember-0.400
Token his
Token ID465
Feature activation+8.61e-02

Pos logit contributions
wash+0.009
+0.009
pak+0.008
kat+0.008
gross+0.008
Neg logit contributions
 AST-0.009
elaide-0.009
outh-0.009
igree-0.009
 Monarch-0.009
Token penis
Token ID16360
Feature activation-7.61e-02

Pos logit contributions
wash+0.172
+0.169
pak+0.161
kat+0.157
gross+0.157
Neg logit contributions
 AST-0.139
elaide-0.132
igree-0.131
outh-0.130
ovember-0.130
Token in
Token ID287
Feature activation+4.75e-02

Pos logit contributions
 AST+0.134
elaide+0.128
igree+0.127
outh+0.126
ovember+0.126
Neg logit contributions
wash-0.140
-0.138
pak-0.131
kat-0.127
gross-0.127
Token/
Token ID14
Feature activation+1.26e-01

Pos logit contributions
wash+0.206
+0.203
pak+0.193
kat+0.188
gross+0.188
Neg logit contributions
 AST-0.186
elaide-0.176
outh-0.174
igree-0.174
ovember-0.172
Token10
Token ID940
Feature activation-1.21e-01

Pos logit contributions
wash+0.181
+0.177
pak+0.166
kat+0.160
gross+0.159
Neg logit contributions
 AST-0.275
elaide-0.264
outh-0.262
igree-0.262
ovember-0.260
Token"
Token ID1
Feature activation+9.71e-02

Pos logit contributions
 AST+0.229
elaide+0.218
igree+0.217
outh+0.216
ovember+0.214
Neg logit contributions
wash-0.209
-0.205
pak-0.195
kat-0.189
gross-0.188
Token
Token ID198
Feature activation-3.49e-03

Pos logit contributions
wash+0.177
+0.174
pak+0.165
kat+0.161
gross+0.160
Neg logit contributions
 AST-0.173
elaide-0.166
igree-0.164
outh-0.163
ovember-0.162
Token
Token ID198
Feature activation-2.34e-02

Pos logit contributions
 AST+0.006
outh+0.005
 Monarch+0.005
 ADHD+0.005
 Lyme+0.005
Neg logit contributions
wash-0.007
-0.007
pak-0.006
gross-0.006
kat-0.006
Tokenhttp
Token ID4023
Feature activation+1.03e+00

Pos logit contributions
 AST+0.049
elaide+0.047
outh+0.047
igree+0.047
ovember+0.046
Neg logit contributions
wash-0.035
-0.035
pak-0.033
kat-0.031
gross-0.031
Token://
Token ID1378
Feature activation+8.63e-01

Pos logit contributions
wash+1.681
+1.660
pak+1.562
kat+1.515
gross+1.502
Neg logit contributions
 AST-2.036
elaide-1.976
igree-1.954
ovember-1.935
outh-1.934
Tokenthe
Token ID1169
Feature activation-3.38e-02

Pos logit contributions
wash+1.216
+1.189
pak+1.114
kat+1.075
gross+1.068
Neg logit contributions
 AST-1.897
elaide-1.832
igree-1.811
outh-1.807
ovember-1.807
Tokenhook
Token ID25480
Feature activation-5.03e-01

Pos logit contributions
 AST+0.067
elaide+0.064
igree+0.063
outh+0.063
ovember+0.063
Neg logit contributions
wash-0.055
-0.054
pak-0.051
kat-0.049
gross-0.049
Tokenjournal
Token ID24891
Feature activation-7.48e-01

Pos logit contributions
 AST+0.927
elaide+0.895
igree+0.889
outh+0.889
ovember+0.880
Neg logit contributions
wash-0.871
-0.868
pak-0.809
gross-0.787
kat-0.786
Token.
Token ID13
Feature activation-5.95e-03

Pos logit contributions
 AST+1.219
elaide+1.177
outh+1.168
igree+1.158
ovember+1.148
Neg logit contributions
-1.453
wash-1.453
pak-1.359
gross-1.328
kat-1.319
Token {
Token ID1391
Feature activation+1.94e-01

Pos logit contributions
 AST+0.360
elaide+0.343
outh+0.339
igree+0.338
ovember+0.335
Neg logit contributions
wash-0.387
-0.378
pak-0.362
kat-0.351
gross-0.351
Token1
Token ID16
Feature activation+8.97e-02

Pos logit contributions
wash+0.287
+0.281
pak+0.264
kat+0.254
gross+0.254
Neg logit contributions
 AST-0.411
elaide-0.396
igree-0.392
outh-0.392
ovember-0.390
Token,
Token ID11
Feature activation-1.18e-01

Pos logit contributions
wash+0.191
+0.188
pak+0.180
gross+0.176
kat+0.176
Neg logit contributions
 AST-0.133
outh-0.124
elaide-0.123
igree-0.122
ovember-0.121
Token 6
Token ID718
Feature activation+1.62e-01

Pos logit contributions
 AST+0.215
elaide+0.206
igree+0.203
outh+0.203
ovember+0.202
Neg logit contributions
wash-0.212
-0.208
pak-0.198
kat-0.192
gross-0.192
Token}
Token ID92
Feature activation-5.50e-01

Pos logit contributions
wash+0.290
+0.286
pak+0.271
kat+0.263
gross+0.262
Neg logit contributions
 AST-0.294
elaide-0.282
igree-0.279
outh-0.278
ovember-0.277
Token <
Token ID1279
Feature activation+1.03e+00

Pos logit contributions
 AST+0.899
elaide+0.850
outh+0.840
igree+0.839
ovember+0.832
Neg logit contributions
wash-1.090
-1.066
pak-1.022
kat-0.996
gross-0.995
Token->
Token ID3784
Feature activation+2.60e-01

Pos logit contributions
wash+1.412
+1.405
pak+1.298
kat+1.251
gross+1.222
Neg logit contributions
 AST-2.298
elaide-2.227
igree-2.202
outh-2.195
ovember-2.190
Token {
Token ID1391
Feature activation+1.39e-01

Pos logit contributions
wash+0.586
+0.581
pak+0.555
kat+0.543
gross+0.541
Neg logit contributions
 AST-0.350
elaide-0.332
igree-0.327
outh-0.326
ovember-0.325
Token2
Token ID17
Feature activation+1.12e-01

Pos logit contributions
wash+0.205
+0.201
pak+0.189
kat+0.182
gross+0.181
Neg logit contributions
 AST-0.296
elaide-0.285
igree-0.282
outh-0.282
ovember-0.281
Token,
Token ID11
Feature activation-1.58e-01

Pos logit contributions
wash+0.242
+0.237
pak+0.228
gross+0.223
kat+0.222
Neg logit contributions
 AST-0.164
outh-0.153
elaide-0.151
 Monarch-0.150
igree-0.149
Token 6
Token ID718
Feature activation+1.62e-01

Pos logit contributions
 AST+0.290
elaide+0.276
outh+0.273
igree+0.272
ovember+0.271
Neg logit contributions
wash-0.282
-0.277
pak-0.263
kat-0.255
gross-0.255
Token distinct
Token ID7310
Feature activation-4.73e-01

Pos logit contributions
wash+0.113
+0.112
pak+0.106
kat+0.103
gross+0.103
Neg logit contributions
 AST-0.103
elaide-0.099
igree-0.098
outh-0.098
ovember-0.097
Token flavor
Token ID9565
Feature activation+4.62e-01

Pos logit contributions
 AST+0.715
elaide+0.674
igree+0.667
outh+0.666
ovember+0.657
Neg logit contributions
wash-0.990
-0.979
pak-0.934
gross-0.910
kat-0.909
Token and
Token ID290
Feature activation-6.75e-03

Pos logit contributions
wash+0.870
+0.858
pak+0.815
kat+0.793
gross+0.791
Neg logit contributions
 AST-0.795
elaide-0.761
igree-0.751
outh-0.750
ovember-0.747
Token slightly
Token ID4622
Feature activation+5.28e-01

Pos logit contributions
 AST+0.012
elaide+0.011
outh+0.011
igree+0.011
ovember+0.011
Neg logit contributions
wash-0.012
-0.012
pak-0.012
kat-0.011
gross-0.011
Token green
Token ID4077
Feature activation+4.72e-01

Pos logit contributions
wash+0.998
+0.984
pak+0.933
kat+0.909
gross+0.906
Neg logit contributions
 AST-0.901
elaide-0.867
igree-0.856
ovember-0.852
outh-0.850
Token color
Token ID3124
Feature activation+1.02e+00

Pos logit contributions
wash+0.928
+0.918
pak+0.876
kat+0.853
gross+0.851
Neg logit contributions
 AST-0.770
elaide-0.732
igree-0.725
outh-0.725
ovember-0.715
Token and
Token ID290
Feature activation+8.55e-02

Pos logit contributions
wash+1.919
+1.888
pak+1.787
kat+1.739
gross+1.737
Neg logit contributions
 AST-1.761
elaide-1.696
igree-1.665
ovember-1.664
outh-1.660
Token is
Token ID318
Feature activation+1.43e-01

Pos logit contributions
wash+0.161
+0.159
pak+0.151
kat+0.147
gross+0.146
Neg logit contributions
 AST-0.148
elaide-0.140
igree-0.139
outh-0.139
ovember-0.138
Token easier
Token ID4577
Feature activation-5.92e-02

Pos logit contributions
wash+0.268
+0.264
pak+0.251
kat+0.244
gross+0.243
Neg logit contributions
 AST-0.247
elaide-0.237
igree-0.233
outh-0.233
ovember-0.232
Token to
Token ID284
Feature activation+6.63e-02

Pos logit contributions
 AST+0.114
elaide+0.110
outh+0.109
igree+0.108
ovember+0.108
Neg logit contributions
wash-0.099
-0.098
pak-0.092
kat-0.089
gross-0.089
Token make
Token ID787
Feature activation+2.51e-01

Pos logit contributions
wash+0.141
+0.139
pak+0.133
kat+0.130
gross+0.129
Neg logit contributions
 AST-0.098
elaide-0.093
igree-0.092
outh-0.091
ovember-0.091
Token joke
Token ID9707
Feature activation+2.35e-01

Pos logit contributions
 AST+0.162
elaide+0.157
igree+0.156
ovember+0.154
outh+0.154
Neg logit contributions
wash-0.221
-0.217
pak-0.206
kat-0.204
gross-0.201
Token,
Token ID11
Feature activation-2.41e-02

Pos logit contributions
wash+0.452
+0.446
pak+0.424
kat+0.413
gross+0.412
Neg logit contributions
 AST-0.395
elaide-0.378
igree-0.373
outh-0.372
ovember-0.370
Token and
Token ID290
Feature activation-4.37e-04

Pos logit contributions
 AST+0.041
elaide+0.039
igree+0.039
outh+0.039
ovember+0.038
Neg logit contributions
wash-0.046
-0.045
pak-0.043
kat-0.042
gross-0.042
Token the
Token ID262
Feature activation+7.84e-02

Pos logit contributions
 AST+0.001
elaide+0.001
igree+0.001
outh+0.001
ovember+0.001
Neg logit contributions
wash-0.001
-0.001
pak-0.001
kat-0.001
gross-0.001
Token steep
Token ID14559
Feature activation-1.88e-01

Pos logit contributions
wash+0.158
+0.156
pak+0.149
kat+0.145
gross+0.145
Neg logit contributions
 AST-0.125
elaide-0.118
igree-0.117
outh-0.117
ovember-0.116
Token incl
Token ID13358
Feature activation-1.33e+00

Pos logit contributions
 AST+0.319
elaide+0.304
igree+0.301
outh+0.300
ovember+0.297
Neg logit contributions
wash-0.359
-0.354
pak-0.337
kat-0.328
gross-0.328
Tokenines
Token ID1127
Feature activation-5.12e-01

Pos logit contributions
 AST+1.625
outh+1.521
igree+1.500
elaide+1.489
 Monarch+1.410
Neg logit contributions
wash-3.147
-3.071
pak-3.031
kat-2.950
200000-2.927
Token can
Token ID460
Feature activation-4.83e-02

Pos logit contributions
 AST+0.917
elaide+0.874
outh+0.866
igree+0.866
ovember+0.859
Neg logit contributions
wash-0.926
-0.915
pak-0.867
kat-0.844
gross-0.841
Token be
Token ID307
Feature activation+3.93e-02

Pos logit contributions
 AST+0.083
elaide+0.079
igree+0.078
outh+0.078
ovember+0.078
Neg logit contributions
wash-0.092
-0.090
pak-0.086
kat-0.083
gross-0.083
Token treacherous
Token ID45365
Feature activation-1.25e-01

Pos logit contributions
wash+0.076
+0.074
pak+0.071
gross+0.069
kat+0.069
Neg logit contributions
 AST-0.066
elaide-0.063
igree-0.062
ovember-0.062
outh-0.062
Token with
Token ID351
Feature activation+6.54e-02

Pos logit contributions
 AST+0.212
elaide+0.202
igree+0.200
outh+0.199
ovember+0.198
Neg logit contributions
wash-0.238
-0.235
pak-0.224
kat-0.218
gross-0.217
Token a
Token ID257
Feature activation+5.04e-03

Pos logit contributions
wash+0.046
+0.046
pak+0.044
kat+0.043
gross+0.042
Neg logit contributions
 AST-0.037
elaide-0.035
igree-0.035
outh-0.034
ovember-0.034
Token 1
Token ID352
Feature activation+1.08e-01

Pos logit contributions
wash+0.010
+0.009
pak+0.009
kat+0.009
gross+0.009
Neg logit contributions
 AST-0.009
elaide-0.008
igree-0.008
outh-0.008
ovember-0.008
Token,
Token ID11
Feature activation-5.50e-02

Pos logit contributions
wash+0.202
+0.199
pak+0.189
kat+0.184
gross+0.183
Neg logit contributions
 AST-0.186
elaide-0.179
igree-0.176
outh-0.176
ovember-0.175
Token000
Token ID830
Feature activation-2.26e-01

Pos logit contributions
 AST+0.130
elaide+0.126
igree+0.125
outh+0.125
ovember+0.124
Neg logit contributions
wash-0.068
-0.067
pak-0.061
kat-0.059
gross-0.058
Token ft
Token ID10117
Feature activation+2.82e-01

Pos logit contributions
 AST+0.257
elaide+0.237
igree+0.234
outh+0.233
ovember+0.231
Neg logit contributions
wash-0.558
-0.552
pak-0.532
kat-0.520
gross-0.519
Token incl
Token ID13358
Feature activation-1.33e+00

Pos logit contributions
wash+0.554
+0.547
pak+0.520
kat+0.507
gross+0.505
Neg logit contributions
 AST-0.463
elaide-0.443
igree-0.437
outh-0.436
ovember-0.435
Tokenine
Token ID500
Feature activation-4.00e-01

Pos logit contributions
 AST+1.822
outh+1.714
igree+1.712
elaide+1.707
ovember+1.641
Neg logit contributions
wash-2.930
-2.877
pak-2.805
kat-2.722
gross-2.698
Token over
Token ID625
Feature activation+9.84e-02

Pos logit contributions
 AST+0.642
elaide+0.607
igree+0.602
outh+0.600
ovember+0.595
Neg logit contributions
wash-0.799
-0.791
pak-0.756
kat-0.734
gross-0.733
Token 1
Token ID352
Feature activation+1.16e-01

Pos logit contributions
wash+0.205
+0.203
pak+0.194
kat+0.189
gross+0.189
Neg logit contributions
 AST-0.149
elaide-0.141
igree-0.140
outh-0.139
ovember-0.138
Token.
Token ID13
Feature activation-9.06e-02

Pos logit contributions
wash+0.236
+0.233
pak+0.222
kat+0.216
gross+0.216
Neg logit contributions
 AST-0.182
elaide-0.175
igree-0.172
outh-0.171
ovember-0.171
Token3
Token ID18
Feature activation+3.18e-02

Pos logit contributions
 AST+0.178
elaide+0.169
outh+0.169
igree+0.168
ovember+0.168
Neg logit contributions
wash-0.149
-0.146
pak-0.138
gross-0.134
kat-0.133
Token equivalent
Token ID7548
Feature activation-3.40e-01

Pos logit contributions
 AST+0.385
outh+0.361
elaide+0.361
igree+0.359
 Monarch+0.358
Neg logit contributions
wash-0.385
-0.379
pak-0.360
kat-0.348
gross-0.348
Token of
Token ID286
Feature activation-1.51e-01

Pos logit contributions
 AST+0.515
elaide+0.482
outh+0.478
igree+0.476
ovember+0.472
Neg logit contributions
wash-0.711
-0.703
pak-0.670
kat-0.656
gross-0.653
Token an
Token ID281
Feature activation-1.72e-01

Pos logit contributions
 AST+0.251
elaide+0.236
outh+0.235
igree+0.233
ovember+0.232
Neg logit contributions
wash-0.296
-0.292
pak-0.278
kat-0.271
gross-0.269
Token Olympic
Token ID11514
Feature activation-2.55e-01

Pos logit contributions
 AST+0.284
elaide+0.270
igree+0.267
outh+0.267
ovember+0.265
Neg logit contributions
wash-0.337
-0.333
pak-0.317
kat-0.309
gross-0.308
Token gymn
Token ID38581
Feature activation-2.32e-01

Pos logit contributions
 AST+0.376
elaide+0.354
outh+0.350
igree+0.350
ovember+0.347
Neg logit contributions
wash-0.542
-0.537
pak-0.512
gross-0.500
kat-0.499
Tokenastics
Token ID24232
Feature activation-1.31e+00

Pos logit contributions
 AST+0.365
outh+0.344
elaide+0.343
igree+0.341
ovember+0.339
Neg logit contributions
wash-0.470
-0.469
pak-0.444
gross-0.434
kat-0.430
Token routine
Token ID8027
Feature activation-8.52e-01

Pos logit contributions
 AST+1.954
outh+1.775
igree+1.752
 Monarch+1.750
 ADHD+1.748
Neg logit contributions
wash-2.792
-2.766
pak-2.637
gross-2.597
kat-2.565
Token for
Token ID329
Feature activation-1.75e-01

Pos logit contributions
 AST+1.388
elaide+1.301
outh+1.291
igree+1.290
ovember+1.277
Neg logit contributions
wash-1.678
-1.661
pak-1.588
kat-1.546
gross-1.543
Token the
Token ID262
Feature activation-1.63e-01

Pos logit contributions
 AST+0.278
elaide+0.261
outh+0.259
igree+0.258
ovember+0.257
Neg logit contributions
wash-0.353
-0.350
pak-0.333
kat-0.325
gross-0.324
Token speaker
Token ID10834
Feature activation+2.68e-01

Pos logit contributions
 AST+0.265
elaide+0.250
outh+0.248
igree+0.247
ovember+0.246
Neg logit contributions
wash-0.325
-0.321
pak-0.306
kat-0.298
gross-0.298
Token
Token ID447
Feature activation-2.23e-01

Pos logit contributions
wash+0.516
+0.509
pak+0.484
kat+0.471
gross+0.470
Neg logit contributions
 AST-0.451
elaide-0.431
igree-0.426
outh-0.425
ovember-0.423
Token quickly
Token ID2952
Feature activation+9.32e-03

Pos logit contributions
wash+0.026
+0.026
pak+0.025
kat+0.024
gross+0.024
Neg logit contributions
 AST-0.027
elaide-0.025
igree-0.025
outh-0.025
ovember-0.025
Token came
Token ID1625
Feature activation-6.99e-02

Pos logit contributions
wash+0.016
+0.016
pak+0.015
kat+0.015
gross+0.015
Neg logit contributions
 AST-0.017
elaide-0.016
igree-0.016
outh-0.016
ovember-0.016
Token to
Token ID284
Feature activation-4.30e-02

Pos logit contributions
 AST+0.122
elaide+0.117
igree+0.115
outh+0.115
ovember+0.115
Neg logit contributions
wash-0.130
-0.128
pak-0.122
kat-0.118
gross-0.118
Token a
Token ID257
Feature activation-1.73e-02

Pos logit contributions
 AST+0.063
elaide+0.060
igree+0.059
outh+0.059
ovember+0.058
Neg logit contributions
wash-0.092
-0.091
pak-0.087
kat-0.085
gross-0.084
Token steep
Token ID14559
Feature activation-2.00e-01

Pos logit contributions
 AST+0.028
elaide+0.027
igree+0.026
outh+0.026
ovember+0.026
Neg logit contributions
wash-0.034
-0.034
pak-0.032
kat-0.031
gross-0.031
Token incl
Token ID13358
Feature activation-1.30e+00

Pos logit contributions
 AST+0.329
elaide+0.315
igree+0.310
outh+0.310
ovember+0.308
Neg logit contributions
wash-0.392
-0.387
pak-0.368
kat-0.358
gross-0.357
Tokenine
Token ID500
Feature activation-5.07e-01

Pos logit contributions
 AST+1.795
outh+1.695
igree+1.689
elaide+1.686
ovember+1.628
Neg logit contributions
wash-2.829
-2.781
pak-2.715
kat-2.643
gross-2.627
Token at
Token ID379
Feature activation-1.30e-01

Pos logit contributions
 AST+0.820
elaide+0.777
igree+0.769
outh+0.769
ovember+0.762
Neg logit contributions
wash-1.003
-0.995
pak-0.949
kat-0.924
gross-0.922
Token mile
Token ID10591
Feature activation-7.24e-02

Pos logit contributions
 AST+0.196
elaide+0.187
igree+0.184
outh+0.183
ovember+0.183
Neg logit contributions
wash-0.272
-0.269
pak-0.256
kat-0.250
gross-0.250
Token 16
Token ID1467
Feature activation-2.08e-01

Pos logit contributions
 AST+0.119
elaide+0.113
outh+0.111
igree+0.111
ovember+0.110
Neg logit contributions
wash-0.142
-0.140
pak-0.134
gross-0.130
kat-0.130
Token.
Token ID13
Feature activation-1.08e-01

Pos logit contributions
 AST+0.340
elaide+0.324
igree+0.320
outh+0.320
ovember+0.317
Neg logit contributions
wash-0.409
-0.404
pak-0.385
kat-0.375
gross-0.374
Token year
Token ID614
Feature activation-6.83e-02

Pos logit contributions
 AST+0.169
elaide+0.161
igree+0.158
outh+0.157
ovember+0.156
Neg logit contributions
wash-0.307
-0.303
pak-0.290
kat-0.285
gross-0.283
Token was
Token ID373
Feature activation-3.17e-02

Pos logit contributions
 AST+0.110
elaide+0.105
igree+0.104
outh+0.103
ovember+0.103
Neg logit contributions
wash-0.136
-0.134
pak-0.128
kat-0.125
gross-0.125
Token last
Token ID938
Feature activation-2.50e-01

Pos logit contributions
 AST+0.055
elaide+0.052
igree+0.052
outh+0.052
ovember+0.051
Neg logit contributions
wash-0.060
-0.059
pak-0.056
kat-0.054
gross-0.054
Token year
Token ID614
Feature activation-7.53e-02

Pos logit contributions
 AST+0.328
elaide+0.312
igree+0.307
outh+0.304
ovember+0.303
Neg logit contributions
wash-0.571
-0.563
pak-0.540
kat-0.529
gross-0.527
Token,"
Token ID553
Feature activation-1.04e-01

Pos logit contributions
 AST+0.126
elaide+0.121
igree+0.119
outh+0.119
ovember+0.118
Neg logit contributions
wash-0.146
-0.143
pak-0.136
kat-0.133
gross-0.133
Token Stevens
Token ID20019
Feature activation-1.19e+00

Pos logit contributions
 AST+0.168
elaide+0.160
igree+0.158
outh+0.157
ovember+0.157
Neg logit contributions
wash-0.207
-0.205
pak-0.195
kat-0.190
gross-0.190
Token said
Token ID531
Feature activation-1.85e-01

Pos logit contributions
 AST+1.941
elaide+1.849
outh+1.829
igree+1.827
ovember+1.817
Neg logit contributions
wash-2.340
-2.309
pak-2.195
kat-2.141
gross-2.138
Token.
Token ID13
Feature activation-4.42e-02

Pos logit contributions
 AST+0.307
elaide+0.293
igree+0.289
outh+0.289
ovember+0.287
Neg logit contributions
wash-0.360
-0.356
pak-0.338
kat-0.329
gross-0.328
Token "
Token ID366
Feature activation-2.13e-01

Pos logit contributions
 AST+0.077
elaide+0.074
igree+0.073
outh+0.073
ovember+0.073
Neg logit contributions
wash-0.082
-0.081
pak-0.076
kat-0.074
gross-0.074
TokenI
Token ID40
Feature activation-4.09e-02

Pos logit contributions
 AST+0.418
elaide+0.403
igree+0.399
outh+0.397
ovember+0.396
Neg logit contributions
wash-0.351
-0.346
pak-0.326
kat-0.316
gross-0.314
Token don
Token ID836
Feature activation+2.02e-02

Pos logit contributions
 AST+0.074
elaide+0.071
igree+0.070
outh+0.070
ovember+0.069
Neg logit contributions
wash-0.074
-0.073
pak-0.069
kat-0.067
gross-0.067
Token resemble
Token ID22464
Feature activation+3.45e-02

Pos logit contributions
wash+0.800
+0.787
pak+0.750
kat+0.730
gross+0.727
Neg logit contributions
 AST-0.642
elaide-0.614
outh-0.604
igree-0.603
ovember-0.601
Token symptoms
Token ID7460
Feature activation-3.00e-01

Pos logit contributions
wash+0.067
+0.066
pak+0.063
kat+0.061
gross+0.061
Neg logit contributions
 AST-0.058
elaide-0.055
igree-0.054
outh-0.054
ovember-0.054
Token of
Token ID286
Feature activation-5.62e-02

Pos logit contributions
 AST+0.464
elaide+0.439
igree+0.434
outh+0.434
ovember+0.430
Neg logit contributions
wash-0.617
-0.610
pak-0.581
kat-0.568
gross-0.566
Token schizophrenia
Token ID22794
Feature activation-3.44e-01

Pos logit contributions
 AST+0.078
elaide+0.074
igree+0.072
outh+0.072
ovember+0.072
Neg logit contributions
wash-0.125
-0.123
pak-0.118
kat-0.115
gross-0.115
Token called
Token ID1444
Feature activation-3.75e-01

Pos logit contributions
 AST+0.547
elaide+0.519
igree+0.512
outh+0.512
ovember+0.507
Neg logit contributions
wash-0.694
-0.686
pak-0.654
kat-0.638
gross-0.637
Token derail
Token ID33749
Feature activation-1.19e+00

Pos logit contributions
 AST+0.579
elaide+0.546
outh+0.540
igree+0.538
ovember+0.534
Neg logit contributions
wash-0.775
-0.767
pak-0.731
kat-0.714
gross-0.712
Tokenment
Token ID434
Feature activation-3.23e-01

Pos logit contributions
 AST+2.355
elaide+2.245
igree+2.229
outh+2.219
ovember+2.214
Neg logit contributions
wash-1.888
-1.860
pak-1.775
kat-1.704
gross-1.696
Token and
Token ID290
Feature activation-3.85e-02

Pos logit contributions
 AST+0.442
elaide+0.416
igree+0.409
outh+0.409
ovember+0.406
Neg logit contributions
wash-0.723
-0.715
pak-0.685
kat-0.670
gross-0.668
Token delusion
Token ID40969
Feature activation-1.71e-01

Pos logit contributions
 AST+0.059
elaide+0.056
igree+0.056
outh+0.055
ovember+0.055
Neg logit contributions
wash-0.079
-0.079
pak-0.075
kat-0.073
gross-0.073
Token.
Token ID13
Feature activation+1.31e-01

Pos logit contributions
 AST+0.269
elaide+0.255
outh+0.252
igree+0.252
 Monarch+0.249
Neg logit contributions
wash-0.347
-0.343
pak-0.327
kat-0.320
gross-0.318
Token In
Token ID554
Feature activation-4.46e-02

Pos logit contributions
wash+0.246
+0.243
pak+0.231
kat+0.224
gross+0.222
Neg logit contributions
 AST-0.224
elaide-0.219
igree-0.216
ovember-0.215
outh-0.214
TokenC
Token ID34
Feature activation+8.19e-02

Pos logit contributions
 AST+0.134
elaide+0.129
outh+0.127
igree+0.127
ovember+0.127
Neg logit contributions
wash-0.134
-0.132
pak-0.125
kat-0.121
gross-0.121
Tokenelt
Token ID2120
Feature activation+2.71e-01

Pos logit contributions
wash+0.082
+0.081
pak+0.074
kat+0.070
gross+0.068
Neg logit contributions
 AST-0.211
outh-0.206
elaide-0.205
igree-0.204
ovember-0.204
Tokenics
Token ID873
Feature activation-4.00e-01

Pos logit contributions
wash+0.546
+0.538
pak+0.512
gross+0.499
kat+0.499
Neg logit contributions
 AST-0.434
elaide-0.408
outh-0.408
igree-0.407
ovember-0.404
Token coach
Token ID3985
Feature activation-2.93e-01

Pos logit contributions
 AST+0.419
elaide+0.378
outh+0.377
igree+0.374
ovember+0.372
Neg logit contributions
wash-1.025
-1.017
pak-0.979
kat-0.962
gross-0.959
Token Brad
Token ID8114
Feature activation-2.70e-01

Pos logit contributions
 AST+0.494
elaide+0.473
igree+0.466
outh+0.466
ovember+0.464
Neg logit contributions
wash-0.560
-0.552
pak-0.525
kat-0.511
gross-0.510
Token Stevens
Token ID20019
Feature activation-1.18e+00

Pos logit contributions
 AST+0.417
igree+0.393
elaide+0.393
outh+0.390
ovember+0.388
Neg logit contributions
wash-0.557
-0.549
pak-0.522
kat-0.510
gross-0.508
Token isn
Token ID2125
Feature activation-6.09e-02

Pos logit contributions
 AST+1.928
outh+1.805
elaide+1.805
ovember+1.798
igree+1.795
Neg logit contributions
wash-2.301
-2.279
pak-2.161
kat-2.111
gross-2.103
Token't
Token ID470
Feature activation-1.25e-01

Pos logit contributions
 AST+0.122
outh+0.116
elaide+0.114
 ADHD+0.114
ovember+0.114
Neg logit contributions
wash-0.097
-0.095
pak-0.090
gross-0.087
kat-0.087
Token sure
Token ID1654
Feature activation-6.59e-02

Pos logit contributions
 AST+0.222
elaide+0.213
igree+0.211
outh+0.210
ovember+0.209
Neg logit contributions
wash-0.227
-0.224
pak-0.212
kat-0.206
gross-0.206
Token if
Token ID611
Feature activation-5.30e-02

Pos logit contributions
 AST+0.104
elaide+0.100
igree+0.098
outh+0.097
ovember+0.097
Neg logit contributions
wash-0.134
-0.132
pak-0.125
kat-0.122
gross-0.122
Token any
Token ID597
Feature activation+6.76e-02

Pos logit contributions
 AST+0.071
elaide+0.068
igree+0.067
outh+0.067
ovember+0.066
Neg logit contributions
wash-0.119
-0.118
pak-0.112
gross-0.110
kat-0.110
Token Pennsylvania
Token ID9589
Feature activation-1.64e-01

Pos logit contributions
wash+0.387
+0.382
pak+0.365
kat+0.356
gross+0.355
Neg logit contributions
 AST-0.285
elaide-0.271
igree-0.267
outh-0.267
ovember-0.265
Token's
Token ID338
Feature activation+1.52e-03

Pos logit contributions
 AST+0.284
elaide+0.270
igree+0.267
outh+0.267
ovember+0.265
Neg logit contributions
wash-0.308
-0.304
pak-0.289
kat-0.281
gross-0.280
Token Th
Token ID536
Feature activation-2.31e-01

Pos logit contributions
wash+0.003
+0.003
pak+0.003
kat+0.003
gross+0.003
Neg logit contributions
 AST-0.003
elaide-0.002
igree-0.002
outh-0.002
ovember-0.002
Tokenadd
Token ID2860
Feature activation-2.86e-01

Pos logit contributions
 AST+0.401
elaide+0.384
outh+0.380
igree+0.379
ovember+0.377
Neg logit contributions
wash-0.431
-0.426
pak-0.404
kat-0.392
gross-0.392
Tokeneus
Token ID27650
Feature activation-6.13e-02

Pos logit contributions
 AST+0.429
elaide+0.405
ovember+0.401
igree+0.400
outh+0.396
Neg logit contributions
wash-0.603
-0.593
pak-0.566
kat-0.554
gross-0.554
Token Stevens
Token ID20019
Feature activation-1.17e+00

Pos logit contributions
 AST+0.095
elaide+0.090
igree+0.089
outh+0.089
ovember+0.088
Neg logit contributions
wash-0.126
-0.125
pak-0.119
kat-0.116
gross-0.116
Token,
Token ID11
Feature activation+1.34e-02

Pos logit contributions
 AST+1.723
outh+1.608
elaide+1.607
igree+1.605
 Monarch+1.594
Neg logit contributions
wash-2.480
-2.443
pak-2.336
gross-2.281
kat-2.272
Token who
Token ID508
Feature activation+5.23e-02

Pos logit contributions
wash+0.027
+0.027
pak+0.025
kat+0.025
gross+0.025
Neg logit contributions
 AST-0.021
elaide-0.020
igree-0.020
outh-0.020
ovember-0.020
Token represented
Token ID7997
Feature activation-2.36e-02

Pos logit contributions
wash+0.100
+0.098
pak+0.093
kat+0.091
gross+0.091
Neg logit contributions
 AST-0.089
elaide-0.085
igree-0.084
outh-0.084
ovember-0.083
Token the
Token ID262
Feature activation+5.13e-02

Pos logit contributions
 AST+0.033
elaide+0.031
igree+0.031
outh+0.031
ovember+0.031
Neg logit contributions
wash-0.052
-0.051
pak-0.049
kat-0.048
gross-0.048
Token mining
Token ID9691
Feature activation-3.45e-01

Pos logit contributions
wash+0.102
+0.101
pak+0.096
kat+0.094
gross+0.093
Neg logit contributions
 AST-0.083
elaide-0.079
igree-0.078
outh-0.078
ovember-0.077
Tokenwww
Token ID2503
Feature activation+4.48e-02

Pos logit contributions
+0.813
wash+0.803
pak+0.717
kat+0.682
Net+0.679
Neg logit contributions
 AST-1.764
outh-1.736
elaide-1.724
igree-1.708
ovember-1.678
Token.
Token ID13
Feature activation+1.17e-02

Pos logit contributions
wash+0.091
+0.090
pak+0.086
gross+0.085
kat+0.084
Neg logit contributions
 AST-0.069
outh-0.065
 ADHD-0.064
 Monarch-0.063
elaide-0.063
Tokenbel
Token ID6667
Feature activation-1.45e-01

Pos logit contributions
+0.016
wash+0.015
pak+0.014
kat+0.013
200000+0.013
Neg logit contributions
 AST-0.026
outh-0.026
elaide-0.026
igree-0.026
 Lyme-0.025
Tokenfast
Token ID7217
Feature activation+4.17e-03

Pos logit contributions
 AST+0.247
elaide+0.236
igree+0.233
outh+0.233
ovember+0.232
Neg logit contributions
wash-0.274
-0.271
pak-0.257
kat-0.250
gross-0.249
Tokente
Token ID660
Feature activation-5.58e-03

Pos logit contributions
wash+0.007
+0.007
pak+0.007
kat+0.007
gross+0.007
Neg logit contributions
 AST-0.008
elaide-0.007
igree-0.007
outh-0.007
ovember-0.007
Tokenlegraph
Token ID16606
Feature activation-1.16e+00

Pos logit contributions
 AST+0.007
elaide+0.006
outh+0.006
igree+0.006
roit+0.006
Neg logit contributions
wash-0.013
-0.013
pak-0.012
200000-0.012
gross-0.012
Token.
Token ID13
Feature activation+6.74e-03

Pos logit contributions
 AST+1.745
outh+1.660
elaide+1.620
 ADHD+1.600
 Monarch+1.587
Neg logit contributions
wash-2.388
-2.355
pak-2.253
gross-2.220
kat-2.168
Tokenco
Token ID1073
Feature activation-6.45e-02

Pos logit contributions
wash+0.014
+0.014
pak+0.013
kat+0.013
gross+0.013
Neg logit contributions
 AST-0.010
elaide-0.009
outh-0.009
igree-0.009
ovember-0.009
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
 AST+0.107
elaide+0.101
outh+0.101
igree+0.100
ovember+0.099
Neg logit contributions
wash-0.126
-0.124
pak-0.118
gross-0.115
kat-0.115
Tokenuk
Token ID2724
Feature activation-3.14e-02

Pos logit contributions
 AST+0.026
elaide+0.024
outh+0.024
igree+0.024
ovember+0.024
Neg logit contributions
wash-0.027
-0.027
pak-0.025
gross-0.025
kat-0.025
Token/
Token ID14
Feature activation+1.06e-04

Pos logit contributions
 AST+0.054
elaide+0.052
outh+0.051
igree+0.051
ovember+0.051
Neg logit contributions
wash-0.059
-0.058
pak-0.055
kat-0.054
gross-0.054
Token House
Token ID2097
Feature activation-1.80e-01

Pos logit contributions
 AST+0.026
elaide+0.025
igree+0.025
outh+0.025
ovember+0.024
Neg logit contributions
wash-0.032
-0.032
pak-0.030
kat-0.030
gross-0.030
Token of
Token ID286
Feature activation+1.67e-02

Pos logit contributions
 AST+0.287
elaide+0.273
igree+0.269
outh+0.269
ovember+0.267
Neg logit contributions
wash-0.362
-0.358
pak-0.341
kat-0.332
gross-0.331
Token Representatives
Token ID17132
Feature activation+9.21e-02

Pos logit contributions
wash+0.027
+0.027
pak+0.025
kat+0.025
gross+0.025
Neg logit contributions
 AST-0.033
elaide-0.031
igree-0.031
outh-0.031
ovember-0.031
Token (
Token ID357
Feature activation+9.60e-03

Pos logit contributions
wash+0.169
+0.167
pak+0.158
kat+0.154
gross+0.153
Neg logit contributions
 AST-0.163
elaide-0.156
igree-0.154
outh-0.154
ovember-0.153
Tokenthe
Token ID1169
Feature activation+9.48e-02

Pos logit contributions
wash+0.015
+0.015
pak+0.014
kat+0.014
gross+0.014
Neg logit contributions
 AST-0.019
elaide-0.019
outh-0.018
igree-0.018
ovember-0.018
Token lower
Token ID2793
Feature activation-1.16e+00

Pos logit contributions
wash+0.204
+0.202
pak+0.193
kat+0.188
gross+0.188
Neg logit contributions
 AST-0.138
elaide-0.131
igree-0.129
outh-0.128
ovember-0.128
Token house
Token ID2156
Feature activation+1.36e-01

Pos logit contributions
 AST+1.904
elaide+1.792
igree+1.780
 Monarch+1.774
outh+1.773
Neg logit contributions
wash-2.270
-2.260
pak-2.142
kat-2.090
gross-2.074
Token)
Token ID8
Feature activation+7.34e-02

Pos logit contributions
wash+0.248
+0.244
pak+0.232
kat+0.225
gross+0.224
Neg logit contributions
 AST-0.243
elaide-0.232
igree-0.229
outh-0.229
ovember-0.228
Token has
Token ID468
Feature activation+8.99e-03

Pos logit contributions
wash+0.132
+0.130
pak+0.123
kat+0.120
gross+0.119
Neg logit contributions
 AST-0.133
elaide-0.127
outh-0.125
igree-0.125
ovember-0.125
Token 150
Token ID6640
Feature activation+7.54e-02

Pos logit contributions
wash+0.018
+0.018
pak+0.017
kat+0.016
gross+0.016
Neg logit contributions
 AST-0.015
elaide-0.014
outh-0.014
igree-0.014
ovember-0.014
Token members
Token ID1866
Feature activation+3.18e-01

Pos logit contributions
wash+0.116
+0.113
pak+0.106
kat+0.103
gross+0.102
Neg logit contributions
 AST-0.157
elaide-0.151
outh-0.149
igree-0.149
ovember-0.148
Token basketball
Token ID9669
Feature activation-1.08e-01

Pos logit contributions
wash+0.178
+0.176
pak+0.168
kat+0.163
gross+0.163
Neg logit contributions
 AST-0.142
elaide-0.136
igree-0.135
outh-0.134
ovember-0.133
Token won
Token ID1839
Feature activation-1.63e-02

Pos logit contributions
 AST+0.186
elaide+0.178
igree+0.176
outh+0.175
ovember+0.175
Neg logit contributions
wash-0.202
-0.200
pak-0.189
kat-0.184
gross-0.184
Token out
Token ID503
Feature activation-1.11e-01

Pos logit contributions
 AST+0.030
elaide+0.029
igree+0.028
outh+0.028
ovember+0.028
Neg logit contributions
wash-0.029
-0.028
pak-0.027
kat-0.026
gross-0.026
Token.
Token ID13
Feature activation+6.34e-02

Pos logit contributions
 AST+0.183
elaide+0.175
igree+0.172
outh+0.172
ovember+0.171
Neg logit contributions
wash-0.215
-0.213
pak-0.202
kat-0.197
gross-0.196
Token A
Token ID317
Feature activation+6.78e-02

Pos logit contributions
wash+0.120
+0.119
pak+0.113
kat+0.110
gross+0.110
Neg logit contributions
 AST-0.107
elaide-0.104
igree-0.103
outh-0.102
ovember-0.102
Token court
Token ID2184
Feature activation-1.15e+00

Pos logit contributions
wash+0.137
+0.135
pak+0.129
kat+0.125
gross+0.125
Neg logit contributions
 AST-0.108
elaide-0.103
igree-0.101
outh-0.101
ovember-0.100
Token was
Token ID373
Feature activation-4.22e-02

Pos logit contributions
 AST+1.866
elaide+1.772
igree+1.754
outh+1.752
ovember+1.743
Neg logit contributions
wash-2.276
-2.263
pak-2.155
kat-2.095
gross-2.090
Token set
Token ID900
Feature activation-3.98e-01

Pos logit contributions
 AST+0.075
elaide+0.072
igree+0.071
outh+0.071
ovember+0.070
Neg logit contributions
wash-0.077
-0.076
pak-0.072
kat-0.070
gross-0.070
Token up
Token ID510
Feature activation+1.63e-02

Pos logit contributions
 AST+0.552
elaide+0.524
igree+0.517
outh+0.513
ovember+0.513
Neg logit contributions
wash-0.882
-0.869
pak-0.832
kat-0.815
gross-0.811
Token,
Token ID11
Feature activation-5.06e-02

Pos logit contributions
wash+0.031
+0.031
pak+0.029
kat+0.029
gross+0.029
Neg logit contributions
 AST-0.027
elaide-0.026
igree-0.026
outh-0.026
ovember-0.025
Token concrete
Token ID10017
Feature activation-2.24e-01

Pos logit contributions
 AST+0.080
elaide+0.077
igree+0.075
outh+0.075
ovember+0.075
Neg logit contributions
wash-0.102
-0.101
pak-0.096
kat-0.094
gross-0.094
Token goals
Token ID4661
Feature activation-2.10e-01

Pos logit contributions
 AST+0.182
elaide+0.174
ovember+0.172
igree+0.172
outh+0.171
Neg logit contributions
wash-0.237
-0.234
pak-0.223
kat-0.217
gross-0.217
Token or
Token ID393
Feature activation-1.03e-01

Pos logit contributions
 AST+0.346
elaide+0.331
igree+0.326
outh+0.326
ovember+0.324
Neg logit contributions
wash-0.410
-0.404
pak-0.384
kat-0.375
gross-0.373
Token hitting
Token ID9008
Feature activation-4.68e-01

Pos logit contributions
 AST+0.163
elaide+0.156
igree+0.154
outh+0.154
ovember+0.153
Neg logit contributions
wash-0.208
-0.205
pak-0.196
kat-0.191
gross-0.191
Token cross
Token ID3272
Feature activation-5.53e-01

Pos logit contributions
 AST+0.734
elaide+0.697
igree+0.688
outh+0.686
ovember+0.681
Neg logit contributions
wash-0.953
-0.941
pak-0.898
kat-0.876
gross-0.873
Token-
Token ID12
Feature activation-2.42e-01

Pos logit contributions
 AST+0.906
elaide+0.858
igree+0.851
outh+0.841
ovember+0.836
Neg logit contributions
wash-1.092
-1.082
pak-1.026
gross-0.998
kat-0.996
Tokencourt
Token ID22230
Feature activation-1.15e+00

Pos logit contributions
 AST+0.367
elaide+0.350
igree+0.345
outh+0.341
ovember+0.336
Neg logit contributions
wash-0.504
-0.501
pak-0.475
gross-0.464
kat-0.464
Token winners
Token ID14591
Feature activation-2.04e-01

Pos logit contributions
 AST+1.824
elaide+1.728
igree+1.704
outh+1.699
 Monarch+1.675
Neg logit contributions
wash-2.343
-2.313
pak-2.208
gross-2.153
kat-2.145
Token when
Token ID618
Feature activation-1.31e-01

Pos logit contributions
 AST+0.339
elaide+0.324
igree+0.320
outh+0.319
ovember+0.317
Neg logit contributions
wash-0.395
-0.390
pak-0.371
kat-0.361
gross-0.360
Token a
Token ID257
Feature activation-6.73e-02

Pos logit contributions
 AST+0.188
elaide+0.179
igree+0.176
outh+0.175
ovember+0.175
Neg logit contributions
wash-0.284
-0.280
pak-0.268
kat-0.262
gross-0.261
Token child
Token ID1200
Feature activation-6.66e-01

Pos logit contributions
 AST+0.101
elaide+0.096
igree+0.095
ovember+0.094
outh+0.094
Neg logit contributions
wash-0.141
-0.140
pak-0.133
kat-0.130
gross-0.130
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
 AST+1.149
elaide+1.100
igree+1.086
outh+1.084
ovember+1.079
Neg logit contributions
wash-1.250
-1.233
pak-1.171
kat-1.139
gross-1.136
Token:
Token ID25
Feature activation-6.03e-03

Pos logit contributions
wash+0.104
+0.103
pak+0.098
kat+0.096
gross+0.095
Neg logit contributions
 AST-0.084
elaide-0.080
igree-0.079
outh-0.079
ovember-0.079
Token
Token ID198
Feature activation-1.75e-01

Pos logit contributions
 AST+0.011
elaide+0.011
igree+0.011
outh+0.010
ovember+0.010
Neg logit contributions
wash-0.011
-0.010
pak-0.010
kat-0.010
gross-0.010
Token
Token ID198
Feature activation-1.36e-01

Pos logit contributions
 AST+0.283
outh+0.264
 ADHD+0.259
 Monarch+0.259
 Lyme+0.259
Neg logit contributions
wash-0.348
-0.340
pak-0.327
gross-0.319
kat-0.317
Token13
Token ID1485
Feature activation-3.77e-02

Pos logit contributions
 AST+0.258
elaide+0.248
outh+0.246
ovember+0.245
igree+0.245
Neg logit contributions
wash-0.228
-0.222
pak-0.212
kat-0.205
gross-0.204
Token PH
Token ID9370
Feature activation-1.50e-01

Pos logit contributions
 AST+0.066
elaide+0.063
igree+0.063
outh+0.062
ovember+0.062
Neg logit contributions
wash-0.070
-0.069
pak-0.065
kat-0.063
gross-0.063
TokenOTOS
Token ID33291
Feature activation-1.15e+00

Pos logit contributions
 AST+0.151
elaide+0.139
igree+0.136
outh+0.135
ovember+0.134
Neg logit contributions
wash-0.389
-0.385
pak-0.372
kat-0.365
gross-0.363
Token Donald
Token ID3759
Feature activation-3.50e-01

Pos logit contributions
 AST+1.780
outh+1.655
 Monarch+1.641
elaide+1.627
ovember+1.626
Neg logit contributions
wash-2.383
-2.338
pak-2.227
kat-2.189
gross-2.182
Token Trump
Token ID1301
Feature activation-5.71e-02

Pos logit contributions
 AST+0.513
outh+0.476
elaide+0.475
ovember+0.474
igree+0.471
Neg logit contributions
wash-0.748
-0.739
pak-0.704
gross-0.691
kat-0.690
Token's
Token ID338
Feature activation+8.37e-02

Pos logit contributions
 AST+0.100
elaide+0.095
igree+0.094
outh+0.094
ovember+0.094
Neg logit contributions
wash-0.106
-0.104
pak-0.099
kat-0.097
gross-0.096
Token potential
Token ID2785
Feature activation+2.66e-02

Pos logit contributions
wash+0.159
+0.157
pak+0.149
kat+0.145
gross+0.145
Neg logit contributions
 AST-0.143
elaide-0.137
igree-0.135
outh-0.134
ovember-0.134
Token running
Token ID2491
Feature activation+1.60e-01

Pos logit contributions
wash+0.062
+0.061
pak+0.059
kat+0.057
gross+0.057
Neg logit contributions
 AST-0.034
elaide-0.032
outh-0.032
igree-0.032
ovember-0.031
Tokenwww
Token ID2503
Feature activation+1.51e-01

Pos logit contributions
+0.840
wash+0.831
pak+0.731
kat+0.697
gross+0.696
Neg logit contributions
 AST-1.969
outh-1.928
elaide-1.921
igree-1.904
ovember-1.885
Token.
Token ID13
Feature activation-4.40e-02

Pos logit contributions
wash+0.300
+0.296
pak+0.283
gross+0.277
kat+0.274
Neg logit contributions
 AST-0.241
outh-0.228
elaide-0.223
 Monarch-0.222
 ADHD-0.222
Tokenbel
Token ID6667
Feature activation-1.60e-02

Pos logit contributions
outh+0.099
 AST+0.098
elaide+0.098
igree+0.097
ovember+0.094
Neg logit contributions
-0.059
wash-0.056
pak-0.051
200000-0.050
kat-0.049
Tokenfast
Token ID7217
Feature activation-3.10e-02

Pos logit contributions
 AST+0.026
elaide+0.025
outh+0.025
igree+0.025
ovember+0.025
Neg logit contributions
wash-0.031
-0.031
pak-0.029
kat-0.029
gross-0.028
Tokente
Token ID660
Feature activation+4.07e-02

Pos logit contributions
 AST+0.056
elaide+0.054
outh+0.053
igree+0.053
ovember+0.052
Neg logit contributions
wash-0.056
-0.055
pak-0.052
gross-0.050
kat-0.050
Tokenlegraph
Token ID16606
Feature activation-1.14e+00

Pos logit contributions
wash+0.091
+0.090
pak+0.086
gross+0.084
kat+0.084
Neg logit contributions
 AST-0.056
elaide-0.053
outh-0.052
igree-0.052
ovember-0.051
Token.
Token ID13
Feature activation-6.63e-02

Pos logit contributions
 AST+1.737
outh+1.640
elaide+1.595
 ADHD+1.590
 Monarch+1.581
Neg logit contributions
wash-2.338
-2.298
pak-2.206
gross-2.176
kat-2.133
Tokenco
Token ID1073
Feature activation+1.54e-02

Pos logit contributions
 AST+0.098
outh+0.093
elaide+0.092
igree+0.091
 Monarch+0.090
Neg logit contributions
wash-0.139
-0.138
pak-0.130
kat-0.128
gross-0.128
Token.
Token ID13
Feature activation-9.04e-02

Pos logit contributions
wash+0.030
+0.030
pak+0.029
gross+0.028
kat+0.028
Neg logit contributions
 AST-0.025
outh-0.024
elaide-0.024
ovember-0.023
igree-0.023
Tokenuk
Token ID2724
Feature activation+4.82e-02

Pos logit contributions
 AST+0.158
outh+0.150
elaide+0.150
igree+0.147
ovember+0.147
Neg logit contributions
wash-0.166
-0.164
pak-0.155
gross-0.152
kat-0.151
Token/
Token ID14
Feature activation+9.82e-03

Pos logit contributions
wash+0.091
+0.090
pak+0.085
gross+0.083
kat+0.083
Neg logit contributions
 AST-0.083
elaide-0.078
outh-0.078
ovember-0.077
igree-0.077
Token and
Token ID290
Feature activation+2.46e-02

Pos logit contributions
 AST+0.448
elaide+0.426
igree+0.420
outh+0.419
ovember+0.417
Neg logit contributions
wash-0.565
-0.558
pak-0.532
kat-0.519
gross-0.517
Token ore
Token ID23751
Feature activation-8.07e-02

Pos logit contributions
wash+0.046
+0.046
pak+0.043
kat+0.042
gross+0.042
Neg logit contributions
 AST-0.042
elaide-0.040
igree-0.040
outh-0.040
ovember-0.040
Token refinement
Token ID47517
Feature activation+1.90e-01

Pos logit contributions
 AST+0.131
elaide+0.125
igree+0.124
outh+0.123
ovember+0.123
Neg logit contributions
wash-0.160
-0.158
pak-0.150
kat-0.146
gross-0.146
Token machinery
Token ID20230
Feature activation+1.70e-01

Pos logit contributions
wash+0.363
+0.359
pak+0.340
kat+0.331
gross+0.330
Neg logit contributions
 AST-0.322
elaide-0.308
igree-0.304
outh-0.304
ovember-0.302
Token,
Token ID11
Feature activation-2.29e-02

Pos logit contributions
wash+0.333
+0.329
pak+0.313
kat+0.305
gross+0.304
Neg logit contributions
 AST-0.280
elaide-0.267
igree-0.264
outh-0.263
ovember-0.262
Token Stevens
Token ID20019
Feature activation-1.13e+00

Pos logit contributions
 AST+0.038
elaide+0.036
igree+0.035
outh+0.035
ovember+0.035
Neg logit contributions
wash-0.045
-0.044
pak-0.042
kat-0.041
gross-0.041
Token related
Token ID3519
Feature activation+1.92e-01

Pos logit contributions
 AST+1.890
elaide+1.780
outh+1.770
igree+1.768
ovember+1.764
Neg logit contributions
wash-2.162
-2.132
pak-2.025
kat-1.969
gross-1.965
Token,
Token ID11
Feature activation-2.97e-02

Pos logit contributions
wash+0.378
+0.373
pak+0.355
kat+0.346
gross+0.345
Neg logit contributions
 AST-0.313
elaide-0.299
igree-0.295
outh-0.294
ovember-0.293
Token and
Token ID290
Feature activation+7.68e-03

Pos logit contributions
 AST+0.049
elaide+0.046
igree+0.046
outh+0.046
ovember+0.045
Neg logit contributions
wash-0.058
-0.058
pak-0.055
kat-0.053
gross-0.053
Token it
Token ID340
Feature activation-5.11e-02

Pos logit contributions
wash+0.016
+0.015
pak+0.015
kat+0.014
gross+0.014
Neg logit contributions
 AST-0.012
elaide-0.012
igree-0.011
outh-0.011
ovember-0.011
Token was
Token ID373
Feature activation-2.67e-02

Pos logit contributions
 AST+0.089
elaide+0.085
igree+0.084
outh+0.084
ovember+0.083
Neg logit contributions
wash-0.095
-0.094
pak-0.089
kat-0.087
gross-0.087
Token the
Token ID262
Feature activation-9.85e-02

Pos logit contributions
 AST+0.221
elaide+0.211
igree+0.209
outh+0.208
ovember+0.207
Neg logit contributions
wash-0.261
-0.258
pak-0.245
kat-0.239
gross-0.238
Token prime
Token ID6994
Feature activation-4.58e-02

Pos logit contributions
 AST+0.181
elaide+0.173
outh+0.172
igree+0.171
ovember+0.170
Neg logit contributions
wash-0.174
-0.171
pak-0.162
kat-0.157
gross-0.157
Token challenge
Token ID4427
Feature activation-1.61e-01

Pos logit contributions
 AST+0.073
elaide+0.070
igree+0.069
outh+0.068
ovember+0.068
Neg logit contributions
wash-0.093
-0.091
pak-0.087
kat-0.085
gross-0.085
Token Belfast
Token ID29713
Feature activation-8.45e-02

Pos logit contributions
 AST+0.272
elaide+0.259
igree+0.256
outh+0.256
ovember+0.254
Neg logit contributions
wash-0.309
-0.304
pak-0.289
kat-0.282
gross-0.281
TokenTe
Token ID6767
Feature activation-1.56e-01

Pos logit contributions
 AST+0.141
elaide+0.134
outh+0.133
igree+0.132
ovember+0.131
Neg logit contributions
wash-0.164
-0.162
pak-0.154
kat-0.150
gross-0.150
Tokenlegraph
Token ID16606
Feature activation-1.12e+00

Pos logit contributions
 AST+0.202
elaide+0.191
igree+0.185
outh+0.185
ovember+0.184
Neg logit contributions
wash-0.365
-0.360
pak-0.346
gross-0.338
kat-0.335
Token.
Token ID13
Feature activation+2.00e-02

Pos logit contributions
 AST+1.781
elaide+1.637
outh+1.609
igree+1.607
 Lyme+1.604
Neg logit contributions
wash-2.298
-2.250
pak-2.168
gross-2.134
kat-2.079
Tokenco
Token ID1073
Feature activation-5.01e-02

Pos logit contributions
wash+0.043
+0.043
pak+0.041
gross+0.040
kat+0.040
Neg logit contributions
 AST-0.029
elaide-0.027
outh-0.027
 Monarch-0.026
igree-0.026
Token.
Token ID13
Feature activation-1.72e-02

Pos logit contributions
 AST+0.082
elaide+0.078
outh+0.078
igree+0.076
ovember+0.076
Neg logit contributions
wash-0.099
-0.097
pak-0.092
gross-0.090
kat-0.089
Tokenuk
Token ID2724
Feature activation-2.79e-02

Pos logit contributions
 AST+0.030
elaide+0.029
outh+0.029
igree+0.028
ovember+0.028
Neg logit contributions
wash-0.031
-0.031
pak-0.029
gross-0.029
kat-0.029
Token Dis
Token ID3167
Feature activation-4.64e-01

Pos logit contributions
 AST+0.046
elaide+0.044
igree+0.044
outh+0.044
ovember+0.043
Neg logit contributions
wash-0.054
-0.054
pak-0.051
kat-0.050
gross-0.050
Token like
Token ID588
Feature activation-5.64e-02

Pos logit contributions
wash+0.033
+0.033
pak+0.031
kat+0.030
gross+0.030
Neg logit contributions
 AST-0.027
elaide-0.026
igree-0.026
outh-0.026
ovember-0.026
Token public
Token ID1171
Feature activation+1.28e-01

Pos logit contributions
 AST+0.095
elaide+0.090
igree+0.089
outh+0.089
ovember+0.089
Neg logit contributions
wash-0.109
-0.107
pak-0.102
kat-0.099
gross-0.099
Tokenizing
Token ID2890
Feature activation+4.70e-02

Pos logit contributions
wash+0.257
+0.253
pak+0.241
kat+0.235
gross+0.234
Neg logit contributions
 AST-0.205
elaide-0.196
igree-0.194
outh-0.192
ovember-0.192
Token mar
Token ID1667
Feature activation+2.70e-01

Pos logit contributions
wash+0.098
+0.097
pak+0.092
kat+0.090
gross+0.090
Neg logit contributions
 AST-0.071
elaide-0.068
igree-0.067
outh-0.067
ovember-0.066
Tokenath
Token ID776
Feature activation+8.18e-02

Pos logit contributions
wash+0.477
+0.469
pak+0.447
kat+0.435
gross+0.432
Neg logit contributions
 AST-0.494
elaide-0.474
igree-0.468
outh-0.466
ovember-0.466
Tokenons
Token ID684
Feature activation-1.12e+00

Pos logit contributions
wash+0.186
+0.184
pak+0.176
kat+0.172
gross+0.172
Neg logit contributions
 AST-0.109
elaide-0.103
igree-0.101
outh-0.101
ovember-0.100
Token to
Token ID284
Feature activation-8.17e-02

Pos logit contributions
 AST+1.768
elaide+1.676
outh+1.673
ovember+1.650
igree+1.648
Neg logit contributions
wash-2.225
-2.189
pak-2.103
gross-2.038
kat-2.037
Token promote
Token ID7719
Feature activation+3.09e-01

Pos logit contributions
 AST+0.128
elaide+0.122
igree+0.121
outh+0.120
ovember+0.120
Neg logit contributions
wash-0.166
-0.164
pak-0.156
kat-0.152
gross-0.152
Token j
Token ID474
Feature activation-1.73e-01

Pos logit contributions
wash+0.635
+0.626
pak+0.596
kat+0.583
gross+0.581
Neg logit contributions
 AST-0.474
elaide-0.458
igree-0.453
outh-0.446
ovember-0.445
Tokenogging
Token ID30853
Feature activation+3.68e-01

Pos logit contributions
 AST+0.260
elaide+0.247
outh+0.243
igree+0.243
ovember+0.242
Neg logit contributions
wash-0.364
-0.360
pak-0.344
kat-0.335
gross-0.334
Token
Token ID960
Feature activation-1.37e-01

Pos logit contributions
wash+0.718
+0.712
pak+0.671
kat+0.658
gross+0.653
Neg logit contributions
 AST-0.608
elaide-0.582
igree-0.577
ovember-0.570
outh-0.569
Token well
Token ID880
Feature activation+4.35e-01

Pos logit contributions
wash+1.123
+1.095
pak+1.041
gross+1.010
kat+1.006
Neg logit contributions
 AST-1.177
elaide-1.153
ovember-1.136
igree-1.135
outh-1.124
Token.
Token ID13
Feature activation-9.30e-02

Pos logit contributions
wash+0.827
+0.814
pak+0.775
kat+0.753
gross+0.752
Neg logit contributions
 AST-0.735
elaide-0.709
igree-0.699
ovember-0.695
outh-0.695
Token
Token ID198
Feature activation-1.34e-01

Pos logit contributions
 AST+0.169
elaide+0.166
igree+0.163
ovember+0.163
outh+0.162
Neg logit contributions
wash-0.165
-0.163
pak-0.154
kat-0.150
gross-0.148
Token
Token ID198
Feature activation-1.19e-01

Pos logit contributions
 AST+0.219
outh+0.205
 ADHD+0.201
 Monarch+0.201
 Lyme+0.201
Neg logit contributions
wash-0.265
-0.260
pak-0.249
gross-0.244
kat-0.242
TokenCon
Token ID3103
Feature activation-2.63e-01

Pos logit contributions
 AST+0.230
elaide+0.221
igree+0.219
outh+0.218
ovember+0.217
Neg logit contributions
wash-0.198
-0.194
pak-0.184
kat-0.178
gross-0.177
Tokenclusions
Token ID11539
Feature activation-1.11e+00

Pos logit contributions
 AST+0.295
elaide+0.275
igree+0.270
outh+0.269
ovember+0.266
Neg logit contributions
wash-0.654
-0.647
pak-0.622
kat-0.610
gross-0.609
Token
Token ID198
Feature activation-2.29e-01

Pos logit contributions
 AST+1.875
elaide+1.760
igree+1.754
outh+1.748
ovember+1.740
Neg logit contributions
wash-2.152
-2.070
pak-2.009
kat-1.955
gross-1.949
Token
Token ID198
Feature activation-2.12e-01

Pos logit contributions
 AST+0.373
outh+0.348
 ADHD+0.342
 Monarch+0.342
 Lyme+0.341
Neg logit contributions
wash-0.455
-0.444
pak-0.426
gross-0.417
kat-0.415
TokenArthur
Token ID29874
Feature activation+2.16e-01

Pos logit contributions
 AST+0.405
elaide+0.389
igree+0.385
outh+0.384
ovember+0.383
Neg logit contributions
wash-0.357
-0.351
pak-0.332
kat-0.321
gross-0.321
Token Sch
Token ID3059
Feature activation-5.54e-02

Pos logit contributions
wash+0.442
+0.437
pak+0.417
kat+0.406
gross+0.405
Neg logit contributions
 AST-0.337
elaide-0.321
igree-0.316
outh-0.315
ovember-0.314
Tokenopen
Token ID9654
Feature activation-1.18e-01

Pos logit contributions
 AST+0.099
elaide+0.095
igree+0.093
outh+0.093
ovember+0.093
Neg logit contributions
wash-0.101
-0.100
pak-0.094
kat-0.092
gross-0.091
Token ends
Token ID5645
Feature activation-1.74e-01

Pos logit contributions
wash+0.203
+0.200
pak+0.190
kat+0.185
gross+0.184
Neg logit contributions
 AST-0.197
elaide-0.189
igree-0.187
outh-0.186
ovember-0.186
Token stand
Token ID1302
Feature activation-7.67e-02

Pos logit contributions
 AST+0.279
elaide+0.266
igree+0.263
outh+0.262
ovember+0.260
Neg logit contributions
wash-0.349
-0.346
pak-0.329
kat-0.320
gross-0.319
Token over
Token ID625
Feature activation+5.17e-02

Pos logit contributions
 AST+0.129
elaide+0.123
igree+0.122
outh+0.121
ovember+0.121
Neg logit contributions
wash-0.148
-0.145
pak-0.139
kat-0.135
gross-0.135
Token an
Token ID281
Feature activation-2.08e-02

Pos logit contributions
wash+0.110
+0.108
pak+0.103
kat+0.101
gross+0.101
Neg logit contributions
 AST-0.077
elaide-0.073
igree-0.072
outh-0.072
ovember-0.071
Token empty
Token ID6565
Feature activation+4.44e-01

Pos logit contributions
 AST+0.035
elaide+0.034
igree+0.033
outh+0.033
ovember+0.033
Neg logit contributions
wash-0.040
-0.039
pak-0.038
kat-0.037
gross-0.036
Token court
Token ID2184
Feature activation-1.10e+00

Pos logit contributions
wash+0.947
+0.932
pak+0.892
kat+0.870
gross+0.866
Neg logit contributions
 AST-0.650
elaide-0.624
igree-0.613
outh-0.610
ovember-0.608
Token.
Token ID13
Feature activation-2.10e-02

Pos logit contributions
 AST+1.791
elaide+1.702
igree+1.683
outh+1.678
ovember+1.668
Neg logit contributions
wash-2.161
-2.159
pak-2.046
kat-1.989
gross-1.986
Token
Token ID198
Feature activation+6.75e-02

Pos logit contributions
 AST+0.036
elaide+0.034
igree+0.034
outh+0.034
ovember+0.034
Neg logit contributions
wash-0.040
-0.039
pak-0.037
kat-0.036
gross-0.036
Token
Token ID198
Feature activation+6.02e-02

Pos logit contributions
wash+0.133
+0.131
pak+0.125
gross+0.123
kat+0.122
Neg logit contributions
 AST-0.110
outh-0.103
 Monarch-0.101
 ADHD-0.101
 Lyme-0.101
TokenThe
Token ID464
Feature activation+7.98e-02

Pos logit contributions
wash+0.099
+0.097
pak+0.092
kat+0.089
gross+0.089
Neg logit contributions
 AST-0.117
elaide-0.112
outh-0.112
igree-0.111
ovember-0.111
Token goals
Token ID4661
Feature activation+9.91e-02

Pos logit contributions
wash+0.158
+0.156
pak+0.149
kat+0.145
gross+0.145
Neg logit contributions
 AST-0.129
elaide-0.124
igree-0.122
outh-0.122
ovember-0.121
Token played
Token ID2826
Feature activation-2.82e-01

Pos logit contributions
 AST+0.104
elaide+0.099
igree+0.098
outh+0.098
ovember+0.097
Neg logit contributions
wash-0.104
-0.103
pak-0.097
kat-0.095
gross-0.094
Token on
Token ID319
Feature activation-1.63e-02

Pos logit contributions
 AST+0.457
elaide+0.433
igree+0.427
ovember+0.427
outh+0.427
Neg logit contributions
wash-0.561
-0.555
pak-0.529
kat-0.515
gross-0.513
Token a
Token ID257
Feature activation-8.44e-04

Pos logit contributions
 AST+0.025
elaide+0.023
igree+0.023
outh+0.023
ovember+0.023
Neg logit contributions
wash-0.034
-0.034
pak-0.032
kat-0.031
gross-0.031
Token half
Token ID2063
Feature activation-3.54e-01

Pos logit contributions
 AST+0.001
elaide+0.001
igree+0.001
outh+0.001
ovember+0.001
Neg logit contributions
wash-0.002
-0.002
pak-0.002
kat-0.002
gross-0.002
Token-
Token ID12
Feature activation+2.27e-02

Pos logit contributions
 AST+0.467
elaide+0.440
igree+0.433
outh+0.432
ovember+0.429
Neg logit contributions
wash-0.809
-0.801
pak-0.767
kat-0.750
gross-0.749
Tokencourt
Token ID22230
Feature activation-1.10e+00

Pos logit contributions
wash+0.048
+0.048
pak+0.045
kat+0.044
gross+0.044
Neg logit contributions
 AST-0.034
elaide-0.032
igree-0.031
outh-0.031
ovember-0.031
Token in
Token ID287
Feature activation-1.73e-02

Pos logit contributions
 AST+1.598
elaide+1.486
outh+1.477
igree+1.477
 Monarch+1.461
Neg logit contributions
wash-2.371
-2.357
pak-2.259
kat-2.187
gross-2.185
Token the
Token ID262
Feature activation-4.46e-02

Pos logit contributions
 AST+0.026
elaide+0.024
igree+0.024
outh+0.024
ovember+0.024
Neg logit contributions
wash-0.037
-0.036
pak-0.035
kat-0.034
gross-0.034
Token yard
Token ID12699
Feature activation-7.33e-02

Pos logit contributions
 AST+0.067
elaide+0.063
igree+0.062
outh+0.062
ovember+0.062
Neg logit contributions
wash-0.094
-0.093
pak-0.089
kat-0.087
gross-0.087
Token,
Token ID11
Feature activation+1.02e-01

Pos logit contributions
 AST+0.117
elaide+0.112
igree+0.110
outh+0.110
ovember+0.109
Neg logit contributions
wash-0.147
-0.145
pak-0.138
kat-0.135
gross-0.134
Token with
Token ID351
Feature activation+5.00e-03

Pos logit contributions
wash+0.200
+0.198
pak+0.188
kat+0.183
gross+0.183
Neg logit contributions
 AST-0.167
elaide-0.160
igree-0.158
outh-0.158
ovember-0.157
Token Pre
Token ID3771
Feature activation-1.35e-01

Pos logit contributions
wash+0.106
+0.105
pak+0.100
gross+0.098
kat+0.098
Neg logit contributions
 AST-0.089
 Monarch-0.083
outh-0.082
 Lyme-0.082
igree-0.082
Tokeny
Token ID88
Feature activation+4.32e-02

Pos logit contributions
 AST+0.251
outh+0.244
igree+0.238
elaide+0.236
 ADHD+0.236
Neg logit contributions
wash-0.228
-0.225
pak-0.214
gross-0.209
kat-0.206
Token
Token ID198
Feature activation-1.26e-04

Pos logit contributions
wash+0.081
+0.080
pak+0.076
kat+0.074
gross+0.074
Neg logit contributions
 AST-0.075
elaide-0.071
igree-0.070
outh-0.070
ovember-0.070
Token
Token ID198
Feature activation-7.11e-03

Pos logit contributions
 AST+0.000
outh+0.000
 Monarch+0.000
 ADHD+0.000
 Lyme+0.000
Neg logit contributions
wash-0.000
-0.000
pak-0.000
gross-0.000
kat-0.000
Tokenhttps
Token ID5450
Feature activation+9.14e-01

Pos logit contributions
 AST+0.014
elaide+0.014
outh+0.014
igree+0.014
ovember+0.014
Neg logit contributions
wash-0.011
-0.011
pak-0.010
kat-0.010
gross-0.010
Token://
Token ID1378
Feature activation+9.38e-01

Pos logit contributions
wash+1.523
+1.499
pak+1.414
kat+1.370
gross+1.366
Neg logit contributions
 AST-1.773
elaide-1.702
igree-1.683
outh-1.683
ovember-1.674
Tokenkill
Token ID12728
Feature activation+3.12e-01

Pos logit contributions
wash+1.593
+1.565
pak+1.481
kat+1.439
gross+1.433
Neg logit contributions
 AST-1.792
elaide-1.718
igree-1.695
ovember-1.693
outh-1.693
Tokenert
Token ID861
Feature activation+6.92e-01

Pos logit contributions
wash+0.524
+0.515
pak+0.486
kat+0.471
gross+0.470
Neg logit contributions
 AST-0.603
elaide-0.579
igree-0.573
outh-0.572
ovember-0.569
Tokenof
Token ID1659
Feature activation-2.80e-02

Pos logit contributions
wash+1.289
+1.258
pak+1.205
kat+1.172
gross+1.168
Neg logit contributions
 AST-1.216
elaide-1.155
igree-1.138
ovember-1.133
outh-1.131
Tokenure
Token ID495
Feature activation-2.89e-01

Pos logit contributions
 AST+0.052
elaide+0.050
igree+0.050
outh+0.050
ovember+0.049
Neg logit contributions
-0.048
wash-0.048
pak-0.044
kat-0.043
gross-0.043
Tokenc
Token ID66
Feature activation+2.98e-01

Pos logit contributions
 AST+0.587
elaide+0.565
outh+0.565
igree+0.562
ovember+0.556
Neg logit contributions
wash-0.451
-0.447
pak-0.416
gross-0.402
kat-0.401
Token
Token ID198
Feature activation-7.60e-02

Pos logit contributions
 AST+0.094
outh+0.088
 Monarch+0.086
 ADHD+0.086
elaide+0.086
Neg logit contributions
wash-0.114
-0.111
pak-0.107
gross-0.105
kat-0.104
TokenYou
Token ID1639
Feature activation-2.16e-01

Pos logit contributions
 AST+0.147
elaide+0.141
igree+0.140
outh+0.139
ovember+0.139
Neg logit contributions
wash-0.127
-0.125
pak-0.118
kat-0.115
gross-0.114
Token can
Token ID460
Feature activation-7.46e-02

Pos logit contributions
 AST+0.387
elaide+0.370
igree+0.366
outh+0.366
ovember+0.364
Neg logit contributions
wash-0.390
-0.384
pak-0.365
kat-0.355
gross-0.354
Token pick
Token ID2298
Feature activation-7.51e-02

Pos logit contributions
 AST+0.131
elaide+0.125
igree+0.124
outh+0.123
ovember+0.123
Neg logit contributions
wash-0.138
-0.136
pak-0.129
kat-0.125
gross-0.125
Token a
Token ID257
Feature activation+4.36e-02

Pos logit contributions
 AST+0.117
elaide+0.111
igree+0.109
outh+0.109
ovember+0.109
Neg logit contributions
wash-0.154
-0.152
pak-0.145
kat-0.142
gross-0.141
Token maths
Token ID47761
Feature activation+6.76e-01

Pos logit contributions
wash+0.088
+0.087
pak+0.083
kat+0.080
gross+0.080
Neg logit contributions
 AST-0.069
elaide-0.066
igree-0.065
outh-0.065
ovember-0.065
Token teacher
Token ID4701
Feature activation+2.23e-01

Pos logit contributions
wash+1.405
+1.390
pak+1.327
kat+1.293
gross+1.288
Neg logit contributions
 AST-1.017
elaide-0.978
igree-0.967
ovember-0.961
outh-0.956
Token,
Token ID11
Feature activation-1.22e-01

Pos logit contributions
wash+0.437
+0.431
pak+0.410
kat+0.400
gross+0.398
Neg logit contributions
 AST-0.367
elaide-0.351
igree-0.346
outh-0.345
ovember-0.344
Token a
Token ID257
Feature activation-4.29e-03

Pos logit contributions
 AST+0.190
elaide+0.181
igree+0.178
outh+0.178
ovember+0.177
Neg logit contributions
wash-0.251
-0.248
pak-0.237
kat-0.231
gross-0.230
Token mental
Token ID5110
Feature activation-4.51e-02

Pos logit contributions
 AST+0.007
elaide+0.006
igree+0.006
outh+0.006
ovember+0.006
Neg logit contributions
wash-0.009
-0.009
pak-0.008
kat-0.008
gross-0.008
Token capacity
Token ID5339
Feature activation+1.63e-01

Pos logit contributions
 AST+0.072
elaide+0.068
outh+0.067
igree+0.067
ovember+0.067
Neg logit contributions
wash-0.091
-0.090
pak-0.085
kat-0.083
gross-0.083
Token DPR
Token ID41176
Feature activation-1.42e-02

Pos logit contributions
 AST+0.159
elaide+0.150
igree+0.148
outh+0.148
ovember+0.147
Neg logit contributions
wash-0.228
-0.226
pak-0.215
kat-0.210
gross-0.210
Token Korea
Token ID4969
Feature activation-1.77e-01

Pos logit contributions
 AST+0.025
elaide+0.024
igree+0.024
outh+0.024
ovember+0.024
Neg logit contributions
wash-0.026
-0.026
pak-0.024
kat-0.024
gross-0.024
Token lose
Token ID4425
Feature activation-5.82e-02

Pos logit contributions
 AST+0.307
elaide+0.293
outh+0.289
igree+0.289
ovember+0.287
Neg logit contributions
wash-0.329
-0.325
pak-0.308
kat-0.300
gross-0.300
Token their
Token ID511
Feature activation+2.11e-02

Pos logit contributions
 AST+0.092
elaide+0.088
igree+0.086
outh+0.086
ovember+0.086
Neg logit contributions
wash-0.118
-0.116
pak-0.111
kat-0.108
gross-0.108
Token last
Token ID938
Feature activation-1.91e-01

Pos logit contributions
wash+0.038
+0.038
pak+0.036
kat+0.035
gross+0.035
Neg logit contributions
 AST-0.037
elaide-0.036
outh-0.035
igree-0.035
ovember-0.035
Token match
Token ID2872
Feature activation+6.69e-01

Pos logit contributions
 AST+0.260
elaide+0.246
igree+0.242
outh+0.241
ovember+0.240
Neg logit contributions
wash-0.428
-0.423
pak-0.405
kat-0.397
gross-0.396
Token against
Token ID1028
Feature activation+1.23e-01

Pos logit contributions
wash+1.281
+1.264
pak+1.202
kat+1.171
gross+1.164
Neg logit contributions
 AST-1.128
elaide-1.081
igree-1.069
outh-1.064
ovember-1.062
Token the
Token ID262
Feature activation-5.04e-02

Pos logit contributions
wash+0.259
+0.256
pak+0.244
kat+0.238
gross+0.238
Neg logit contributions
 AST-0.185
elaide-0.176
igree-0.174
outh-0.173
ovember-0.172
Token Philippines
Token ID13316
Feature activation-1.33e-01

Pos logit contributions
 AST+0.082
elaide+0.077
outh+0.076
igree+0.076
ovember+0.076
Neg logit contributions
wash-0.100
-0.099
pak-0.094
kat-0.092
gross-0.092
Token in
Token ID287
Feature activation-4.70e-02

Pos logit contributions
 AST+0.211
elaide+0.200
outh+0.198
igree+0.197
ovember+0.196
Neg logit contributions
wash-0.270
-0.266
pak-0.254
kat-0.248
gross-0.247
Token Manila
Token ID31721
Feature activation-1.18e-01

Pos logit contributions
 AST+0.081
elaide+0.077
outh+0.076
igree+0.076
ovember+0.075
Neg logit contributions
wash-0.089
-0.088
pak-0.083
gross-0.081
kat-0.081
Tokenaddress
Token ID21975
Feature activation+3.23e-01

Pos logit contributions
 AST+0.334
elaide+0.320
outh+0.316
igree+0.315
ovember+0.312
Neg logit contributions
wash-0.347
-0.342
pak-0.325
kat-0.316
gross-0.315
Token of
Token ID286
Feature activation-2.93e-02

Pos logit contributions
wash+0.661
+0.653
pak+0.623
kat+0.607
gross+0.605
Neg logit contributions
 AST-0.500
elaide-0.478
igree-0.472
outh-0.468
ovember-0.468
Token system
Token ID1080
Feature activation+8.11e-02

Pos logit contributions
 AST+0.049
elaide+0.047
igree+0.046
outh+0.046
ovember+0.046
Neg logit contributions
wash-0.057
-0.056
pak-0.053
kat-0.052
gross-0.052
Token]
Token ID60
Feature activation-2.07e-01

Pos logit contributions
wash+0.200
+0.198
pak+0.191
kat+0.187
gross+0.186
Neg logit contributions
 AST-0.092
elaide-0.086
igree-0.084
outh-0.084
ovember-0.084
Token |
Token ID930
Feature activation-2.09e-01

Pos logit contributions
 AST+0.306
outh+0.280
 Monarch+0.278
elaide+0.277
 ADHD+0.276
Neg logit contributions
wash-0.448
-0.435
pak-0.419
gross-0.412
kat-0.410
Token <
Token ID1279
Feature activation+7.77e-01

Pos logit contributions
 AST+0.398
elaide+0.380
igree+0.375
outh+0.375
ovember+0.373
Neg logit contributions
wash-0.357
-0.350
pak-0.332
kat-0.322
gross-0.321
Token--
Token ID438
Feature activation-2.79e-01

Pos logit contributions
wash+1.680
+1.663
pak+1.589
kat+1.548
gross+1.543
Neg logit contributions
 AST-1.122
elaide-1.074
igree-1.055
outh-1.045
ovember-1.045
Token stack
Token ID8931
Feature activation+1.82e-01

Pos logit contributions
 AST+0.391
elaide+0.369
igree+0.364
outh+0.363
ovember+0.360
Neg logit contributions
wash-0.615
-0.608
pak-0.581
kat-0.569
gross-0.567
Token pointer
Token ID17562
Feature activation+2.15e-01

Pos logit contributions
wash+0.459
+0.455
pak+0.437
kat+0.429
gross+0.428
Neg logit contributions
 AST-0.197
elaide-0.183
igree-0.179
outh-0.179
ovember-0.177
Token +
Token ID1343
Feature activation-1.71e-02

Pos logit contributions
wash+0.364
+0.358
pak+0.339
kat+0.328
gross+0.327
Neg logit contributions
 AST-0.413
elaide-0.396
igree-0.392
outh-0.391
ovember-0.389
Token--------------------
Token ID19351
Feature activation-1.82e-02

Pos logit contributions
 AST+0.031
outh+0.029
elaide+0.029
igree+0.029
ovember+0.029
Neg logit contributions
wash-0.031
-0.030
pak-0.029
kat-0.028
gross-0.028
Token technology
Token ID3037
Feature activation+2.18e-01

Pos logit contributions
 AST+0.131
elaide+0.125
igree+0.124
outh+0.123
ovember+0.122
Neg logit contributions
wash-0.152
-0.150
pak-0.142
kat-0.139
gross-0.138
Token:
Token ID25
Feature activation-3.55e-03

Pos logit contributions
wash+0.415
+0.410
pak+0.388
kat+0.379
gross+0.377
Neg logit contributions
 AST-0.372
elaide-0.356
igree-0.352
outh-0.350
ovember-0.349
Token
Token ID198
Feature activation-1.39e-01

Pos logit contributions
 AST+0.006
elaide+0.006
outh+0.006
igree+0.006
ovember+0.006
Neg logit contributions
wash-0.007
-0.006
pak-0.006
gross-0.006
kat-0.006
Token
Token ID198
Feature activation-8.35e-02

Pos logit contributions
 AST+0.224
outh+0.210
 ADHD+0.206
 Monarch+0.205
 Lyme+0.205
Neg logit contributions
wash-0.278
-0.271
pak-0.261
gross-0.256
kat-0.253
Tokenhttps
Token ID5450
Feature activation+8.29e-01

Pos logit contributions
 AST+0.203
elaide+0.196
outh+0.195
ovember+0.194
igree+0.194
Neg logit contributions
wash-0.097
-0.094
pak-0.087
gross-0.083
kat-0.082
Token://
Token ID1378
Feature activation+8.59e-01

Pos logit contributions
wash+1.384
+1.362
pak+1.285
kat+1.245
gross+1.242
Neg logit contributions
 AST-1.603
elaide-1.537
outh-1.522
igree-1.520
ovember-1.513
Tokenwww
Token ID2503
Feature activation+2.28e-01

Pos logit contributions
wash+1.020
+0.992
pak+0.915
kat+0.877
gross+0.870
Neg logit contributions
 AST-2.082
elaide-2.017
igree-1.998
outh-1.991
ovember-1.988
Token.
Token ID13
Feature activation+4.00e-02

Pos logit contributions
wash+0.449
+0.442
pak+0.423
gross+0.412
kat+0.410
Neg logit contributions
 AST-0.371
outh-0.350
elaide-0.346
igree-0.342
 Monarch-0.342
Tokeneff
Token ID14822
Feature activation-7.91e-02

Pos logit contributions
wash+0.109
+0.108
pak+0.104
kat+0.102
gross+0.102
Neg logit contributions
 AST-0.035
elaide-0.032
outh-0.031
igree-0.031
ovember-0.031
Token.
Token ID13
Feature activation+2.20e-02

Pos logit contributions
 AST+0.131
elaide+0.125
outh+0.124
igree+0.124
ovember+0.123
Neg logit contributions
wash-0.153
-0.151
pak-0.143
gross-0.140
kat-0.140
Tokenorg
Token ID2398
Feature activation+1.33e-01

Pos logit contributions
wash+0.039
+0.039
pak+0.036
kat+0.035
gross+0.035
Neg logit contributions
 AST-0.040
elaide-0.038
outh-0.038
igree-0.038
ovember-0.038
Token he
Token ID339
Feature activation-4.25e-02

Pos logit contributions
wash+0.209
+0.206
pak+0.197
kat+0.192
gross+0.192
Neg logit contributions
 AST-0.150
elaide-0.143
igree-0.141
outh-0.140
ovember-0.140
Token's
Token ID338
Feature activation+1.15e-01

Pos logit contributions
 AST+0.074
elaide+0.071
igree+0.070
outh+0.070
ovember+0.069
Neg logit contributions
wash-0.079
-0.078
pak-0.074
kat-0.072
gross-0.072
Token notorious
Token ID18192
Feature activation+3.31e-01

Pos logit contributions
wash+0.212
+0.209
pak+0.198
kat+0.193
gross+0.192
Neg logit contributions
 AST-0.202
elaide-0.193
igree-0.191
outh-0.190
ovember-0.189
Token about
Token ID546
Feature activation-1.55e-01

Pos logit contributions
wash+0.640
+0.631
pak+0.600
kat+0.584
gross+0.582
Neg logit contributions
 AST-0.554
elaide-0.531
igree-0.523
outh-0.522
ovember-0.521
Token stealing
Token ID16568
Feature activation-6.77e-01

Pos logit contributions
 AST+0.249
elaide+0.237
igree+0.234
outh+0.234
ovember+0.232
Neg logit contributions
wash-0.310
-0.306
pak-0.292
kat-0.284
gross-0.284
Token players
Token ID1938
Feature activation+1.31e-01

Pos logit contributions
 AST+1.151
elaide+1.088
outh+1.082
igree+1.080
 Monarch+1.075
Neg logit contributions
wash-1.288
-1.268
pak-1.211
kat-1.180
gross-1.180
Token from
Token ID422
Feature activation-1.00e-01

Pos logit contributions
wash+0.251
+0.248
pak+0.236
kat+0.229
gross+0.229
Neg logit contributions
 AST-0.222
elaide-0.213
igree-0.210
outh-0.209
ovember-0.209
Token other
Token ID584
Feature activation-7.27e-02

Pos logit contributions
 AST+0.159
elaide+0.152
igree+0.150
outh+0.149
ovember+0.149
Neg logit contributions
wash-0.201
-0.199
pak-0.189
kat-0.184
gross-0.184
Token team
Token ID1074
Feature activation+3.07e-02

Pos logit contributions
 AST+0.124
elaide+0.118
igree+0.117
outh+0.117
ovember+0.116
Neg logit contributions
wash-0.138
-0.136
pak-0.130
kat-0.126
gross-0.126
Token such
Token ID884
Feature activation-3.41e-01

Pos logit contributions
wash+0.058
+0.057
pak+0.054
kat+0.053
gross+0.053
Neg logit contributions
 AST-0.053
elaide-0.050
igree-0.050
outh-0.050
ovember-0.049
Token as
Token ID355
Feature activation+9.55e-02

Pos logit contributions
 AST+0.621
elaide+0.594
igree+0.587
outh+0.586
ovember+0.582
Neg logit contributions
wash-0.610
-0.603
pak-0.567
gross-0.552
kat-0.551
Token:
Token ID25
Feature activation+2.64e-02

Pos logit contributions
 AST+1.282
outh+1.201
 ADHD+1.190
 Lyme+1.174
 Monarch+1.170
Neg logit contributions
wash-1.463
-1.419
pak-1.361
gross-1.346
kat-1.327
Token Carly
Token ID35982
Feature activation+3.18e-02

Pos logit contributions
wash+0.040
+0.038
pak+0.036
gross+0.036
kat+0.035
Neg logit contributions
 AST-0.057
 Lyme-0.053
outh-0.053
 Monarch-0.053
 ADHD-0.053
Token Fiorina
Token ID49028
Feature activation-3.80e-02

Pos logit contributions
wash+0.036
+0.034
pak+0.032
kat+0.031
gross+0.031
Neg logit contributions
 AST-0.079
outh-0.076
 Lyme-0.075
igree-0.075
 ADHD-0.075
Token's
Token ID338
Feature activation+1.41e-02

Pos logit contributions
 AST+0.058
outh+0.054
elaide+0.054
 Monarch+0.054
igree+0.053
Neg logit contributions
wash-0.079
-0.078
pak-0.074
gross-0.073
kat-0.073
Token political
Token ID1964
Feature activation+2.83e-01

Pos logit contributions
wash+0.026
+0.026
pak+0.024
kat+0.024
gross+0.023
Neg logit contributions
 AST-0.025
outh-0.024
elaide-0.024
igree-0.023
 Monarch-0.023
Token career
Token ID3451
Feature activation+5.14e-01

Pos logit contributions
wash+0.591
+0.584
pak+0.557
kat+0.543
gross+0.542
Neg logit contributions
 AST-0.429
elaide-0.410
igree-0.403
outh-0.402
ovember-0.400
Token Fiorina
Token ID49028
Feature activation-5.26e-02

Pos logit contributions
wash+0.574
+0.561
pak+0.513
kat+0.488
gross+0.488
Neg logit contributions
 AST-1.282
elaide-1.237
outh-1.230
igree-1.229
ovember-1.222
Token speaks
Token ID9209
Feature activation-3.79e-01

Pos logit contributions
 AST+0.092
elaide+0.087
outh+0.086
igree+0.086
ovember+0.086
Neg logit contributions
wash-0.098
-0.097
pak-0.092
kat-0.089
gross-0.089
Token during
Token ID1141
Feature activation-4.10e-02

Pos logit contributions
 AST+0.628
elaide+0.588
outh+0.588
ovember+0.586
igree+0.584
Neg logit contributions
wash-0.736
-0.734
pak-0.694
kat-0.678
gross-0.677
Token a
Token ID257
Feature activation+2.93e-02

Pos logit contributions
 AST+0.058
elaide+0.054
outh+0.054
igree+0.053
 Monarch+0.053
Neg logit contributions
wash-0.091
-0.090
pak-0.085
kat-0.084
gross-0.084
Token forum
Token ID10041
Feature activation+5.98e-02

Pos logit contributions
wash+0.059
+0.059
pak+0.056
kat+0.055
gross+0.054
Neg logit contributions
 AST-0.046
outh-0.044
elaide-0.043
 Monarch-0.043
ovember-0.043
Token
Token ID247
Feature activation+3.04e-02

Pos logit contributions
wash+0.384
+0.377
pak+0.362
kat+0.355
gross+0.351
Neg logit contributions
 AST-0.239
elaide-0.226
igree-0.225
outh-0.223
ovember-0.221
Token and
Token ID290
Feature activation-3.08e-02

Pos logit contributions
wash+0.058
+0.057
pak+0.055
kat+0.053
gross+0.053
Neg logit contributions
 AST-0.051
elaide-0.049
igree-0.048
outh-0.048
ovember-0.048
Token
Token ID564
Feature activation-7.01e-03

Pos logit contributions
 AST+0.051
elaide+0.048
igree+0.047
outh+0.047
ovember+0.047
Neg logit contributions
wash-0.061
-0.060
pak-0.057
kat-0.055
gross-0.055
Token
Token ID246
Feature activation+9.85e-03

Pos logit contributions
 AST+0.011
elaide+0.011
igree+0.011
outh+0.011
ovember+0.010
Neg logit contributions
wash-0.014
-0.014
pak-0.013
kat-0.013
gross-0.013
TokenEvery
Token ID6109
Feature activation-2.35e-02

Pos logit contributions
wash+0.017
+0.016
pak+0.016
kat+0.015
gross+0.015
Neg logit contributions
 AST-0.019
elaide-0.018
outh-0.018
igree-0.018
ovember-0.018
Token Time
Token ID3862
Feature activation+1.38e-01

Pos logit contributions
 AST+0.038
elaide+0.037
igree+0.036
outh+0.036
ovember+0.036
Neg logit contributions
wash-0.046
-0.046
pak-0.044
kat-0.043
gross-0.042
Token the
Token ID262
Feature activation+1.37e-01

Pos logit contributions
wash+0.276
+0.273
pak+0.260
kat+0.253
gross+0.252
Neg logit contributions
 AST-0.222
elaide-0.212
igree-0.209
outh-0.208
ovember-0.208
Token Sun
Token ID3825
Feature activation-1.98e-01

Pos logit contributions
wash+0.263
+0.260
pak+0.247
kat+0.240
gross+0.239
Neg logit contributions
 AST-0.229
elaide-0.220
igree-0.216
outh-0.216
ovember-0.216
Token Comes
Token ID34606
Feature activation+1.32e-01

Pos logit contributions
 AST+0.363
elaide+0.342
outh+0.339
igree+0.338
 Monarch+0.337
Neg logit contributions
wash-0.352
-0.347
pak-0.328
kat-0.320
gross-0.319
Token Up
Token ID3205
Feature activation+6.10e-02

Pos logit contributions
wash+0.285
+0.282
pak+0.270
kat+0.263
gross+0.263
Neg logit contributions
 AST-0.189
elaide-0.179
igree-0.176
outh-0.176
ovember-0.175
Token
Token ID447
Feature activation+2.04e-01

Pos logit contributions
wash+0.105
+0.104
pak+0.098
kat+0.095
gross+0.095
Neg logit contributions
 AST-0.115
elaide-0.110
igree-0.109
outh-0.109
ovember-0.108
Token video
Token ID2008
Feature activation-2.08e-01

Pos logit contributions
 AST+0.030
elaide+0.028
igree+0.028
outh+0.028
ovember+0.028
Neg logit contributions
wash-0.035
-0.034
pak-0.033
kat-0.032
gross-0.032
Token that
Token ID326
Feature activation-5.75e-02

Pos logit contributions
 AST+0.360
elaide+0.345
igree+0.341
outh+0.340
ovember+0.339
Neg logit contributions
wash-0.389
-0.384
pak-0.365
kat-0.355
gross-0.354
Token I
Token ID314
Feature activation+1.76e-02

Pos logit contributions
 AST+0.099
elaide+0.094
igree+0.093
outh+0.093
ovember+0.092
Neg logit contributions
wash-0.109
-0.107
pak-0.102
kat-0.099
gross-0.099
Token have
Token ID423
Feature activation-1.08e-02

Pos logit contributions
wash+0.032
+0.032
pak+0.030
kat+0.029
gross+0.029
Neg logit contributions
 AST-0.031
elaide-0.030
igree-0.029
outh-0.029
ovember-0.029
Token never
Token ID1239
Feature activation-1.48e-01

Pos logit contributions
 AST+0.018
elaide+0.017
outh+0.017
igree+0.017
ovember+0.017
Neg logit contributions
wash-0.021
-0.020
pak-0.019
kat-0.019
gross-0.019
Token seen
Token ID1775
Feature activation+1.83e-02

Pos logit contributions
 AST+0.221
elaide+0.208
outh+0.207
igree+0.205
ovember+0.205
Neg logit contributions
wash-0.312
-0.308
pak-0.293
kat-0.287
gross-0.286
Token or
Token ID393
Feature activation-8.06e-02

Pos logit contributions
wash+0.035
+0.035
pak+0.033
kat+0.032
gross+0.032
Neg logit contributions
 AST-0.031
elaide-0.029
outh-0.029
igree-0.029
ovember-0.029
Token does
Token ID857
Feature activation+1.47e-01

Pos logit contributions
 AST+0.126
elaide+0.120
outh+0.118
igree+0.118
ovember+0.118
Neg logit contributions
wash-0.164
-0.162
pak-0.155
kat-0.151
gross-0.151
Token not
Token ID407
Feature activation-3.05e-02

Pos logit contributions
wash+0.227
+0.221
pak+0.209
kat+0.202
gross+0.201
Neg logit contributions
 AST-0.303
elaide-0.291
outh-0.289
igree-0.288
ovember-0.287
Token exist
Token ID2152
Feature activation-2.75e-01

Pos logit contributions
 AST+0.053
elaide+0.051
outh+0.050
igree+0.050
ovember+0.050
Neg logit contributions
wash-0.057
-0.056
pak-0.053
kat-0.051
gross-0.051
Token.
Token ID13
Feature activation-2.99e-02

Pos logit contributions
 AST+0.454
elaide+0.434
outh+0.430
igree+0.428
ovember+0.426
Neg logit contributions
wash-0.537
-0.526
pak-0.501
gross-0.487
kat-0.486
Token and
Token ID290
Feature activation+5.56e-02

Pos logit contributions
wash+0.506
+0.500
pak+0.475
gross+0.462
kat+0.461
Neg logit contributions
 AST-0.472
elaide-0.449
outh-0.444
igree-0.444
ovember-0.441
Token white
Token ID2330
Feature activation-2.70e-01

Pos logit contributions
wash+0.121
+0.119
pak+0.114
kat+0.111
gross+0.111
Neg logit contributions
 AST-0.079
elaide-0.075
igree-0.074
outh-0.074
ovember-0.074
Token?
Token ID30
Feature activation+5.50e-03

Pos logit contributions
 AST+0.495
elaide+0.464
outh+0.464
 Monarch+0.463
igree+0.462
Neg logit contributions
wash-0.481
-0.471
pak-0.449
gross-0.438
kat-0.433
Token Although
Token ID4900
Feature activation-3.53e-02

Pos logit contributions
wash+0.010
+0.010
pak+0.009
kat+0.009
gross+0.009
Neg logit contributions
 AST-0.010
elaide-0.009
igree-0.009
outh-0.009
ovember-0.009
Token the
Token ID262
Feature activation+6.90e-02

Pos logit contributions
 AST+0.054
elaide+0.051
igree+0.050
outh+0.050
ovember+0.050
Neg logit contributions
wash-0.073
-0.073
pak-0.069
kat-0.068
gross-0.067
Token color
Token ID3124
Feature activation+2.16e-01

Pos logit contributions
wash+0.130
+0.127
pak+0.121
kat+0.118
gross+0.118
Neg logit contributions
 AST-0.120
elaide-0.113
igree-0.112
outh-0.112
ovember-0.112
Token of
Token ID286
Feature activation+2.20e-02

Pos logit contributions
wash+0.418
+0.412
pak+0.391
kat+0.381
gross+0.380
Neg logit contributions
 AST-0.361
elaide-0.346
igree-0.341
outh-0.340
ovember-0.338
Token the
Token ID262
Feature activation+6.42e-02

Pos logit contributions
wash+0.047
+0.047
pak+0.045
kat+0.044
gross+0.044
Neg logit contributions
 AST-0.032
elaide-0.030
outh-0.030
igree-0.029
ovember-0.029
Token device
Token ID3335
Feature activation-1.61e-02

Pos logit contributions
wash+0.120
+0.118
pak+0.112
gross+0.110
kat+0.109
Neg logit contributions
 AST-0.112
elaide-0.105
outh-0.105
igree-0.105
ovember-0.104
Token has
Token ID468
Feature activation-1.22e-02

Pos logit contributions
 AST+0.029
elaide+0.028
igree+0.027
outh+0.027
ovember+0.027
Neg logit contributions
wash-0.029
-0.029
pak-0.027
kat-0.026
gross-0.026
Token a
Token ID257
Feature activation+5.31e-02

Pos logit contributions
 AST+0.022
elaide+0.021
outh+0.021
igree+0.021
ovember+0.021
Neg logit contributions
wash-0.022
-0.022
pak-0.020
kat-0.020
gross-0.020
Token and
Token ID290
Feature activation-8.02e-02

Pos logit contributions
 AST+0.083
elaide+0.079
igree+0.078
outh+0.078
ovember+0.078
Neg logit contributions
wash-0.098
-0.097
pak-0.092
kat-0.090
gross-0.089
Token two
Token ID734
Feature activation-1.09e-01

Pos logit contributions
 AST+0.125
elaide+0.119
igree+0.118
outh+0.118
ovember+0.117
Neg logit contributions
wash-0.164
-0.161
pak-0.154
kat-0.150
gross-0.150
Token touchdowns
Token ID17692
Feature activation+3.94e-01

Pos logit contributions
 AST+0.186
elaide+0.177
igree+0.175
outh+0.174
ovember+0.173
Neg logit contributions
wash-0.206
-0.204
pak-0.194
kat-0.189
gross-0.189
Token through
Token ID832
Feature activation-4.78e-01

Pos logit contributions
wash+0.764
+0.753
pak+0.716
kat+0.697
gross+0.695
Neg logit contributions
 AST-0.656
elaide-0.628
igree-0.621
outh-0.618
ovember-0.616
Token the
Token ID262
Feature activation+2.50e-02

Pos logit contributions
 AST+0.672
elaide+0.634
igree+0.622
outh+0.621
ovember+0.618
Neg logit contributions
wash-1.051
-1.044
pak-0.997
kat-0.976
gross-0.973
Token air
Token ID1633
Feature activation-1.37e-01

Pos logit contributions
wash+0.047
+0.046
pak+0.044
kat+0.043
gross+0.043
Neg logit contributions
 AST-0.044
elaide-0.041
igree-0.041
outh-0.041
ovember-0.041
Token.
Token ID13
Feature activation-3.81e-02

Pos logit contributions
 AST+0.222
elaide+0.212
igree+0.209
outh+0.209
ovember+0.208
Neg logit contributions
wash-0.271
-0.268
pak-0.255
kat-0.249
gross-0.248
Token Per
Token ID2448
Feature activation-2.63e-01

Pos logit contributions
 AST+0.067
elaide+0.064
igree+0.063
outh+0.063
ovember+0.063
Neg logit contributions
wash-0.071
-0.070
pak-0.066
kat-0.064
gross-0.064
Token Football
Token ID9957
Feature activation-1.50e-01

Pos logit contributions
 AST+0.376
elaide+0.355
igree+0.350
outh+0.349
ovember+0.346
Neg logit contributions
wash-0.573
-0.567
pak-0.542
kat-0.530
gross-0.528
Token Outs
Token ID46580
Feature activation-3.07e-01

Pos logit contributions
 AST+0.185
elaide+0.171
igree+0.170
outh+0.168
ovember+0.167
Neg logit contributions
wash-0.355
-0.352
pak-0.337
kat-0.332
gross-0.331
Tokeniders
Token ID4157
Feature activation-1.26e-01

Pos logit contributions
 AST+0.452
elaide+0.426
outh+0.424
igree+0.423
ovember+0.416
Neg logit contributions
wash-0.657
-0.646
pak-0.617
gross-0.604
kat-0.601
Tokenured
Token ID1522
Feature activation-1.92e-01

Pos logit contributions
wash+0.138
+0.137
pak+0.127
kat+0.123
gross+0.122
Neg logit contributions
 AST-0.206
elaide-0.198
outh-0.197
igree-0.196
ovember-0.195
Token loans
Token ID10021
Feature activation+4.84e-01

Pos logit contributions
 AST+0.368
elaide+0.351
igree+0.348
outh+0.348
ovember+0.346
Neg logit contributions
wash-0.325
-0.320
pak-0.301
kat-0.292
gross-0.292
Token.
Token ID13
Feature activation+7.01e-02

Pos logit contributions
wash+0.927
+0.914
pak+0.871
kat+0.848
gross+0.846
Neg logit contributions
 AST-0.812
elaide-0.782
igree-0.771
outh-0.768
ovember-0.764
Token The
Token ID383
Feature activation-4.22e-02

Pos logit contributions
wash+0.135
+0.133
pak+0.126
kat+0.123
gross+0.123
Neg logit contributions
 AST-0.118
elaide-0.113
igree-0.111
outh-0.111
ovember-0.110
Token three
Token ID1115
Feature activation-7.25e-04

Pos logit contributions
 AST+0.073
elaide+0.070
igree+0.069
outh+0.069
ovember+0.069
Neg logit contributions
wash-0.079
-0.078
pak-0.074
kat-0.072
gross-0.072
Token men
Token ID1450
Feature activation-4.88e-02

Pos logit contributions
 AST+0.001
elaide+0.001
igree+0.001
outh+0.001
ovember+0.001
Neg logit contributions
wash-0.001
-0.001
pak-0.001
kat-0.001
gross-0.001
Token own
Token ID898
Feature activation+1.85e-01

Pos logit contributions
 AST+0.088
elaide+0.083
igree+0.083
outh+0.083
ovember+0.083
Neg logit contributions
wash-0.088
-0.087
pak-0.083
kat-0.080
gross-0.080
Token five
Token ID1936
Feature activation-4.85e-02

Pos logit contributions
wash+0.371
+0.366
pak+0.350
kat+0.341
gross+0.340
Neg logit contributions
 AST-0.296
elaide-0.283
igree-0.279
outh-0.278
ovember-0.277
Token additional
Token ID3224
Feature activation-3.27e-01

Pos logit contributions
 AST+0.085
elaide+0.081
igree+0.080
outh+0.080
ovember+0.079
Neg logit contributions
wash-0.090
-0.089
pak-0.084
kat-0.082
gross-0.082
Token Kh
Token ID5311
Feature activation-6.42e-03

Pos logit contributions
 AST+0.613
elaide+0.584
igree+0.579
outh+0.578
 Monarch+0.576
Neg logit contributions
wash-0.567
-0.559
pak-0.525
kat-0.513
gross-0.510
Tokenark
Token ID668
Feature activation-2.49e-01

Pos logit contributions
 AST+0.012
elaide+0.011
outh+0.011
igree+0.011
ovember+0.011
Neg logit contributions
wash-0.012
-0.011
pak-0.011
gross-0.010
kat-0.010
Token who
Token ID508
Feature activation-2.12e-02

Pos logit contributions
 AST+0.188
elaide+0.180
igree+0.178
outh+0.177
ovember+0.176
Neg logit contributions
wash-0.205
-0.203
pak-0.192
kat-0.187
gross-0.187
Token was
Token ID373
Feature activation-1.07e-02

Pos logit contributions
 AST+0.037
elaide+0.036
igree+0.035
outh+0.035
ovember+0.035
Neg logit contributions
wash-0.039
-0.039
pak-0.037
kat-0.036
gross-0.036
Token following
Token ID1708
Feature activation-4.22e-01

Pos logit contributions
 AST+0.019
elaide+0.018
igree+0.018
outh+0.018
ovember+0.018
Neg logit contributions
wash-0.020
-0.019
pak-0.018
kat-0.018
gross-0.018
Token her
Token ID607
Feature activation+1.50e-02

Pos logit contributions
 AST+0.717
elaide+0.677
igree+0.675
outh+0.670
 Monarch+0.666
Neg logit contributions
wash-0.806
-0.796
pak-0.757
gross-0.737
kat-0.736
Token upstairs
Token ID26148
Feature activation-9.43e-02

Pos logit contributions
wash+0.030
+0.030
pak+0.028
kat+0.027
gross+0.027
Neg logit contributions
 AST-0.024
elaide-0.023
igree-0.023
outh-0.023
ovember-0.023
Token,
Token ID11
Feature activation-1.81e-02

Pos logit contributions
 AST+0.149
elaide+0.142
outh+0.140
igree+0.140
ovember+0.139
Neg logit contributions
wash-0.190
-0.189
pak-0.180
kat-0.175
gross-0.174
Token got
Token ID1392
Feature activation+1.53e-01

Pos logit contributions
 AST+0.032
elaide+0.031
igree+0.030
outh+0.030
ovember+0.030
Neg logit contributions
wash-0.033
-0.033
pak-0.031
kat-0.030
gross-0.030
Token crushed
Token ID18577
Feature activation+2.51e-01

Pos logit contributions
wash+0.311
+0.307
pak+0.293
kat+0.285
gross+0.285
Neg logit contributions
 AST-0.241
elaide-0.230
igree-0.226
outh-0.226
ovember-0.225
Token under
Token ID739
Feature activation+7.06e-02

Pos logit contributions
wash+0.459
+0.453
pak+0.429
kat+0.417
gross+0.416
Neg logit contributions
 AST-0.445
elaide-0.426
igree-0.421
outh-0.420
ovember-0.419
Token her
Token ID607
Feature activation+4.47e-02

Pos logit contributions
wash+0.153
+0.151
pak+0.144
kat+0.141
gross+0.141
Neg logit contributions
 AST-0.102
elaide-0.096
igree-0.095
outh-0.095
ovember-0.094
Token weight
Token ID3463
Feature activation+1.30e-01

Pos logit contributions
wash+0.093
+0.092
pak+0.087
kat+0.085
gross+0.085
Neg logit contributions
 AST-0.068
elaide-0.065
igree-0.064
outh-0.064
ovember-0.064
Token
Token ID960
Feature activation-2.42e-01

Pos logit contributions
 AST+0.022
elaide+0.021
outh+0.021
igree+0.021
ovember+0.021
Neg logit contributions
wash-0.028
-0.028
pak-0.026
kat-0.026
gross-0.026
Tokensp
Token ID2777
Feature activation+1.37e-01

Pos logit contributions
 AST+0.520
elaide+0.501
outh+0.498
igree+0.497
ovember+0.492
Neg logit contributions
wash-0.348
-0.345
pak-0.319
kat-0.308
gross-0.304
Tokenark
Token ID668
Feature activation-3.20e-01

Pos logit contributions
wash+0.247
+0.244
pak+0.230
kat+0.224
gross+0.223
Neg logit contributions
 AST-0.248
elaide-0.238
igree-0.235
outh-0.235
ovember-0.234
Tokened
Token ID276
Feature activation-1.83e-01

Pos logit contributions
 AST+0.612
elaide+0.587
outh+0.581
igree+0.578
ovember+0.575
Neg logit contributions
wash-0.541
-0.535
pak-0.505
kat-0.489
gross-0.487
Token even
Token ID772
Feature activation+1.37e-01

Pos logit contributions
 AST+0.281
elaide+0.268
igree+0.264
outh+0.263
ovember+0.262
Neg logit contributions
wash-0.380
-0.375
pak-0.358
kat-0.349
gross-0.348
Token more
Token ID517
Feature activation-1.62e-01

Pos logit contributions
wash+0.236
+0.232
pak+0.219
kat+0.213
gross+0.212
Neg logit contributions
 AST-0.257
elaide-0.249
igree-0.246
outh-0.244
ovember-0.244
Token anger
Token ID8993
Feature activation+2.81e-01

Pos logit contributions
 AST+0.247
elaide+0.236
igree+0.233
outh+0.231
ovember+0.230
Neg logit contributions
wash-0.336
-0.331
pak-0.316
kat-0.308
gross-0.308
Token.
Token ID13
Feature activation-9.70e-02

Pos logit contributions
wash+0.549
+0.541
pak+0.514
kat+0.501
gross+0.500
Neg logit contributions
 AST-0.464
elaide-0.443
igree-0.438
outh-0.436
ovember-0.435
Token
Token ID198
Feature activation-9.61e-02

Pos logit contributions
 AST+0.167
elaide+0.159
outh+0.157
igree+0.157
ovember+0.156
Neg logit contributions
wash-0.183
-0.180
pak-0.171
gross-0.166
kat-0.166
Token
Token ID198
Feature activation-9.05e-02

Pos logit contributions
 AST+0.155
outh+0.146
 ADHD+0.143
 Monarch+0.143
 Lyme+0.142
Neg logit contributions
wash-0.191
-0.187
pak-0.179
gross-0.176
kat-0.174
TokenTwo
Token ID7571
Feature activation-5.89e-02

Pos logit contributions
 AST+0.175
elaide+0.167
outh+0.166
igree+0.165
ovember+0.165
Neg logit contributions
wash-0.151
-0.148
pak-0.140
gross-0.136
kat-0.135
Token knew
Token ID2993
Feature activation-3.76e-01

Pos logit contributions
 AST+0.339
elaide+0.324
igree+0.320
outh+0.320
ovember+0.318
Neg logit contributions
wash-0.361
-0.357
pak-0.339
kat-0.330
gross-0.329
Token from
Token ID422
Feature activation-1.47e-01

Pos logit contributions
 AST+0.589
elaide+0.558
igree+0.552
outh+0.551
ovember+0.546
Neg logit contributions
wash-0.767
-0.757
pak-0.723
kat-0.704
gross-0.703
Token the
Token ID262
Feature activation-1.24e-01

Pos logit contributions
 AST+0.218
elaide+0.207
outh+0.204
igree+0.204
ovember+0.202
Neg logit contributions
wash-0.311
-0.307
pak-0.294
kat-0.287
gross-0.286
Token start
Token ID923
Feature activation-8.07e-02

Pos logit contributions
 AST+0.242
elaide+0.231
outh+0.230
igree+0.229
 Monarch+0.227
Neg logit contributions
wash-0.204
-0.200
pak-0.190
kat-0.184
gross-0.184
Token I
Token ID314
Feature activation-9.05e-02

Pos logit contributions
 AST+0.130
elaide+0.124
igree+0.122
outh+0.122
ovember+0.121
Neg logit contributions
wash-0.161
-0.159
pak-0.151
kat-0.148
gross-0.147
Token could
Token ID714
Feature activation-1.40e-01

Pos logit contributions
 AST+0.158
elaide+0.151
igree+0.150
outh+0.149
ovember+0.149
Neg logit contributions
wash-0.168
-0.166
pak-0.157
kat-0.153
gross-0.153
Token never
Token ID1239
Feature activation-2.49e-01

Pos logit contributions
 AST+0.246
elaide+0.234
igree+0.232
outh+0.231
ovember+0.230
Neg logit contributions
wash-0.259
-0.256
pak-0.243
kat-0.237
gross-0.236
Token become
Token ID1716
Feature activation-4.58e-03

Pos logit contributions
 AST+0.417
elaide+0.394
outh+0.390
igree+0.390
ovember+0.387
Neg logit contributions
wash-0.479
-0.473
pak-0.450
kat-0.440
gross-0.439
Token Na
Token ID11013
Feature activation-1.31e-01

Pos logit contributions
 AST+0.007
elaide+0.007
igree+0.007
outh+0.007
ovember+0.007
Neg logit contributions
wash-0.009
-0.009
pak-0.009
kat-0.009
gross-0.009
Tokenof
Token ID1659
Feature activation-1.63e-01

Pos logit contributions
 AST+0.243
elaide+0.233
outh+0.232
igree+0.231
ovember+0.230
Neg logit contributions
wash-0.228
-0.226
pak-0.213
kat-0.207
gross-0.207
Tokenumi
Token ID12994
Feature activation+2.10e-01

Pos logit contributions
 AST+0.318
outh+0.308
igree+0.306
elaide+0.306
ovember+0.303
Neg logit contributions
wash-0.266
-0.262
pak-0.247
gross-0.240
kat-0.237
Tokens
Token ID82
Feature activation-2.60e-01

Pos logit contributions
wash+0.295
+0.289
pak+0.272
gross+0.266
kat+0.264
Neg logit contributions
 AST-0.329
elaide-0.312
outh-0.311
igree-0.310
 Monarch-0.308
Token
Token ID564
Feature activation-2.37e-02

Pos logit contributions
 AST+0.445
elaide+0.418
outh+0.416
igree+0.415
 Monarch+0.415
Neg logit contributions
wash-0.494
-0.483
pak-0.462
gross-0.452
kat-0.448
Token
Token ID250
Feature activation-1.14e-01

Pos logit contributions
 AST+0.053
elaide+0.051
igree+0.051
outh+0.051
ovember+0.051
Neg logit contributions
wash-0.032
-0.032
pak-0.029
kat-0.028
gross-0.028
TokenEvent
Token ID9237
Feature activation+1.75e-01

Pos logit contributions
 AST+0.213
elaide+0.204
igree+0.201
outh+0.201
ovember+0.201
Neg logit contributions
wash-0.197
-0.194
pak-0.183
gross-0.178
kat-0.178
Token Qu
Token ID2264
Feature activation+1.96e-01

Pos logit contributions
wash+0.317
+0.314
pak+0.297
kat+0.288
gross+0.287
Neg logit contributions
 AST-0.314
elaide-0.301
igree-0.297
outh-0.297
ovember-0.295
Tokenests
Token ID3558
Feature activation-7.38e-01

Pos logit contributions
wash+0.456
+0.451
pak+0.432
kat+0.422
gross+0.422
Neg logit contributions
 AST-0.252
elaide-0.236
igree-0.234
outh-0.233
ovember-0.231
Token
Token ID447
Feature activation+4.53e-02

Pos logit contributions
 AST+1.225
elaide+1.151
outh+1.147
igree+1.141
 Monarch+1.138
Neg logit contributions
wash-1.431
-1.399
pak-1.343
gross-1.314
kat-1.308
Token
Token ID251
Feature activation-9.20e-02

Pos logit contributions
wash+0.062
+0.061
pak+0.056
kat+0.054
gross+0.054
Neg logit contributions
 AST-0.101
elaide-0.097
outh-0.097
igree-0.097
ovember-0.096
Token and
Token ID290
Feature activation-1.56e-01

Pos logit contributions
 AST+0.167
elaide+0.160
outh+0.158
igree+0.158
ovember+0.157
Neg logit contributions
wash-0.165
-0.162
pak-0.153
kat-0.149
gross-0.149
Token
Token ID564
Feature activation-7.40e-02

Pos logit contributions
 AST+0.258
elaide+0.246
igree+0.243
outh+0.242
ovember+0.241
Neg logit contributions
wash-0.306
-0.302
pak-0.287
kat-0.280
gross-0.279
Token
Token ID250
Feature activation-1.06e-01

Pos logit contributions
 AST+0.171
elaide+0.165
igree+0.164
outh+0.164
ovember+0.164
Neg logit contributions
wash-0.095
-0.092
pak-0.086
kat-0.082
gross-0.082
Token
Token ID564
Feature activation+1.72e-01

Pos logit contributions
wash+0.127
+0.125
pak+0.118
kat+0.115
gross+0.115
Neg logit contributions
 AST-0.118
elaide-0.113
igree-0.111
outh-0.111
ovember-0.111
Token
Token ID250
Feature activation-6.06e-02

Pos logit contributions
wash+0.228
+0.223
pak+0.209
kat+0.200
gross+0.199
Neg logit contributions
 AST-0.385
elaide-0.373
igree-0.371
outh-0.371
ovember-0.371
TokenC
Token ID34
Feature activation+1.73e-01

Pos logit contributions
 AST+0.120
elaide+0.115
outh+0.114
igree+0.114
ovember+0.114
Neg logit contributions
wash-0.098
-0.097
pak-0.091
kat-0.088
gross-0.088
Tokenute
Token ID1133
Feature activation-3.59e-01

Pos logit contributions
wash+0.307
+0.304
pak+0.287
kat+0.279
gross+0.279
Neg logit contributions
 AST-0.314
elaide-0.301
outh-0.300
igree-0.297
ovember-0.297
Token video
Token ID2008
Feature activation-1.68e-01

Pos logit contributions
 AST+0.606
outh+0.573
elaide+0.571
igree+0.569
ovember+0.568
Neg logit contributions
wash-0.681
-0.669
pak-0.640
gross-0.624
kat-0.620
Token Aj
Token ID22028
Feature activation-7.05e-01

Pos logit contributions
 AST+0.275
elaide+0.261
igree+0.258
outh+0.258
ovember+0.257
Neg logit contributions
wash-0.329
-0.325
pak-0.310
gross-0.301
kat-0.301
Tokenit
Token ID270
Feature activation-1.67e-01

Pos logit contributions
 AST+1.389
elaide+1.335
igree+1.332
outh+1.329
ovember+1.323
Neg logit contributions
wash-1.128
-1.113
pak-1.038
gross-1.008
kat-1.003
Token
Token ID564
Feature activation+6.65e-02

Pos logit contributions
 AST+0.332
elaide+0.318
outh+0.316
ovember+0.316
igree+0.316
Neg logit contributions
wash-0.268
-0.262
pak-0.248
gross-0.240
kat-0.239
Token
Token ID246
Feature activation+1.09e-02

Pos logit contributions
wash+0.092
+0.089
pak+0.084
kat+0.081
gross+0.080
Neg logit contributions
 AST-0.147
elaide-0.142
igree-0.141
ovember-0.141
outh-0.141
TokenAren
Token ID43199
Feature activation+4.01e-01

Pos logit contributions
wash+0.019
+0.019
pak+0.018
kat+0.017
gross+0.017
Neg logit contributions
 AST-0.020
elaide-0.020
outh-0.019
igree-0.019
ovember-0.019
Token
Token ID447
Feature activation+6.83e-02

Pos logit contributions
wash+0.652
+0.642
pak+0.604
kat+0.585
gross+0.583
Neg logit contributions
 AST-0.791
elaide-0.761
igree-0.752
outh-0.752
ovember-0.748
Token for
Token ID329
Feature activation+4.82e-02

Pos logit contributions
 AST+0.268
elaide+0.254
outh+0.253
igree+0.251
 Monarch+0.249
Neg logit contributions
wash-0.335
-0.330
pak-0.316
kat-0.307
gross-0.304
Token tuition
Token ID18385
Feature activation+3.47e-01

Pos logit contributions
wash+0.101
+0.099
pak+0.095
kat+0.093
gross+0.092
Neg logit contributions
 AST-0.073
elaide-0.069
igree-0.068
outh-0.068
ovember-0.068
Token and
Token ID290
Feature activation+7.42e-02

Pos logit contributions
wash+0.698
+0.689
pak+0.655
kat+0.640
gross+0.639
Neg logit contributions
 AST-0.554
elaide-0.529
igree-0.522
outh-0.520
ovember-0.518
Token boasts
Token ID22103
Feature activation+2.70e-01

Pos logit contributions
wash+0.146
+0.144
pak+0.137
kat+0.134
gross+0.133
Neg logit contributions
 AST-0.121
elaide-0.115
igree-0.114
outh-0.114
ovember-0.113
Token a
Token ID257
Feature activation+7.15e-02

Pos logit contributions
wash+0.558
+0.551
pak+0.526
kat+0.513
gross+0.512
Neg logit contributions
 AST-0.415
elaide-0.393
igree-0.388
outh-0.388
ovember-0.385
Token high
Token ID1029
Feature activation-7.27e-01

Pos logit contributions
wash+0.142
+0.140
pak+0.133
kat+0.130
gross+0.130
Neg logit contributions
 AST-0.116
elaide-0.111
igree-0.109
outh-0.109
ovember-0.108
Token success
Token ID1943
Feature activation-2.59e-01

Pos logit contributions
 AST+1.086
elaide+1.035
igree+1.018
outh+1.015
ovember+1.012
Neg logit contributions
wash-1.536
-1.517
pak-1.448
kat-1.414
gross-1.411
Token rate
Token ID2494
Feature activation-1.63e-02

Pos logit contributions
 AST+0.414
elaide+0.398
igree+0.390
ovember+0.389
outh+0.389
Neg logit contributions
wash-0.517
-0.511
pak-0.485
kat-0.474
gross-0.474
Token in
Token ID287
Feature activation+6.88e-02

Pos logit contributions
 AST+0.027
elaide+0.025
igree+0.025
outh+0.025
ovember+0.025
Neg logit contributions
wash-0.032
-0.032
pak-0.030
gross-0.029
kat-0.029
Token getting
Token ID1972
Feature activation-2.10e-02

Pos logit contributions
wash+0.138
+0.137
pak+0.130
gross+0.127
kat+0.127
Neg logit contributions
 AST-0.108
elaide-0.105
igree-0.103
ovember-0.102
outh-0.102
Token its
Token ID663
Feature activation-1.28e-01

Pos logit contributions
 AST+0.035
elaide+0.034
igree+0.033
outh+0.033
ovember+0.033
Neg logit contributions
wash-0.041
-0.040
pak-0.038
kat-0.037
gross-0.037
Token has
Token ID468
Feature activation+1.48e-03

Pos logit contributions
 AST+0.153
elaide+0.143
outh+0.141
igree+0.140
ovember+0.139
Neg logit contributions
wash-0.313
-0.311
pak-0.298
kat-0.292
gross-0.292
Token a
Token ID257
Feature activation-8.06e-03

Pos logit contributions
wash+0.003
+0.003
pak+0.003
kat+0.003
gross+0.003
Neg logit contributions
 AST-0.002
elaide-0.002
outh-0.002
igree-0.002
ovember-0.002
Token fo
Token ID11511
Feature activation-3.74e-01

Pos logit contributions
 AST+0.013
elaide+0.012
igree+0.012
outh+0.012
ovember+0.012
Neg logit contributions
wash-0.016
-0.016
pak-0.015
kat-0.015
gross-0.015
Tokenos
Token ID418
Feature activation-1.40e-01

Pos logit contributions
 AST+0.685
elaide+0.653
outh+0.649
igree+0.649
ovember+0.642
Neg logit contributions
wash-0.661
-0.652
pak-0.619
kat-0.600
gross-0.599
Tokenball
Token ID1894
Feature activation-1.21e-01

Pos logit contributions
 AST+0.141
elaide+0.133
outh+0.131
igree+0.129
 Monarch+0.126
Neg logit contributions
wash-0.360
-0.359
pak-0.345
kat-0.337
gross-0.337
Token table
Token ID3084
Feature activation-9.38e-01

Pos logit contributions
 AST+0.173
elaide+0.163
igree+0.162
outh+0.161
ovember+0.160
Neg logit contributions
wash-0.263
-0.260
pak-0.249
kat-0.243
gross-0.243
Token,
Token ID11
Feature activation+3.78e-02

Pos logit contributions
 AST+1.509
elaide+1.442
outh+1.428
igree+1.420
ovember+1.409
Neg logit contributions
wash-1.844
-1.834
pak-1.747
kat-1.696
gross-1.691
Token and
Token ID290
Feature activation+4.58e-02

Pos logit contributions
wash+0.076
+0.075
pak+0.072
kat+0.070
gross+0.070
Neg logit contributions
 AST-0.060
elaide-0.057
igree-0.056
outh-0.056
ovember-0.056
Token it
Token ID340
Feature activation+5.93e-02

Pos logit contributions
wash+0.093
+0.092
pak+0.088
kat+0.086
gross+0.086
Neg logit contributions
 AST-0.072
elaide-0.068
outh-0.067
igree-0.067
ovember-0.067
Token saw
Token ID2497
Feature activation-3.18e-01

Pos logit contributions
wash+0.105
+0.104
pak+0.098
kat+0.095
gross+0.095
Neg logit contributions
 AST-0.109
elaide-0.104
igree-0.103
outh-0.103
ovember-0.102
Token action
Token ID2223
Feature activation-1.79e-01

Pos logit contributions
 AST+0.507
elaide+0.484
outh+0.480
igree+0.476
ovember+0.472
Neg logit contributions
wash-0.637
-0.629
pak-0.601
kat-0.585
gross-0.582
Token tools
Token ID4899
Feature activation+3.13e-01

Pos logit contributions
 AST+0.534
elaide+0.511
igree+0.503
outh+0.503
ovember+0.501
Neg logit contributions
wash-0.616
-0.608
pak-0.578
kat-0.560
gross-0.560
Token provided
Token ID2810
Feature activation-3.29e-01

Pos logit contributions
wash+0.578
+0.569
pak+0.541
kat+0.526
gross+0.524
Neg logit contributions
 AST-0.551
elaide-0.529
igree-0.522
outh-0.520
ovember-0.520
Token to
Token ID284
Feature activation-4.17e-02

Pos logit contributions
 AST+0.608
elaide+0.581
igree+0.575
outh+0.574
ovember+0.569
Neg logit contributions
wash-0.578
-0.568
pak-0.539
kat-0.524
gross-0.522
Token gather
Token ID6431
Feature activation-6.36e-01

Pos logit contributions
 AST+0.070
elaide+0.067
igree+0.066
outh+0.066
ovember+0.066
Neg logit contributions
wash-0.080
-0.079
pak-0.075
kat-0.073
gross-0.073
Token inf
Token ID1167
Feature activation-4.84e-01

Pos logit contributions
 AST+1.030
elaide+0.982
igree+0.969
outh+0.967
ovember+0.962
Neg logit contributions
wash-1.263
-1.246
pak-1.187
kat-1.157
gross-1.154
Tokenerences
Token ID4972
Feature activation-7.07e-01

Pos logit contributions
 AST+0.842
elaide+0.805
igree+0.797
outh+0.795
ovember+0.790
Neg logit contributions
wash-0.901
-0.889
pak-0.844
kat-0.821
gross-0.818
Token and
Token ID290
Feature activation-1.40e-01

Pos logit contributions
 AST+1.135
elaide+1.073
outh+1.066
igree+1.064
ovember+1.053
Neg logit contributions
wash-1.414
-1.393
pak-1.330
kat-1.297
gross-1.291
Token observations
Token ID13050
Feature activation+4.60e-02

Pos logit contributions
 AST+0.229
elaide+0.218
igree+0.215
outh+0.215
ovember+0.214
Neg logit contributions
wash-0.275
-0.271
pak-0.258
kat-0.251
gross-0.251
Token on
Token ID319
Feature activation-2.05e-01

Pos logit contributions
wash+0.089
+0.088
pak+0.084
kat+0.081
gross+0.081
Neg logit contributions
 AST-0.077
elaide-0.073
igree-0.072
outh-0.072
ovember-0.072
Token the
Token ID262
Feature activation-7.07e-02

Pos logit contributions
 AST+0.307
elaide+0.294
igree+0.289
outh+0.287
ovember+0.286
Neg logit contributions
wash-0.432
-0.427
pak-0.407
kat-0.397
gross-0.396
Token team
Token ID1074
Feature activation-2.22e-02

Pos logit contributions
 AST+0.100
elaide+0.095
igree+0.093
outh+0.093
ovember+0.092
Neg logit contributions
wash-0.155
-0.153
pak-0.147
kat-0.143
gross-0.143