TOP ACTIVATIONS
MAX = 8.372

ri va have se perate shr ines here , where p
skipped payments on non - deb t obligations if the government
only temple which has a shrine for Kar th ave ery
nu D urga also have shr ines here .
echoes of M . Night Shy am alan s
Vish nu temple have a shrine for Bh air ava .
ansky , The Deb as ement of Din ah
: There is a special shrine for Lord of medicine and
i , they have a shrine in this temple . A
of these three deb t free countries
to come . Deb t to fund infrastructure projects
being paired with " The Doors "? Yeah , dude ,
great things : Decre ases blood glucose .
Chan , an official with Greenpeace in southern China .
s just like using the Amazon store , only free !
support Sunday for Senate candidate Deb ra Ross , attorney general
failed attempt to cross the Misty Mountains through the Red horn
pre z debate . # Deb ate 2016 pic . twitter
, head of environmental group Greenpeace s International Nuclear
licensed under a Creative Commons Attribution - Non Commercial 3 .

MIN ACTIVATIONS
MIN = -8.469

Three months ago students at Ober lin College in Ohio objected
a pot - add led Ober lin College freshman 's
rate GT / s 72 GT / s 109 . 2
/ s 109 . 2 GT / s 120 . 5
a model of Pont iac GT O sold from 1969 till
160 Texture fill - rate GT / s 72 GT /
/ s 120 . 5 GT / s 180 . 7
family , fighting , and FO OD ! Oh crap
k ong / a - flex ible - limit - tr
/ s 180 . 7 GT / s 257 . 1
scale and violence of the forc ible recruitment by al -
David De Cast ro and Maur k ice P ounce y
/ s 257 . 1 GT / s Memory Clock 7000
, a major maker of Honey comb tablets , argue they
great , McDonnell said in response to a
of Stamford Bridge , the nort her ners were remarkably absent
frequent Dinosaur Jr . collaborator Maur a Jasper , an essay
traffic control and surveillance . McDonnell s office later
an incompetent fool . Even GT did a better job at
of the city 's famous Cock ers Roses business .

INTERVAL 4.162 - 8.372
CONTAINS 0.256%

also Trump hints he taped Comey conversations in veiled threat President
. <|endoftext|> Ill ust rious Illum ination : Incredible TR ON
pair but require out board amplification and electronics . A pair
. An array of online stores offer a huge range of
I liked the movie The Pur ge but with everything it

INTERVAL -0.049 - 4.162
CONTAINS 52.388%

Italian volunteers Storm Brigade were sent to the An z io
the Democratic Party was going to come down to Hillary Clinton
booth , Bour dain puts on a pair of reading glasses
a Dream a kick - as movie . And who
rise , that 's a huge rise , if you think

INTERVAL -4.259 - -0.049
CONTAINS 47.201%

have deemed UN FOR G IV ABLE ( though that hasn
UR -- With barely a month leading up to her retirement
one of many House Democrats to vote against the bill .
? And what better way to get people to pay attention
natural enemy , the British crown , to defeat a greater

INTERVAL -8.469 - -4.259
CONTAINS 0.154%

of the D - Day land ings . The
, Gh out a , Damascus , A by an ,
ED MON TON Omar Kh adr has agreed to remain
athing system used by the Mau Mau , and denied having
@ Ann C oul ter HAVE YOU SE EN
Tokenri
Token ID380
Feature activation+1.57e+00

Pos logit contributions
 proport+1.760
 suspic+1.711
 comr+1.469
 fortun+1.393
stress+1.281
Neg logit contributions
llah-1.783
ible-1.668
enegger-1.654
 IPM-1.612
esters-1.600
Tokenva
Token ID6862
Feature activation-1.32e+00

Pos logit contributions
 proport+1.509
 suspic+1.472
 comr+1.287
 fortun+1.230
stress+1.146
Neg logit contributions
llah-1.207
ible-1.117
enegger-1.111
 IPM-1.079
esters-1.068
Token have
Token ID423
Feature activation-1.09e-01

Pos logit contributions
llah+0.990
ible+0.915
enegger+0.898
 IPM+0.871
esters+0.868
Neg logit contributions
 proport-1.300
 suspic-1.274
 comr-1.118
 fortun-1.053
stress-0.987
Token se
Token ID384
Feature activation-5.23e-01

Pos logit contributions
llah+0.086
ible+0.081
enegger+0.079
 IPM+0.078
esters+0.077
Neg logit contributions
 proport-0.101
 suspic-0.099
 comr-0.086
 fortun-0.081
stress-0.076
Tokenperate
Token ID30052
Feature activation-7.96e-01

Pos logit contributions
llah+0.468
ible+0.439
enegger+0.433
 IPM+0.425
esters+0.423
Neg logit contributions
 proport-0.440
 suspic-0.431
 comr-0.369
 fortun-0.347
��-0.316
Token shr
Token ID10157
Feature activation+8.37e+00

Pos logit contributions
llah+0.693
ible+0.657
enegger+0.637
 IPM+0.632
esters+0.628
Neg logit contributions
 proport-0.674
 suspic-0.660
 comr-0.566
 fortun-0.525
stress-0.490
Tokenines
Token ID1127
Feature activation+1.92e+00

Pos logit contributions
 proport+5.076
 suspic+4.786
 comr+3.814
 fortun+3.662
stress+3.412
Neg logit contributions
llah-8.913
enegger-8.660
ible-8.381
-8.260
 IPM-8.251
Token here
Token ID994
Feature activation-4.12e-01

Pos logit contributions
 proport+1.919
 suspic+1.873
 comr+1.645
 fortun+1.579
stress+1.477
Neg logit contributions
llah-1.406
ible-1.293
enegger-1.289
 IPM-1.249
esters-1.234
Token,
Token ID11
Feature activation-1.75e-01

Pos logit contributions
llah+0.295
ible+0.272
enegger+0.268
 IPM+0.261
esters+0.258
Neg logit contributions
 proport-0.417
 suspic-0.409
 comr-0.361
 fortun-0.344
stress-0.322
Token where
Token ID810
Feature activation-1.97e+00

Pos logit contributions
llah+0.131
ible+0.122
enegger+0.120
 IPM+0.117
esters+0.116
Neg logit contributions
 proport-0.172
 suspic-0.168
 comr-0.148
 fortun-0.140
stress-0.131
Token p
Token ID279
Feature activation+1.50e+00

Pos logit contributions
llah+1.435
ible+1.336
enegger+1.291
 IPM+1.278
esters+1.266
Neg logit contributions
 proport-1.951
 suspic-1.912
 comr-1.676
 fortun-1.581
stress-1.478
Token skipped
Token ID26684
Feature activation-2.41e-01

Pos logit contributions
llah+0.739
ible+0.693
enegger+0.676
osal+0.654
 IPM+0.653
Neg logit contributions
 proport-0.995
 suspic-0.964
 comr-0.857
 fortun-0.808
��-0.751
Token payments
Token ID7524
Feature activation+2.44e-01

Pos logit contributions
llah+0.186
ible+0.172
enegger+0.171
 IPM+0.167
esters+0.165
Neg logit contributions
 proport-0.230
 suspic-0.225
 comr-0.197
 fortun-0.188
stress-0.175
Token on
Token ID319
Feature activation+3.36e-01

Pos logit contributions
 proport+0.248
 suspic+0.243
 comr+0.215
 fortun+0.205
stress+0.192
Neg logit contributions
llah-0.173
ible-0.160
enegger-0.158
 IPM-0.153
esters-0.152
Token non
Token ID1729
Feature activation-1.96e-01

Pos logit contributions
 proport+0.323
 suspic+0.314
 comr+0.276
 fortun+0.262
stress+0.244
Neg logit contributions
llah-0.258
ible-0.241
enegger-0.236
 IPM-0.231
esters-0.229
Token-
Token ID12
Feature activation+5.97e-01

Pos logit contributions
llah+0.158
ible+0.147
enegger+0.145
esters+0.141
 IPM+0.141
Neg logit contributions
 proport-0.183
 suspic-0.177
 comr-0.154
 fortun-0.148
��-0.135
Tokendeb
Token ID11275
Feature activation+8.00e+00

Pos logit contributions
 proport+0.491
 suspic+0.476
 comr+0.406
 fortun+0.385
stress+0.349
Neg logit contributions
llah-0.544
ible-0.511
enegger-0.507
 IPM-0.495
esters-0.493
Tokent
Token ID83
Feature activation+5.58e-01

Pos logit contributions
 proport+5.500
 suspic+5.224
 comr+4.276
 fortun+4.095
stress+3.880
Neg logit contributions
llah-7.997
enegger-7.709
 IPM-7.532
ible-7.362
esters-7.317
Token obligations
Token ID13675
Feature activation+9.01e-01

Pos logit contributions
 proport+0.517
 suspic+0.504
 comr+0.438
 fortun+0.418
stress+0.388
Neg logit contributions
llah-0.449
ible-0.418
enegger-0.414
 IPM-0.403
esters-0.399
Token if
Token ID611
Feature activation+6.79e-02

Pos logit contributions
 proport+0.923
 suspic+0.903
 comr+0.797
 fortun+0.764
stress+0.715
Neg logit contributions
llah-0.637
ible-0.586
enegger-0.581
 IPM-0.563
esters-0.557
Token the
Token ID262
Feature activation-1.69e-01

Pos logit contributions
 proport+0.066
 suspic+0.065
 comr+0.057
 fortun+0.054
stress+0.050
Neg logit contributions
llah-0.051
ible-0.048
enegger-0.047
 IPM-0.046
esters-0.045
Token government
Token ID1230
Feature activation+1.82e-01

Pos logit contributions
llah+0.135
ible+0.127
enegger+0.124
 IPM+0.122
esters+0.120
Neg logit contributions
 proport-0.157
 suspic-0.153
 comr-0.133
 fortun-0.126
stress-0.117
Token only
Token ID691
Feature activation+1.44e+00

Pos logit contributions
llah+0.073
ible+0.068
enegger+0.067
 IPM+0.066
esters+0.065
Neg logit contributions
 proport-0.083
 suspic-0.081
 comr-0.071
 fortun-0.066
stress-0.062
Token temple
Token ID12505
Feature activation+5.13e+00

Pos logit contributions
 proport+1.298
 suspic+1.263
 comr+1.095
 fortun+1.037
stress+0.965
Neg logit contributions
llah-1.185
ible-1.110
enegger-1.098
 IPM-1.075
esters-1.059
Token which
Token ID543
Feature activation-9.97e-01

Pos logit contributions
 proport+4.906
 suspic+4.769
 comr+4.155
 fortun+4.028
stress+3.741
Neg logit contributions
llah-3.959
enegger-3.649
ible-3.598
 IPM-3.491
esters-3.490
Token has
Token ID468
Feature activation+9.83e-01

Pos logit contributions
llah+0.704
ible+0.651
enegger+0.638
 IPM+0.627
esters+0.617
Neg logit contributions
 proport-1.013
 suspic-0.992
 comr-0.878
 fortun-0.830
stress-0.783
Token a
Token ID257
Feature activation+3.53e-01

Pos logit contributions
 proport+0.950
 suspic+0.927
 comr+0.811
 fortun+0.773
stress+0.724
Neg logit contributions
llah-0.750
ible-0.698
enegger-0.688
 IPM-0.675
esters-0.663
Token shrine
Token ID29981
Feature activation+7.98e+00

Pos logit contributions
 proport+0.322
 suspic+0.313
 comr+0.272
 fortun+0.256
stress+0.240
Neg logit contributions
llah-0.288
ible-0.270
enegger-0.265
 IPM-0.261
esters-0.256
Token for
Token ID329
Feature activation-7.20e-01

Pos logit contributions
 proport+7.388
 suspic+7.120
 comr+6.227
 fortun+6.072
stress+5.707
Neg logit contributions
llah-6.131
enegger-5.723
ible-5.598
esters-5.483
 IPM-5.480
Token Kar
Token ID9375
Feature activation+1.32e+00

Pos logit contributions
llah+0.548
ible+0.510
enegger+0.500
 IPM+0.492
esters+0.485
Neg logit contributions
 proport-0.697
 suspic-0.680
 comr-0.594
 fortun-0.562
stress-0.529
Tokenth
Token ID400
Feature activation+5.42e-01

Pos logit contributions
 proport+1.484
 suspic+1.455
 comr+1.296
 fortun+1.248
stress+1.172
Neg logit contributions
llah-0.813
ible-0.734
enegger-0.730
 IPM-0.700
esters-0.696
Tokenave
Token ID1015
Feature activation-1.25e+00

Pos logit contributions
 proport+0.762
 suspic+0.749
 comr+0.685
 fortun+0.664
stress+0.633
Neg logit contributions
llah-0.178
ible-0.151
enegger-0.144
osal-0.132
esters-0.132
Tokenery
Token ID1924
Feature activation+3.94e-01

Pos logit contributions
llah+1.394
ible+1.325
enegger+1.316
 IPM+1.290
esters+1.283
Neg logit contributions
 proport-0.780
 suspic-0.750
 comr-0.601
 fortun-0.550
stress-0.476
Tokennu
Token ID28803
Feature activation-2.23e-01

Pos logit contributions
 proport+2.735
 suspic+2.665
 comr+2.308
 fortun+2.200
stress+2.038
Neg logit contributions
llah-2.483
ible-2.310
enegger-2.297
 IPM-2.235
esters-2.213
Token D
Token ID360
Feature activation-4.62e-01

Pos logit contributions
llah+0.158
ible+0.145
enegger+0.144
 IPM+0.139
osal+0.138
Neg logit contributions
 proport-0.228
 suspic-0.223
 comr-0.196
 fortun-0.187
stress-0.176
Tokenurga
Token ID45098
Feature activation+1.42e+00

Pos logit contributions
llah+0.382
ible+0.357
enegger+0.352
 IPM+0.343
esters+0.342
Neg logit contributions
 proport-0.422
 suspic-0.412
 comr-0.356
 fortun-0.339
stress-0.311
Token also
Token ID635
Feature activation+7.51e-01

Pos logit contributions
 proport+1.447
 suspic+1.415
 comr+1.248
 fortun+1.195
stress+1.119
Neg logit contributions
llah-1.005
ible-0.925
enegger-0.917
 IPM-0.888
esters-0.879
Token have
Token ID423
Feature activation-2.36e-01

Pos logit contributions
 proport+0.761
 suspic+0.745
 comr+0.658
 fortun+0.626
stress+0.587
Neg logit contributions
llah-0.538
ible-0.497
enegger-0.490
 IPM-0.476
esters-0.471
Token shr
Token ID10157
Feature activation+7.94e+00

Pos logit contributions
llah+0.190
ible+0.180
enegger+0.175
 IPM+0.174
osal+0.171
Neg logit contributions
 proport-0.214
 suspic-0.209
 comr-0.181
 fortun-0.171
stress-0.160
Tokenines
Token ID1127
Feature activation+1.82e+00

Pos logit contributions
 proport+4.539
 suspic+4.260
 comr+3.400
 fortun+3.294
stress+3.221
Neg logit contributions
llah-8.382
enegger-8.217
 IPM-7.851
ible-7.844
-7.810
Token here
Token ID994
Feature activation-3.83e-01

Pos logit contributions
 proport+1.841
 suspic+1.799
 comr+1.584
 fortun+1.518
stress+1.421
Neg logit contributions
llah-1.312
ible-1.208
enegger-1.200
 IPM-1.164
esters-1.151
Token.
Token ID13
Feature activation-5.09e-02

Pos logit contributions
llah+0.266
ible+0.245
enegger+0.241
 IPM+0.234
esters+0.231
Neg logit contributions
 proport-0.397
 suspic-0.388
 comr-0.344
 fortun-0.328
stress-0.308
Token
Token ID198
Feature activation-2.81e-01

Pos logit contributions
llah+0.038
ible+0.035
enegger+0.035
 IPM+0.034
esters+0.033
Neg logit contributions
 proport-0.051
 suspic-0.049
 comr-0.043
 fortun-0.041
stress-0.038
Token
Token ID198
Feature activation+4.50e-02

Pos logit contributions
llah+0.221
enegger+0.207
ible+0.202
esters+0.197
 IPM+0.197
Neg logit contributions
 proport-0.251
 suspic-0.246
 comr-0.214
 fortun-0.209
stress-0.203
Token echoes
Token ID30346
Feature activation+1.14e+00

Pos logit contributions
llah+0.567
ible+0.529
enegger+0.521
 IPM+0.504
esters+0.503
Neg logit contributions
 proport-0.741
 suspic-0.720
 comr-0.631
 fortun-0.603
stress-0.564
Token of
Token ID286
Feature activation+3.44e-02

Pos logit contributions
 proport+1.116
 suspic+1.089
 comr+0.954
 fortun+0.914
stress+0.854
Neg logit contributions
llah-0.849
ible-0.782
enegger-0.779
 IPM-0.758
esters-0.747
Token M
Token ID337
Feature activation-8.58e-01

Pos logit contributions
 proport+0.033
 suspic+0.032
 comr+0.028
 fortun+0.027
stress+0.025
Neg logit contributions
llah-0.026
ible-0.025
enegger-0.024
 IPM-0.024
esters-0.023
Token.
Token ID13
Feature activation+5.86e-01

Pos logit contributions
llah+0.676
ible+0.634
enegger+0.623
esters+0.606
 IPM+0.604
Neg logit contributions
 proport-0.815
 suspic-0.790
 comr-0.691
 fortun-0.657
stress-0.610
Token Night
Token ID5265
Feature activation-1.36e+00

Pos logit contributions
 proport+0.582
 suspic+0.568
 comr+0.498
 fortun+0.479
stress+0.446
Neg logit contributions
llah-0.432
ible-0.398
enegger-0.398
 IPM-0.385
esters-0.382
Token Shy
Token ID36838
Feature activation+7.90e+00

Pos logit contributions
llah+1.083
ible+1.012
enegger+1.000
 IPM+0.968
esters+0.964
Neg logit contributions
 proport-1.282
 suspic-1.246
 comr-1.090
 fortun-1.033
stress-0.951
Tokenam
Token ID321
Feature activation+7.00e-01

Pos logit contributions
 proport+5.804
 suspic+5.664
 comr+4.729
 fortun+4.434
stress+4.173
Neg logit contributions
llah-7.574
enegger-7.235
ible-7.204
 IPM-7.030
RESULTS-6.910
Tokenalan
Token ID25786
Feature activation+8.84e-01

Pos logit contributions
 proport+0.766
 suspic+0.749
 comr+0.662
 fortun+0.642
��+0.576
Neg logit contributions
llah-0.453
ible-0.424
esters-0.424
osal-0.413
enegger-0.413
Token
Token ID447
Feature activation-1.79e-01

Pos logit contributions
 proport+0.847
 suspic+0.825
 comr+0.723
 fortun+0.689
stress+0.640
Neg logit contributions
llah-0.687
ible-0.637
enegger-0.635
 IPM-0.613
esters-0.610
Token
Token ID247
Feature activation+3.11e-01

Pos logit contributions
llah+0.201
enegger+0.192
ible+0.191
 IPM+0.188
esters+0.186
Neg logit contributions
 proport-0.107
 suspic-0.102
 comr-0.081
 fortun-0.075
stress-0.066
Tokens
Token ID82
Feature activation-4.32e-01

Pos logit contributions
 proport+0.369
 suspic+0.361
 comr+0.325
 fortun+0.313
stress+0.296
Neg logit contributions
llah-0.171
ible-0.153
enegger-0.151
 IPM-0.144
esters-0.143
Token Vish
Token ID36900
Feature activation+4.28e+00

Pos logit contributions
 proport+0.077
 suspic+0.075
 comr+0.065
 fortun+0.061
stress+0.057
Neg logit contributions
llah-0.066
ible-0.062
enegger-0.061
 IPM-0.059
esters-0.059
Tokennu
Token ID28803
Feature activation+2.22e-01

Pos logit contributions
 proport+3.801
 suspic+3.699
 comr+3.203
 fortun+3.051
stress+2.829
Neg logit contributions
llah-3.572
ible-3.329
enegger-3.316
 IPM-3.241
esters-3.198
Token temple
Token ID12505
Feature activation+4.77e+00

Pos logit contributions
 proport+0.210
 suspic+0.205
 comr+0.178
 fortun+0.169
stress+0.158
Neg logit contributions
llah-0.176
ible-0.162
enegger-0.161
 IPM-0.156
esters-0.156
Token have
Token ID423
Feature activation+4.85e-01

Pos logit contributions
 proport+4.611
 suspic+4.496
 comr+3.934
 fortun+3.784
stress+3.530
Neg logit contributions
llah-3.612
ible-3.341
enegger-3.338
 IPM-3.239
esters-3.180
Token a
Token ID257
Feature activation+4.55e-01

Pos logit contributions
 proport+0.467
 suspic+0.457
 comr+0.399
 fortun+0.378
stress+0.355
Neg logit contributions
llah-0.370
ible-0.345
enegger-0.338
 IPM-0.333
esters-0.327
Token shrine
Token ID29981
Feature activation+7.56e+00

Pos logit contributions
 proport+0.402
 suspic+0.392
 comr+0.338
 fortun+0.317
stress+0.295
Neg logit contributions
llah-0.385
ible-0.360
enegger-0.353
 IPM-0.348
osal-0.345
Token for
Token ID329
Feature activation-7.24e-01

Pos logit contributions
 proport+6.900
 suspic+6.635
 comr+5.803
 fortun+5.635
stress+5.271
Neg logit contributions
llah-5.926
enegger-5.548
ible-5.460
 IPM-5.333
esters-5.294
Token Bh
Token ID16581
Feature activation-2.55e-01

Pos logit contributions
llah+0.526
ible+0.486
enegger+0.474
 IPM+0.471
esters+0.463
Neg logit contributions
 proport-0.726
 suspic-0.711
 comr-0.622
 fortun-0.590
stress-0.559
Tokenair
Token ID958
Feature activation-1.13e+00

Pos logit contributions
llah+0.177
enegger+0.162
ible+0.161
 IPM+0.156
esters+0.154
Neg logit contributions
 proport-0.263
 suspic-0.257
 comr-0.227
 fortun-0.219
stress-0.206
Tokenava
Token ID4170
Feature activation-1.04e+00

Pos logit contributions
llah+0.780
ible+0.715
enegger+0.710
 IPM+0.688
esters+0.679
Neg logit contributions
 proport-1.183
 suspic-1.156
 comr-1.023
 fortun-0.982
stress-0.922
Token.
Token ID13
Feature activation-7.90e-02

Pos logit contributions
llah+0.704
ible+0.642
enegger+0.635
 IPM+0.613
osal+0.610
Neg logit contributions
 proport-1.091
 suspic-1.071
 comr-0.949
 fortun-0.900
stress-0.844
Tokenansky
Token ID49792
Feature activation-2.06e-01

Pos logit contributions
llah+2.549
ible+2.423
enegger+2.358
osal+2.278
esters+2.275
Neg logit contributions
 proport-2.949
 suspic-2.884
 comr-2.516
 fortun-2.379
��-2.160
Token,
Token ID11
Feature activation-1.29e-01

Pos logit contributions
llah+0.151
ible+0.139
enegger+0.138
 IPM+0.134
esters+0.132
Neg logit contributions
 proport-0.207
 suspic-0.202
 comr-0.178
 fortun-0.170
stress-0.159
Token
Token ID564
Feature activation-6.72e-02

Pos logit contributions
llah+0.098
ible+0.091
enegger+0.090
 IPM+0.088
esters+0.086
Neg logit contributions
 proport-0.125
 suspic-0.122
 comr-0.107
 fortun-0.102
stress-0.095
Token
Token ID250
Feature activation-8.83e-01

Pos logit contributions
llah+0.045
ible+0.041
enegger+0.040
 IPM+0.039
esters+0.039
Neg logit contributions
 proport-0.072
 suspic-0.070
 comr-0.062
 fortun-0.060
stress-0.056
TokenThe
Token ID464
Feature activation+3.84e-01

Pos logit contributions
llah+0.608
ible+0.558
enegger+0.548
 IPM+0.533
esters+0.528
Neg logit contributions
 proport-0.927
 suspic-0.907
 comr-0.801
 fortun-0.767
stress-0.717
Token Deb
Token ID8965
Feature activation+7.50e+00

Pos logit contributions
 proport+0.377
 suspic+0.368
 comr+0.323
 fortun+0.308
stress+0.287
Neg logit contributions
llah-0.290
ible-0.268
enegger-0.265
 IPM-0.258
esters-0.255
Tokenas
Token ID292
Feature activation+1.80e+00

Pos logit contributions
 proport+6.342
 suspic+6.114
 comr+5.203
 fortun+5.054
stress+4.793
Neg logit contributions
llah-6.201
enegger-5.950
 IPM-5.741
ible-5.617
-5.554
Tokenement
Token ID972
Feature activation+1.05e+00

Pos logit contributions
 proport+1.550
 suspic+1.502
 comr+1.292
 fortun+1.234
stress+1.151
Neg logit contributions
llah-1.556
enegger-1.452
ible-1.440
 IPM-1.411
esters-1.405
Token of
Token ID286
Feature activation+4.32e-02

Pos logit contributions
 proport+1.030
 suspic+1.008
 comr+0.883
 fortun+0.843
stress+0.783
Neg logit contributions
llah-0.796
ible-0.740
enegger-0.725
 IPM-0.708
osal-0.700
Token Din
Token ID23448
Feature activation+1.74e+00

Pos logit contributions
 proport+0.044
 suspic+0.043
 comr+0.038
 fortun+0.036
stress+0.034
Neg logit contributions
llah-0.031
ible-0.029
enegger-0.028
 IPM-0.028
esters-0.028
Tokenah
Token ID993
Feature activation+1.11e-01

Pos logit contributions
 proport+1.696
 suspic+1.653
 comr+1.449
 fortun+1.389
stress+1.300
Neg logit contributions
llah-1.318
ible-1.214
enegger-1.212
 IPM-1.176
esters-1.164
Token :
Token ID1058
Feature activation+9.20e-01

Pos logit contributions
 proport+1.436
 suspic+1.398
 comr+1.209
 fortun+1.147
stress+1.061
Neg logit contributions
llah-1.352
ible-1.260
enegger-1.248
 IPM-1.220
esters-1.207
Token There
Token ID1318
Feature activation+1.89e+00

Pos logit contributions
 proport+0.894
 suspic+0.874
 comr+0.764
 fortun+0.729
stress+0.680
Neg logit contributions
llah-0.699
ible-0.648
enegger-0.641
 IPM-0.627
esters-0.618
Token is
Token ID318
Feature activation+5.73e-01

Pos logit contributions
 proport+2.060
 suspic+2.016
 comr+1.794
 fortun+1.723
stress+1.623
Neg logit contributions
llah-1.210
ible-1.102
enegger-1.092
 IPM-1.053
esters-1.042
Token a
Token ID257
Feature activation+1.74e-01

Pos logit contributions
 proport+0.525
 suspic+0.513
 comr+0.445
 fortun+0.423
stress+0.395
Neg logit contributions
llah-0.462
ible-0.433
enegger-0.426
 IPM-0.420
esters-0.412
Token special
Token ID2041
Feature activation+7.83e-01

Pos logit contributions
 proport+0.156
 suspic+0.152
 comr+0.132
 fortun+0.125
stress+0.116
Neg logit contributions
llah-0.145
ible-0.136
enegger-0.133
 IPM-0.131
osal-0.129
Token shrine
Token ID29981
Feature activation+7.35e+00

Pos logit contributions
 proport+0.687
 suspic+0.670
 comr+0.576
 fortun+0.545
stress+0.505
Neg logit contributions
llah-0.666
ible-0.625
enegger-0.618
 IPM-0.607
esters-0.597
Token for
Token ID329
Feature activation-7.54e-01

Pos logit contributions
 proport+6.807
 suspic+6.564
 comr+5.700
 fortun+5.571
stress+5.198
Neg logit contributions
llah-5.762
enegger-5.362
ible-5.231
 IPM-5.108
esters-5.071
Token Lord
Token ID4453
Feature activation+2.89e-02

Pos logit contributions
llah+0.551
ible+0.509
enegger+0.500
 IPM+0.494
esters+0.485
Neg logit contributions
 proport-0.751
 suspic-0.736
 comr-0.643
 fortun-0.611
stress-0.575
Token of
Token ID286
Feature activation+5.16e-01

Pos logit contributions
 proport+0.028
 suspic+0.028
 comr+0.024
 fortun+0.023
stress+0.021
Neg logit contributions
llah-0.022
ible-0.020
enegger-0.020
 IPM-0.020
osal-0.019
Token medicine
Token ID9007
Feature activation+3.52e+00

Pos logit contributions
 proport+0.493
 suspic+0.482
 comr+0.420
 fortun+0.400
stress+0.373
Neg logit contributions
llah-0.400
ible-0.372
enegger-0.368
 IPM-0.360
esters-0.356
Token and
Token ID290
Feature activation+3.11e-01

Pos logit contributions
 proport+3.453
 suspic+3.364
 comr+2.953
 fortun+2.852
stress+2.658
Neg logit contributions
llah-2.610
enegger-2.407
ible-2.407
 IPM-2.318
esters-2.303
Tokeni
Token ID72
Feature activation+1.38e+00

Pos logit contributions
llah+3.112
ible+2.899
enegger+2.838
osal+2.782
 IPM+2.775
Neg logit contributions
 proport-3.293
 suspic-3.232
 comr-2.769
 fortun-2.625
��-2.406
Token,
Token ID11
Feature activation-1.60e-01

Pos logit contributions
 proport+1.355
 suspic+1.323
 comr+1.160
 fortun+1.108
stress+1.035
Neg logit contributions
llah-1.036
ible-0.957
enegger-0.950
 IPM-0.923
esters-0.913
Token they
Token ID484
Feature activation-1.29e+00

Pos logit contributions
llah+0.118
ible+0.110
enegger+0.108
 IPM+0.105
esters+0.105
Neg logit contributions
 proport-0.158
 suspic-0.154
 comr-0.135
 fortun-0.129
stress-0.121
Token have
Token ID423
Feature activation-3.31e-01

Pos logit contributions
llah+0.874
ible+0.802
enegger+0.790
 IPM+0.766
esters+0.757
Neg logit contributions
 proport-1.345
 suspic-1.323
 comr-1.173
 fortun-1.118
stress-1.049
Token a
Token ID257
Feature activation+7.63e-02

Pos logit contributions
llah+0.257
ible+0.241
enegger+0.237
 IPM+0.233
esters+0.229
Neg logit contributions
 proport-0.312
 suspic-0.306
 comr-0.266
 fortun-0.254
stress-0.238
Token shrine
Token ID29981
Feature activation+7.31e+00

Pos logit contributions
 proport+0.067
 suspic+0.066
 comr+0.057
 fortun+0.054
stress+0.050
Neg logit contributions
llah-0.064
ible-0.060
enegger-0.059
 IPM-0.058
osal-0.058
Token in
Token ID287
Feature activation-9.14e-02

Pos logit contributions
 proport+6.813
 suspic+6.584
 comr+5.709
 fortun+5.535
stress+5.192
Neg logit contributions
llah-5.670
enegger-5.296
ible-5.171
 IPM-5.091
esters-5.052
Token this
Token ID428
Feature activation-7.85e-01

Pos logit contributions
llah+0.070
ible+0.065
enegger+0.064
 IPM+0.063
esters+0.062
Neg logit contributions
 proport-0.088
 suspic-0.086
 comr-0.075
 fortun-0.072
stress-0.067
Token temple
Token ID12505
Feature activation+4.97e+00

Pos logit contributions
llah+0.686
ible+0.648
enegger+0.635
 IPM+0.626
esters+0.616
Neg logit contributions
 proport-0.665
 suspic-0.647
 comr-0.557
 fortun-0.525
stress-0.487
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
 proport+4.637
 suspic+4.513
 comr+3.902
 fortun+3.783
stress+3.519
Neg logit contributions
llah-3.887
enegger-3.648
ible-3.575
 IPM-3.501
esters-3.474
Token A
Token ID317
Feature activation-1.29e-01

Pos logit contributions
 proport+0.213
 suspic+0.208
 comr+0.181
 fortun+0.173
stress+0.161
Neg logit contributions
llah-0.176
ible-0.163
enegger-0.162
 IPM-0.158
esters-0.156
Token of
Token ID286
Feature activation-8.77e-02

Pos logit contributions
llah+0.132
ible+0.122
enegger+0.120
 IPM+0.117
osal+0.116
Neg logit contributions
 proport-0.177
 suspic-0.174
 comr-0.153
 fortun-0.146
stress-0.136
Token these
Token ID777
Feature activation-4.38e-01

Pos logit contributions
llah+0.066
ible+0.061
enegger+0.060
 IPM+0.059
esters+0.058
Neg logit contributions
 proport-0.086
 suspic-0.084
 comr-0.074
 fortun-0.070
stress-0.066
Token three
Token ID1115
Feature activation+7.14e-03

Pos logit contributions
llah+0.320
ible+0.296
enegger+0.290
 IPM+0.284
esters+0.281
Neg logit contributions
 proport-0.439
 suspic-0.426
 comr-0.376
 fortun-0.359
stress-0.337
Token
Token ID564
Feature activation+1.04e+00

Pos logit contributions
 proport+0.007
 suspic+0.007
 comr+0.006
 fortun+0.006
stress+0.006
Neg logit contributions
llah-0.005
ible-0.005
enegger-0.005
 IPM-0.005
esters-0.004
Token
Token ID250
Feature activation+8.15e-02

Pos logit contributions
 proport+0.968
 suspic+0.943
 comr+0.822
 fortun+0.784
stress+0.728
Neg logit contributions
llah-0.827
ible-0.768
enegger-0.759
 IPM-0.740
esters-0.735
Tokendeb
Token ID11275
Feature activation+7.29e+00

Pos logit contributions
 proport+0.078
 suspic+0.076
 comr+0.067
 fortun+0.064
stress+0.059
Neg logit contributions
llah-0.063
ible-0.059
enegger-0.058
esters-0.056
 IPM-0.056
Tokent
Token ID83
Feature activation+4.81e-01

Pos logit contributions
 proport+5.214
 suspic+4.997
 comr+4.111
 fortun+3.961
stress+3.693
Neg logit contributions
llah-7.050
enegger-6.776
 IPM-6.679
ible-6.524
esters-6.443
Token free
Token ID1479
Feature activation-1.96e+00

Pos logit contributions
 proport+0.474
 suspic+0.463
 comr+0.406
 fortun+0.388
stress+0.362
Neg logit contributions
llah-0.360
ible-0.334
enegger-0.329
 IPM-0.320
esters-0.317
Token
Token ID447
Feature activation+4.88e-01

Pos logit contributions
llah+1.373
ible+1.261
enegger+1.224
 IPM+1.208
esters+1.207
Neg logit contributions
 proport-2.034
 suspic-1.985
 comr-1.761
 fortun-1.672
stress-1.576
Token
Token ID251
Feature activation+6.14e-01

Pos logit contributions
 proport+0.499
 suspic+0.489
 comr+0.431
 fortun+0.413
stress+0.387
Neg logit contributions
llah-0.346
ible-0.317
enegger-0.314
 IPM-0.306
esters-0.303
Token countries
Token ID2678
Feature activation+2.53e-01

Pos logit contributions
 proport+0.623
 suspic+0.609
 comr+0.537
 fortun+0.514
stress+0.481
Neg logit contributions
llah-0.440
ible-0.405
enegger-0.402
 IPM-0.389
esters-0.385
Token to
Token ID284
Feature activation-5.59e-02

Pos logit contributions
llah+1.522
ible+1.402
enegger+1.367
 IPM+1.323
esters+1.321
Neg logit contributions
 proport-2.491
 suspic-2.445
 comr-2.176
 fortun-2.081
stress-1.947
Token come
Token ID1282
Feature activation-5.02e-01

Pos logit contributions
llah+0.038
ible+0.035
enegger+0.035
esters+0.033
 IPM+0.033
Neg logit contributions
 proport-0.059
 suspic-0.057
 comr-0.051
 fortun-0.049
stress-0.046
Token.
Token ID13
Feature activation-2.57e-02

Pos logit contributions
llah+0.349
ible+0.321
enegger+0.318
 IPM+0.306
esters+0.304
Neg logit contributions
 proport-0.522
 suspic-0.511
 comr-0.452
 fortun-0.432
stress-0.405
Token
Token ID198
Feature activation-3.93e-01

Pos logit contributions
llah+0.021
ible+0.019
enegger+0.019
 IPM+0.019
esters+0.018
Neg logit contributions
 proport-0.024
 suspic-0.023
 comr-0.020
 fortun-0.019
stress-0.018
Token
Token ID198
Feature activation-1.61e-01

Pos logit contributions
llah+0.309
enegger+0.289
ible+0.282
esters+0.275
 IPM+0.275
Neg logit contributions
 proport-0.351
 suspic-0.343
 comr-0.299
 fortun-0.292
stress-0.283
TokenDeb
Token ID16587
Feature activation+7.17e+00

Pos logit contributions
llah+0.126
ible+0.117
enegger+0.115
 IPM+0.112
esters+0.111
Neg logit contributions
 proport-0.155
 suspic-0.150
 comr-0.131
 fortun-0.125
stress-0.115
Tokent
Token ID83
Feature activation+7.11e-01

Pos logit contributions
 proport+5.121
 suspic+4.888
 comr+4.062
 fortun+3.858
stress+3.627
Neg logit contributions
llah-7.024
enegger-6.685
 IPM-6.563
ible-6.529
esters-6.437
Token to
Token ID284
Feature activation-3.11e-01

Pos logit contributions
 proport+0.747
 suspic+0.731
 comr+0.646
 fortun+0.620
stress+0.582
Neg logit contributions
llah-0.483
ible-0.445
enegger-0.440
 IPM-0.426
esters-0.421
Token fund
Token ID1814
Feature activation+7.47e-01

Pos logit contributions
llah+0.212
ible+0.196
enegger+0.192
 IPM+0.187
esters+0.184
Neg logit contributions
 proport-0.325
 suspic-0.319
 comr-0.283
 fortun-0.271
stress-0.255
Token infrastructure
Token ID6884
Feature activation-6.51e-01

Pos logit contributions
 proport+0.705
 suspic+0.687
 comr+0.599
 fortun+0.572
stress+0.532
Neg logit contributions
llah-0.590
ible-0.548
enegger-0.544
 IPM-0.530
esters-0.524
Token projects
Token ID4493
Feature activation-2.34e-01

Pos logit contributions
llah+0.453
ible+0.422
enegger+0.415
 IPM+0.404
esters+0.396
Neg logit contributions
 proport-0.672
 suspic-0.656
 comr-0.580
 fortun-0.554
stress-0.520
Token being
Token ID852
Feature activation-3.70e-01

Pos logit contributions
 proport+0.596
 suspic+0.581
 comr+0.509
 fortun+0.485
stress+0.454
Neg logit contributions
llah-0.467
ible-0.434
enegger-0.431
 IPM-0.418
esters-0.414
Token paired
Token ID20312
Feature activation+7.09e-01

Pos logit contributions
llah+0.276
ible+0.256
enegger+0.254
 IPM+0.248
esters+0.244
Neg logit contributions
 proport-0.364
 suspic-0.355
 comr-0.312
 fortun-0.298
stress-0.279
Token with
Token ID351
Feature activation+7.06e-01

Pos logit contributions
 proport+0.661
 suspic+0.646
 comr+0.565
 fortun+0.534
stress+0.496
Neg logit contributions
llah-0.566
ible-0.527
enegger-0.522
 IPM-0.508
esters-0.503
Token "
Token ID366
Feature activation+1.21e+00

Pos logit contributions
 proport+0.679
 suspic+0.660
 comr+0.578
 fortun+0.550
stress+0.513
Neg logit contributions
llah-0.545
ible-0.507
enegger-0.503
 IPM-0.488
esters-0.483
TokenThe
Token ID464
Feature activation+9.82e-01

Pos logit contributions
 proport+1.155
 suspic+1.127
 comr+0.984
 fortun+0.940
stress+0.874
Neg logit contributions
llah-0.945
ible-0.876
enegger-0.870
 IPM-0.846
esters-0.838
Token Doors
Token ID33775
Feature activation+7.14e+00

Pos logit contributions
 proport+0.924
 suspic+0.900
 comr+0.784
 fortun+0.747
stress+0.694
Neg logit contributions
llah-0.779
ible-0.725
enegger-0.720
 IPM-0.700
esters-0.693
Token"?
Token ID13984
Feature activation-9.95e-01

Pos logit contributions
 proport+6.202
 suspic+6.008
 comr+5.160
 fortun+5.016
stress+4.698
Neg logit contributions
llah-5.991
enegger-5.534
ible-5.477
 IPM-5.363
esters-5.306
Token Yeah
Token ID9425
Feature activation-1.68e+00

Pos logit contributions
llah+0.761
ible+0.709
enegger+0.704
 IPM+0.686
esters+0.675
Neg logit contributions
 proport-0.969
 suspic-0.945
 comr-0.828
 fortun-0.784
stress-0.727
Token,
Token ID11
Feature activation+4.85e-01

Pos logit contributions
llah+1.170
ible+1.091
enegger+1.070
esters+1.028
 IPM+1.026
Neg logit contributions
 proport-1.745
 suspic-1.700
 comr-1.507
 fortun-1.439
stress-1.339
Token dude
Token ID18396
Feature activation+3.26e-01

Pos logit contributions
 proport+0.487
 suspic+0.475
 comr+0.418
 fortun+0.399
stress+0.374
Neg logit contributions
llah-0.353
ible-0.327
enegger-0.324
 IPM-0.315
esters-0.311
Token,
Token ID11
Feature activation+3.78e-01

Pos logit contributions
 proport+0.333
 suspic+0.326
 comr+0.287
 fortun+0.275
stress+0.257
Neg logit contributions
llah-0.232
ible-0.214
enegger-0.212
 IPM-0.205
esters-0.203
Token great
Token ID1049
Feature activation+7.37e-01

Pos logit contributions
llah+0.083
ible+0.077
enegger+0.077
 IPM+0.075
esters+0.074
Neg logit contributions
 proport-0.106
 suspic-0.103
 comr-0.090
 fortun-0.086
stress-0.080
Token things
Token ID1243
Feature activation+2.08e+00

Pos logit contributions
 proport+0.648
 suspic+0.631
 comr+0.544
 fortun+0.517
stress+0.478
Neg logit contributions
llah-0.628
ible-0.586
enegger-0.583
 IPM-0.568
esters-0.563
Token:
Token ID25
Feature activation+1.63e+00

Pos logit contributions
 proport+2.029
 suspic+1.978
 comr+1.732
 fortun+1.662
stress+1.554
Neg logit contributions
llah-1.565
ible-1.442
enegger-1.435
 IPM-1.397
esters-1.381
Token
Token ID198
Feature activation-2.56e-01

Pos logit contributions
 proport+1.616
 suspic+1.582
 comr+1.387
 fortun+1.326
stress+1.237
Neg logit contributions
llah-1.207
ible-1.117
enegger-1.105
 IPM-1.076
esters-1.063
Token
Token ID198
Feature activation-5.98e-02

Pos logit contributions
llah+0.203
enegger+0.189
ible+0.185
esters+0.180
 IPM+0.180
Neg logit contributions
 proport-0.227
 suspic-0.220
 comr-0.193
 fortun-0.188
stress-0.183
TokenDecre
Token ID43198
Feature activation+7.11e+00

Pos logit contributions
llah+0.050
ible+0.047
enegger+0.047
 IPM+0.045
esters+0.045
Neg logit contributions
 proport-0.054
 suspic-0.052
 comr-0.045
 fortun-0.043
stress-0.039
Tokenases
Token ID1386
Feature activation+1.35e+00

Pos logit contributions
 proport+4.921
 suspic+4.647
 comr+3.894
 fortun+3.742
stress+3.561
Neg logit contributions
llah-6.969
enegger-6.612
ible-6.458
 IPM-6.420
esters-6.288
Token blood
Token ID2910
Feature activation-3.62e-01

Pos logit contributions
 proport+1.263
 suspic+1.234
 comr+1.074
 fortun+1.026
stress+0.949
Neg logit contributions
llah-1.065
ible-0.991
enegger-0.982
 IPM-0.957
esters-0.947
Token glucose
Token ID15701
Feature activation-6.35e-01

Pos logit contributions
llah+0.223
ible+0.206
enegger+0.199
esters+0.194
 IPM+0.192
Neg logit contributions
 proport-0.403
 suspic-0.396
 comr-0.352
 fortun-0.339
��-0.316
Token.
Token ID13
Feature activation+7.55e-01

Pos logit contributions
llah+0.423
ible+0.392
enegger+0.382
 IPM+0.373
esters+0.371
Neg logit contributions
 proport-0.670
 suspic-0.660
 comr-0.586
 fortun-0.563
stress-0.521
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
 proport+0.718
 suspic+0.701
 comr+0.611
 fortun+0.582
stress+0.539
Neg logit contributions
llah-0.592
ible-0.551
enegger-0.547
 IPM-0.533
esters-0.526
Token Chan
Token ID18704
Feature activation+1.76e+00

Pos logit contributions
llah+0.265
ible+0.246
enegger+0.244
 IPM+0.236
esters+0.234
Neg logit contributions
 proport-0.341
 suspic-0.334
 comr-0.292
 fortun-0.279
stress-0.259
Token,
Token ID11
Feature activation-2.20e-01

Pos logit contributions
 proport+1.714
 suspic+1.675
 comr+1.466
 fortun+1.403
stress+1.317
Neg logit contributions
llah-1.327
ible-1.225
enegger-1.217
 IPM-1.186
esters-1.172
Token an
Token ID281
Feature activation-1.07e+00

Pos logit contributions
llah+0.175
ible+0.163
enegger+0.162
 IPM+0.158
esters+0.155
Neg logit contributions
 proport-0.207
 suspic-0.201
 comr-0.176
 fortun-0.167
stress-0.155
Token official
Token ID1743
Feature activation-4.34e-01

Pos logit contributions
llah+0.853
ible+0.793
enegger+0.788
 IPM+0.768
esters+0.759
Neg logit contributions
 proport-1.001
 suspic-0.976
 comr-0.850
 fortun-0.810
stress-0.753
Token with
Token ID351
Feature activation+4.09e-01

Pos logit contributions
llah+0.294
ible+0.270
enegger+0.265
 IPM+0.259
esters+0.255
Neg logit contributions
 proport-0.459
 suspic-0.448
 comr-0.398
 fortun-0.380
stress-0.356
Token Greenpeace
Token ID42793
Feature activation+7.11e+00

Pos logit contributions
 proport+0.387
 suspic+0.377
 comr+0.329
 fortun+0.314
stress+0.292
Neg logit contributions
llah-0.322
ible-0.299
enegger-0.298
 IPM-0.290
esters-0.286
Token in
Token ID287
Feature activation-1.92e-01

Pos logit contributions
 proport+6.390
 suspic+6.277
 comr+5.409
 fortun+5.174
stress+4.981
Neg logit contributions
llah-5.571
ible-5.045
enegger-5.027
osal-4.944
 IPM-4.935
Token southern
Token ID8372
Feature activation-2.25e+00

Pos logit contributions
llah+0.132
ible+0.123
enegger+0.121
 IPM+0.118
esters+0.116
Neg logit contributions
 proport-0.201
 suspic-0.196
 comr-0.174
 fortun-0.166
stress-0.155
Token China
Token ID2807
Feature activation+6.42e-01

Pos logit contributions
llah+1.456
ible+1.352
enegger+1.318
 IPM+1.290
esters+1.279
Neg logit contributions
 proport-2.425
 suspic-2.375
 comr-2.100
 fortun-2.009
stress-1.891
Token.
Token ID13
Feature activation-2.71e-01

Pos logit contributions
 proport+0.668
 suspic+0.654
 comr+0.579
 fortun+0.554
stress+0.517
Neg logit contributions
llah-0.444
ible-0.411
enegger-0.405
 IPM-0.391
esters-0.389
Token
Token ID198
Feature activation-4.79e-01

Pos logit contributions
llah+0.194
ible+0.178
enegger+0.178
 IPM+0.174
esters+0.170
Neg logit contributions
 proport-0.279
 suspic-0.273
 comr-0.241
 fortun-0.230
stress-0.213
Tokens
Token ID82
Feature activation-7.37e-01

Pos logit contributions
llah+0.072
ible+0.066
enegger+0.065
 IPM+0.061
esters+0.061
Neg logit contributions
 proport-0.140
 suspic-0.137
 comr-0.123
 fortun-0.118
stress-0.111
Token just
Token ID655
Feature activation-3.40e-01

Pos logit contributions
llah+0.501
ible+0.465
enegger+0.456
 IPM+0.443
esters+0.435
Neg logit contributions
 proport-0.775
 suspic-0.753
 comr-0.670
 fortun-0.641
stress-0.603
Token like
Token ID588
Feature activation+3.41e-01

Pos logit contributions
llah+0.250
ible+0.233
enegger+0.230
 IPM+0.225
esters+0.221
Neg logit contributions
 proport-0.338
 suspic-0.329
 comr-0.291
 fortun-0.277
stress-0.260
Token using
Token ID1262
Feature activation+5.28e-01

Pos logit contributions
 proport+0.331
 suspic+0.322
 comr+0.283
 fortun+0.269
stress+0.252
Neg logit contributions
llah-0.259
ible-0.241
enegger-0.237
 IPM-0.233
esters-0.229
Token the
Token ID262
Feature activation-1.09e-01

Pos logit contributions
 proport+0.504
 suspic+0.491
 comr+0.430
 fortun+0.408
stress+0.383
Neg logit contributions
llah-0.409
ible-0.384
enegger-0.376
 IPM-0.371
esters-0.364
Token Amazon
Token ID6186
Feature activation+7.10e+00

Pos logit contributions
llah+0.082
ible+0.077
enegger+0.075
 IPM+0.074
esters+0.072
Neg logit contributions
 proport-0.107
 suspic-0.104
 comr-0.091
 fortun-0.087
stress-0.082
Token store
Token ID3650
Feature activation+4.82e+00

Pos logit contributions
 proport+6.197
 suspic+6.100
 comr+5.234
 fortun+5.053
stress+4.655
Neg logit contributions
llah-5.842
enegger-5.493
ible-5.286
esters-5.224
 IPM-5.189
Token,
Token ID11
Feature activation+1.39e-01

Pos logit contributions
 proport+4.692
 suspic+4.572
 comr+4.002
 fortun+3.859
stress+3.624
Neg logit contributions
llah-3.592
enegger-3.295
ible-3.264
 IPM-3.174
esters-3.149
Token only
Token ID691
Feature activation+9.88e-01

Pos logit contributions
 proport+0.141
 suspic+0.138
 comr+0.121
 fortun+0.116
stress+0.109
Neg logit contributions
llah-0.100
ible-0.092
enegger-0.091
 IPM-0.088
esters-0.087
Token free
Token ID1479
Feature activation-1.89e+00

Pos logit contributions
 proport+0.983
 suspic+0.960
 comr+0.845
 fortun+0.808
stress+0.756
Neg logit contributions
llah-0.726
ible-0.671
enegger-0.665
 IPM-0.646
esters-0.639
Token!
Token ID0
Feature activation-1.01e+00

Pos logit contributions
llah+1.288
ible+1.212
enegger+1.168
 IPM+1.137
osal+1.120
Neg logit contributions
 proport-1.988
 suspic-1.957
 comr-1.727
 fortun-1.643
stress-1.557
Token support
Token ID1104
Feature activation-7.24e-01

Pos logit contributions
 proport+0.872
 suspic+0.851
 comr+0.753
 fortun+0.722
stress+0.678
Neg logit contributions
llah-0.573
ible-0.527
enegger-0.522
 IPM-0.506
esters-0.499
Token Sunday
Token ID3502
Feature activation-5.29e-02

Pos logit contributions
llah+0.508
ible+0.472
enegger+0.461
 IPM+0.445
esters+0.444
Neg logit contributions
 proport-0.745
 suspic-0.731
 comr-0.649
 fortun-0.615
stress-0.575
Token for
Token ID329
Feature activation-1.39e+00

Pos logit contributions
llah+0.038
ible+0.035
enegger+0.035
 IPM+0.034
esters+0.033
Neg logit contributions
 proport-0.054
 suspic-0.052
 comr-0.046
 fortun-0.044
stress-0.041
Token Senate
Token ID3845
Feature activation+2.19e+00

Pos logit contributions
llah+1.070
ible+0.999
enegger+0.988
 IPM+0.960
esters+0.951
Neg logit contributions
 proport-1.336
 suspic-1.297
 comr-1.140
 fortun-1.076
stress-1.008
Token candidate
Token ID4540
Feature activation-1.67e+00

Pos logit contributions
 proport+2.065
 suspic+2.014
 comr+1.756
 fortun+1.678
stress+1.564
Neg logit contributions
llah-1.722
ible-1.590
enegger-1.584
 IPM-1.540
esters-1.526
Token Deb
Token ID8965
Feature activation+7.06e+00

Pos logit contributions
llah+1.232
ible+1.157
enegger+1.122
 IPM+1.116
esters+1.094
Neg logit contributions
 proport-1.655
 suspic-1.603
 comr-1.414
 fortun-1.348
stress-1.259
Tokenra
Token ID430
Feature activation+1.82e+00

Pos logit contributions
 proport+5.271
 suspic+4.903
 comr+4.260
 fortun+3.987
stress+3.826
Neg logit contributions
llah-6.542
enegger-6.222
 IPM-6.044
-5.940
RESULTS-5.900
Token Ross
Token ID9847
Feature activation-1.70e+00

Pos logit contributions
 proport+1.702
 suspic+1.661
 comr+1.445
 fortun+1.379
stress+1.279
Neg logit contributions
llah-1.454
ible-1.352
enegger-1.341
 IPM-1.306
esters-1.292
Token,
Token ID11
Feature activation-3.82e-01

Pos logit contributions
llah+1.248
ible+1.162
enegger+1.155
 IPM+1.118
esters+1.104
Neg logit contributions
 proport-1.698
 suspic-1.663
 comr-1.461
 fortun-1.398
stress-1.295
Token attorney
Token ID6136
Feature activation-8.40e-02

Pos logit contributions
llah+0.283
ible+0.262
enegger+0.260
 IPM+0.252
esters+0.249
Neg logit contributions
 proport-0.378
 suspic-0.369
 comr-0.324
 fortun-0.310
stress-0.289
Token general
Token ID2276
Feature activation+1.22e+00

Pos logit contributions
llah+0.075
ible+0.071
enegger+0.070
 IPM+0.069
osal+0.068
Neg logit contributions
 proport-0.069
 suspic-0.068
 comr-0.058
 fortun-0.054
stress-0.050
Token failed
Token ID4054
Feature activation+7.02e-01

Pos logit contributions
 proport+0.313
 suspic+0.304
 comr+0.268
 fortun+0.256
stress+0.239
Neg logit contributions
llah-0.228
ible-0.212
enegger-0.209
 IPM-0.203
esters-0.202
Token attempt
Token ID2230
Feature activation-7.05e-01

Pos logit contributions
 proport+0.723
 suspic+0.707
 comr+0.624
 fortun+0.599
stress+0.561
Neg logit contributions
llah-0.493
ible-0.452
enegger-0.450
 IPM-0.436
esters-0.431
Token to
Token ID284
Feature activation+2.17e-01

Pos logit contributions
llah+0.473
ible+0.438
enegger+0.429
esters+0.417
 IPM+0.416
Neg logit contributions
 proport-0.745
 suspic-0.728
 comr-0.647
 fortun-0.616
stress-0.580
Token cross
Token ID3272
Feature activation+4.02e-01

Pos logit contributions
 proport+0.216
 suspic+0.211
 comr+0.185
 fortun+0.177
stress+0.166
Neg logit contributions
llah-0.160
ible-0.147
enegger-0.147
 IPM-0.142
esters-0.141
Token the
Token ID262
Feature activation+2.28e-01

Pos logit contributions
 proport+0.386
 suspic+0.377
 comr+0.329
 fortun+0.314
stress+0.293
Neg logit contributions
llah-0.311
ible-0.289
enegger-0.285
 IPM-0.278
esters-0.276
Token Misty
Token ID47330
Feature activation+7.05e+00

Pos logit contributions
 proport+0.216
 suspic+0.211
 comr+0.184
 fortun+0.175
stress+0.164
Neg logit contributions
llah-0.179
ible-0.166
enegger-0.164
 IPM-0.160
esters-0.159
Token Mountains
Token ID21124
Feature activation+6.26e-01

Pos logit contributions
 proport+7.580
 suspic+7.502
 comr+6.665
 fortun+6.356
stress+6.018
Neg logit contributions
llah-4.456
ible-4.017
enegger-4.000
osal-3.824
 IPM-3.794
Token through
Token ID832
Feature activation+8.59e-01

Pos logit contributions
 proport+0.627
 suspic+0.612
 comr+0.539
 fortun+0.515
stress+0.482
Neg logit contributions
llah-0.457
ible-0.422
enegger-0.418
 IPM-0.406
esters-0.402
Token the
Token ID262
Feature activation+2.82e-01

Pos logit contributions
 proport+0.823
 suspic+0.802
 comr+0.701
 fortun+0.668
stress+0.624
Neg logit contributions
llah-0.665
ible-0.619
enegger-0.612
 IPM-0.595
esters-0.592
Token Red
Token ID2297
Feature activation+2.67e+00

Pos logit contributions
 proport+0.265
 suspic+0.258
 comr+0.225
 fortun+0.214
stress+0.199
Neg logit contributions
llah-0.223
ible-0.208
enegger-0.205
 IPM-0.200
esters-0.198
Tokenhorn
Token ID25311
Feature activation+1.16e+00

Pos logit contributions
 proport+2.885
 suspic+2.836
 comr+2.522
 fortun+2.426
stress+2.300
Neg logit contributions
llah-1.707
enegger-1.539
ible-1.532
 IPM-1.497
esters-1.466
Token pre
Token ID662
Feature activation+1.67e+00

Pos logit contributions
llah+0.002
ible+0.002
enegger+0.002
 IPM+0.002
esters+0.002
Neg logit contributions
 proport-0.003
 suspic-0.003
 comr-0.003
 fortun-0.003
stress-0.003
Tokenz
Token ID89
Feature activation+5.08e-01

Pos logit contributions
 proport+1.679
 suspic+1.642
 comr+1.444
 fortun+1.385
stress+1.293
Neg logit contributions
llah-1.207
ible-1.110
enegger-1.102
 IPM-1.070
esters-1.060
Token debate
Token ID4384
Feature activation+6.20e-01

Pos logit contributions
 proport+0.497
 suspic+0.485
 comr+0.425
 fortun+0.407
stress+0.380
Neg logit contributions
llah-0.382
ible-0.353
enegger-0.351
 IPM-0.341
esters-0.337
Token.
Token ID13
Feature activation+1.21e-01

Pos logit contributions
 proport+0.627
 suspic+0.613
 comr+0.538
 fortun+0.517
stress+0.485
Neg logit contributions
llah-0.446
ible-0.409
enegger-0.408
 IPM-0.395
esters-0.391
Token #
Token ID1303
Feature activation-5.53e-01

Pos logit contributions
 proport+0.121
 suspic+0.118
 comr+0.103
 fortun+0.099
stress+0.092
Neg logit contributions
llah-0.090
ible-0.083
enegger-0.082
 IPM-0.080
esters-0.079
TokenDeb
Token ID16587
Feature activation+6.93e+00

Pos logit contributions
llah+0.494
ible+0.464
enegger+0.460
 IPM+0.448
esters+0.445
Neg logit contributions
 proport-0.465
 suspic-0.451
 comr-0.385
 fortun-0.366
stress-0.333
Tokenate
Token ID378
Feature activation-1.28e+00

Pos logit contributions
 proport+4.391
 suspic+4.314
 comr+3.519
 fortun+3.304
stress+3.275
Neg logit contributions
llah-6.886
enegger-6.679
 IPM-6.488
ible-6.286
RESULTS-6.184
Token2016
Token ID5304
Feature activation-4.11e-01

Pos logit contributions
llah+0.928
ible+0.860
enegger+0.849
 IPM+0.820
esters+0.818
Neg logit contributions
 proport-1.286
 suspic-1.255
 comr-1.104
 fortun-1.057
stress-0.986
Token pic
Token ID8301
Feature activation+9.03e-01

Pos logit contributions
llah+0.281
ible+0.257
enegger+0.255
 IPM+0.247
esters+0.244
Neg logit contributions
 proport-0.431
 suspic-0.421
 comr-0.373
 fortun-0.357
stress-0.335
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
 proport+0.811
 suspic+0.792
 comr+0.692
 fortun+0.675
stress+0.661
Neg logit contributions
llah-0.695
enegger-0.646
ible-0.634
esters-0.620
 IPM-0.618
Tokentwitter
Token ID6956
Feature activation-9.09e-02

Pos logit contributions
 proport+0.890
 suspic+0.868
 comr+0.748
 fortun+0.726
stress+0.701
Neg logit contributions
llah-0.817
enegger-0.768
ible-0.761
 IPM-0.742
esters-0.732
Token,
Token ID11
Feature activation-2.74e-01

Pos logit contributions
 proport+0.349
 suspic+0.341
 comr+0.300
 fortun+0.287
stress+0.266
Neg logit contributions
llah-0.259
ible-0.239
enegger-0.237
 IPM-0.229
esters-0.227
Token head
Token ID1182
Feature activation-1.23e+00

Pos logit contributions
llah+0.215
ible+0.200
enegger+0.199
 IPM+0.194
esters+0.191
Neg logit contributions
 proport-0.259
 suspic-0.252
 comr-0.221
 fortun-0.210
stress-0.195
Token of
Token ID286
Feature activation-6.44e-01

Pos logit contributions
llah+0.899
ible+0.827
enegger+0.812
 IPM+0.804
esters+0.787
Neg logit contributions
 proport-1.233
 suspic-1.209
 comr-1.064
 fortun-1.016
��-0.941
Token environmental
Token ID6142
Feature activation+6.16e-01

Pos logit contributions
llah+0.502
ible+0.467
enegger+0.463
 IPM+0.455
esters+0.447
Neg logit contributions
 proport-0.613
 suspic-0.596
 comr-0.523
 fortun-0.498
stress-0.463
Token group
Token ID1448
Feature activation+4.38e-01

Pos logit contributions
 proport+0.612
 suspic+0.599
 comr+0.526
 fortun+0.504
stress+0.471
Neg logit contributions
llah-0.453
ible-0.417
enegger-0.416
 IPM-0.402
esters-0.398
Token Greenpeace
Token ID42793
Feature activation+6.90e+00

Pos logit contributions
 proport+0.423
 suspic+0.412
 comr+0.361
 fortun+0.345
stress+0.321
Neg logit contributions
llah-0.336
ible-0.312
enegger-0.310
 IPM-0.303
esters-0.299
Token
Token ID447
Feature activation-3.41e-01

Pos logit contributions
 proport+6.264
 suspic+6.184
 comr+5.308
 fortun+5.085
stress+4.863
Neg logit contributions
llah-5.388
enegger-4.909
ible-4.874
osal-4.738
 IPM-4.728
Token
Token ID247
Feature activation-1.66e-01

Pos logit contributions
llah+0.293
ible+0.271
enegger+0.267
 IPM+0.262
esters+0.260
Neg logit contributions
 proport-0.298
 suspic-0.292
 comr-0.251
 fortun-0.241
stress-0.221
Tokens
Token ID82
Feature activation-6.98e-01

Pos logit contributions
llah+0.096
ible+0.087
enegger+0.086
 IPM+0.083
esters+0.082
Neg logit contributions
 proport-0.193
 suspic-0.189
 comr-0.169
 fortun-0.163
stress-0.153
Token International
Token ID4037
Feature activation+1.97e+00

Pos logit contributions
llah+0.520
ible+0.484
enegger+0.481
 IPM+0.469
esters+0.461
Neg logit contributions
 proport-0.687
 suspic-0.669
 comr-0.588
 fortun-0.562
stress-0.524
Token Nuclear
Token ID19229
Feature activation+1.93e+00

Pos logit contributions
 proport+1.987
 suspic+1.940
 comr+1.708
 fortun+1.639
stress+1.543
Neg logit contributions
llah-1.409
ible-1.286
enegger-1.282
 IPM-1.235
esters-1.229
Token licensed
Token ID11971
Feature activation+3.30e-01

Pos logit contributions
 proport+0.349
 suspic+0.343
 comr+0.301
 fortun+0.292
stress+0.274
Neg logit contributions
llah-0.234
ible-0.216
enegger-0.211
 IPM-0.210
esters-0.203
Token under
Token ID739
Feature activation+1.16e+00

Pos logit contributions
 proport+0.351
 suspic+0.345
 comr+0.305
 fortun+0.293
stress+0.275
Neg logit contributions
llah-0.223
ible-0.204
enegger-0.199
 IPM-0.196
esters-0.192
Token a
Token ID257
Feature activation+1.87e-01

Pos logit contributions
 proport+1.067
 suspic+1.035
 comr+0.902
 fortun+0.862
stress+0.799
Neg logit contributions
llah-0.938
ible-0.877
enegger-0.862
 IPM-0.852
esters-0.835
Token Creative
Token ID17404
Feature activation+2.03e+00

Pos logit contributions
 proport+0.198
 suspic+0.193
 comr+0.171
 fortun+0.164
stress+0.155
Neg logit contributions
llah-0.125
ible-0.115
enegger-0.112
 IPM-0.111
esters-0.108
Token Commons
Token ID13815
Feature activation+2.19e+00

Pos logit contributions
 proport+1.569
 suspic+1.523
 comr+1.282
 fortun+1.208
stress+1.099
Neg logit contributions
llah-1.954
ible-1.844
enegger-1.827
 IPM-1.795
esters-1.776
Token Attribution
Token ID45336
Feature activation+6.83e+00

Pos logit contributions
 proport+1.751
 suspic+1.700
 comr+1.441
 fortun+1.362
stress+1.245
Neg logit contributions
llah-2.048
ible-1.923
enegger-1.912
 IPM-1.870
esters-1.853
Token-
Token ID12
Feature activation+9.26e-01

Pos logit contributions
 proport+6.511
 suspic+6.362
 comr+5.587
 fortun+5.337
stress+5.012
Neg logit contributions
llah-5.210
enegger-4.770
ible-4.674
esters-4.582
 IPM-4.572
TokenNon
Token ID15419
Feature activation+6.08e-01

Pos logit contributions
 proport+0.827
 suspic+0.807
 comr+0.699
 fortun+0.664
stress+0.613
Neg logit contributions
llah-0.775
ible-0.730
enegger-0.714
 IPM-0.702
esters-0.694
TokenCommercial
Token ID48401
Feature activation-1.13e+00

Pos logit contributions
 proport+0.483
 suspic+0.471
 comr+0.397
 fortun+0.374
stress+0.338
Neg logit contributions
llah-0.560
ible-0.536
enegger-0.524
 IPM-0.521
esters-0.514
Token 3
Token ID513
Feature activation-4.67e-01

Pos logit contributions
llah+0.764
ible+0.708
enegger+0.695
 IPM+0.677
esters+0.660
Neg logit contributions
 proport-1.187
 suspic-1.164
 comr-1.027
 fortun-0.988
stress-0.926
Token.
Token ID13
Feature activation+9.22e-01

Pos logit contributions
llah+0.331
ible+0.304
enegger+0.302
 IPM+0.293
esters+0.289
Neg logit contributions
 proport-0.477
 suspic-0.466
 comr-0.411
 fortun-0.395
stress-0.370
TokenThree
Token ID12510
Feature activation-6.69e-01

Pos logit contributions
llah+0.164
ible+0.152
enegger+0.150
 IPM+0.146
esters+0.145
Neg logit contributions
 proport-0.203
 suspic-0.198
 comr-0.173
 fortun-0.166
stress-0.154
Token months
Token ID1933
Feature activation-2.14e+00

Pos logit contributions
llah+0.439
ible+0.402
enegger+0.397
 IPM+0.383
esters+0.380
Neg logit contributions
 proport-0.719
 suspic-0.704
 comr-0.625
 fortun-0.600
stress-0.565
Token ago
Token ID2084
Feature activation-1.09e+00

Pos logit contributions
llah+1.241
ible+1.115
enegger+1.105
esters+1.050
 IPM+1.047
Neg logit contributions
 proport-2.460
 suspic-2.408
 comr-2.172
 fortun-2.082
stress-1.958
Token students
Token ID2444
Feature activation-3.76e+00

Pos logit contributions
llah+0.778
ible+0.717
enegger+0.712
 IPM+0.690
esters+0.683
Neg logit contributions
 proport-1.104
 suspic-1.079
 comr-0.952
 fortun-0.915
stress-0.848
Token at
Token ID379
Feature activation-1.03e+00

Pos logit contributions
llah+2.515
ible+2.317
enegger+2.284
 IPM+2.213
esters+2.191
Neg logit contributions
 proport-3.932
 suspic-3.860
 comr-3.436
 fortun-3.284
stress-3.084
Token Ober
Token ID33753
Feature activation-8.47e+00

Pos logit contributions
llah+0.851
ible+0.796
enegger+0.786
 IPM+0.768
esters+0.761
Neg logit contributions
 proport-0.936
 suspic-0.915
 comr-0.794
 fortun-0.757
stress-0.697
Tokenlin
Token ID2815
Feature activation-3.95e+00

Pos logit contributions
llah+4.143
ible+3.866
esters+3.859
enegger+3.637
obic+3.627
Neg logit contributions
 proport-10.158
 suspic-9.968
 comr-9.014
 fortun-8.708
��-8.309
Token College
Token ID5535
Feature activation-2.26e+00

Pos logit contributions
llah+2.640
enegger+2.423
ible+2.421
 IPM+2.324
esters+2.306
Neg logit contributions
 proport-4.114
 suspic-4.047
 comr-3.586
 fortun-3.473
stress-3.219
Token in
Token ID287
Feature activation-4.32e-01

Pos logit contributions
llah+1.580
ible+1.455
enegger+1.447
 IPM+1.396
esters+1.391
Neg logit contributions
 proport-2.305
 suspic-2.255
 comr-1.999
 fortun-1.920
stress-1.787
Token Ohio
Token ID6835
Feature activation-9.16e-01

Pos logit contributions
llah+0.350
ible+0.328
enegger+0.323
 IPM+0.315
esters+0.313
Neg logit contributions
 proport-0.398
 suspic-0.388
 comr-0.337
 fortun-0.322
stress-0.298
Token objected
Token ID29811
Feature activation-1.17e+00

Pos logit contributions
llah+0.643
ible+0.589
enegger+0.585
 IPM+0.567
esters+0.561
Neg logit contributions
 proport-0.941
 suspic-0.921
 comr-0.815
 fortun-0.781
stress-0.731
Token a
Token ID257
Feature activation+2.15e-01

Pos logit contributions
 proport+0.160
 suspic+0.155
 comr+0.136
 fortun+0.130
stress+0.121
Neg logit contributions
llah-0.129
ible-0.120
enegger-0.118
 IPM-0.116
esters-0.114
Token pot
Token ID1787
Feature activation+5.80e-01

Pos logit contributions
 proport+0.211
 suspic+0.205
 comr+0.180
 fortun+0.172
stress+0.161
Neg logit contributions
llah-0.161
ible-0.150
enegger-0.147
 IPM-0.144
osal-0.142
Token-
Token ID12
Feature activation+4.48e-01

Pos logit contributions
 proport+0.545
 suspic+0.532
 comr+0.464
 fortun+0.441
stress+0.410
Neg logit contributions
llah-0.460
ible-0.430
enegger-0.423
 IPM-0.412
esters-0.409
Tokenadd
Token ID2860
Feature activation+8.59e-01

Pos logit contributions
 proport+0.374
 suspic+0.362
 comr+0.310
 fortun+0.292
stress+0.265
Neg logit contributions
llah-0.406
ible-0.382
enegger-0.377
 IPM-0.369
esters-0.367
Tokenled
Token ID992
Feature activation-5.49e-01

Pos logit contributions
 proport+0.762
 suspic+0.744
 comr+0.642
 fortun+0.607
stress+0.560
Neg logit contributions
llah-0.725
ible-0.681
enegger-0.673
 IPM-0.656
esters-0.652
Token Ober
Token ID33753
Feature activation-7.59e+00

Pos logit contributions
llah+0.411
ible+0.384
enegger+0.378
 IPM+0.370
esters+0.363
Neg logit contributions
 proport-0.539
 suspic-0.525
 comr-0.459
 fortun-0.438
stress-0.411
Tokenlin
Token ID2815
Feature activation-3.98e+00

Pos logit contributions
llah+4.599
ible+4.303
enegger+4.112
esters+4.105
obic+4.072
Neg logit contributions
 proport-8.281
 suspic-8.194
 comr-7.285
 fortun-6.908
��-6.538
Token College
Token ID5535
Feature activation-2.26e+00

Pos logit contributions
llah+2.758
ible+2.609
enegger+2.568
 IPM+2.480
osal+2.454
Neg logit contributions
 proport-4.031
 suspic-3.967
 comr-3.476
 fortun-3.313
stress-3.125
Token freshman
Token ID18621
Feature activation-7.59e-02

Pos logit contributions
llah+1.568
ible+1.467
enegger+1.440
 IPM+1.410
esters+1.386
Neg logit contributions
 proport-2.321
 suspic-2.275
 comr-2.002
 fortun-1.913
stress-1.801
Token's
Token ID338
Feature activation-6.60e-01

Pos logit contributions
llah+0.058
ible+0.054
enegger+0.053
 IPM+0.052
esters+0.052
Neg logit contributions
 proport-0.073
 suspic-0.071
 comr-0.062
 fortun-0.059
stress-0.055
Token
Token ID851
Feature activation-3.67e-01

Pos logit contributions
llah+0.492
ible+0.459
enegger+0.452
 IPM+0.442
esters+0.434
Neg logit contributions
 proport-0.649
 suspic-0.632
 comr-0.555
 fortun-0.529
stress-0.496
Tokenrate
Token ID4873
Feature activation+2.39e-01

Pos logit contributions
 proport+0.000
 suspic+0.000
 comr+0.000
 fortun+0.000
��+0.000
Neg logit contributions
llah-0.000
ible-0.000
enegger-0.000
esters-0.000
osal-0.000
Token GT
Token ID7963
Feature activation-7.41e+00

Pos logit contributions
 proport+0.224
 suspic+0.219
 comr+0.190
 fortun+0.182
stress+0.168
Neg logit contributions
llah-0.190
ible-0.178
enegger-0.175
 IPM-0.172
esters-0.170
Token/
Token ID14
Feature activation-1.38e+00

Pos logit contributions
llah+5.217
ible+4.999
enegger+4.830
 IPM+4.779
esters+4.758
Neg logit contributions
 proport-7.193
 suspic-7.036
 comr-6.279
 fortun-5.953
stress-5.426
Tokens
Token ID82
Feature activation-8.30e-01

Pos logit contributions
llah+0.902
ible+0.832
enegger+0.816
 IPM+0.797
esters+0.789
Neg logit contributions
 proport-1.477
 suspic-1.447
 comr-1.286
 fortun-1.235
stress-1.152
Token 72
Token ID7724
Feature activation+2.34e-01

Pos logit contributions
llah+0.570
ible+0.529
enegger+0.519
 IPM+0.510
esters+0.497
Neg logit contributions
 proport-0.862
 suspic-0.847
 comr-0.749
 fortun-0.718
stress-0.674
Token GT
Token ID7963
Feature activation-7.55e+00

Pos logit contributions
 proport+0.226
 suspic+0.221
 comr+0.193
 fortun+0.185
stress+0.172
Neg logit contributions
llah-0.179
ible-0.166
enegger-0.164
 IPM-0.160
esters-0.158
Token/
Token ID14
Feature activation-1.46e+00

Pos logit contributions
llah+4.872
ible+4.620
 IPM+4.477
enegger+4.383
esters+4.377
Neg logit contributions
 proport-7.679
 suspic-7.555
 comr-6.755
 fortun-6.476
stress-5.934
Tokens
Token ID82
Feature activation-1.18e+00

Pos logit contributions
llah+0.746
ible+0.672
enegger+0.646
 IPM+0.629
esters+0.627
Neg logit contributions
 proport-1.792
 suspic-1.758
 comr-1.595
 fortun-1.534
stress-1.430
Token 109
Token ID16003
Feature activation+3.60e-02

Pos logit contributions
llah+0.947
ible+0.886
enegger+0.874
 IPM+0.862
esters+0.844
Neg logit contributions
 proport-1.099
 suspic-1.075
 comr-0.934
 fortun-0.891
stress-0.823
Token.
Token ID13
Feature activation+3.77e-01

Pos logit contributions
 proport+0.048
 suspic+0.047
 comr+0.043
 fortun+0.041
stress+0.039
Neg logit contributions
llah-0.015
ible-0.013
enegger-0.012
 IPM-0.012
esters-0.011
Token2
Token ID17
Feature activation+3.31e-02

Pos logit contributions
 proport+0.375
 suspic+0.367
 comr+0.322
 fortun+0.310
stress+0.292
Neg logit contributions
llah-0.273
ible-0.251
enegger-0.250
 IPM-0.242
esters-0.241
Token/
Token ID14
Feature activation-1.46e+00

Pos logit contributions
llah+4.872
ible+4.620
 IPM+4.477
enegger+4.383
esters+4.377
Neg logit contributions
 proport-7.679
 suspic-7.555
 comr-6.755
 fortun-6.476
stress-5.934
Tokens
Token ID82
Feature activation-1.18e+00

Pos logit contributions
llah+0.746
ible+0.672
enegger+0.646
 IPM+0.629
esters+0.627
Neg logit contributions
 proport-1.792
 suspic-1.758
 comr-1.595
 fortun-1.534
stress-1.430
Token 109
Token ID16003
Feature activation+3.60e-02

Pos logit contributions
llah+0.947
ible+0.886
enegger+0.874
 IPM+0.862
esters+0.844
Neg logit contributions
 proport-1.099
 suspic-1.075
 comr-0.934
 fortun-0.891
stress-0.823
Token.
Token ID13
Feature activation+3.77e-01

Pos logit contributions
 proport+0.048
 suspic+0.047
 comr+0.043
 fortun+0.041
stress+0.039
Neg logit contributions
llah-0.015
ible-0.013
enegger-0.012
 IPM-0.012
esters-0.011
Token2
Token ID17
Feature activation+3.31e-02

Pos logit contributions
 proport+0.375
 suspic+0.367
 comr+0.322
 fortun+0.310
stress+0.292
Neg logit contributions
llah-0.273
ible-0.251
enegger-0.250
 IPM-0.242
esters-0.241
Token GT
Token ID7963
Feature activation-7.48e+00

Pos logit contributions
 proport+0.045
 suspic+0.044
 comr+0.040
 fortun+0.039
stress+0.037
Neg logit contributions
llah-0.013
ible-0.011
enegger-0.011
 IPM-0.010
esters-0.010
Token/
Token ID14
Feature activation-1.65e+00

Pos logit contributions
llah+5.292
ible+4.981
 IPM+4.801
enegger+4.789
osal+4.671
Neg logit contributions
 proport-7.762
 suspic-7.614
 comr-6.714
 fortun-6.331
��-5.725
Tokens
Token ID82
Feature activation-1.48e+00

Pos logit contributions
llah+0.942
enegger+0.847
ible+0.838
 IPM+0.808
esters+0.788
Neg logit contributions
 proport-1.896
 suspic-1.861
 comr-1.665
 fortun-1.615
stress-1.554
Token 120
Token ID7982
Feature activation-9.09e-01

Pos logit contributions
llah+1.248
ible+1.172
enegger+1.158
 IPM+1.143
esters+1.117
Neg logit contributions
 proport-1.322
 suspic-1.289
 comr-1.112
 fortun-1.054
stress-0.969
Token.
Token ID13
Feature activation+2.69e-01

Pos logit contributions
llah+0.560
ible+0.512
enegger+0.504
 IPM+0.491
esters+0.480
Neg logit contributions
 proport-1.010
 suspic-0.994
 comr-0.884
 fortun-0.853
stress-0.802
Token5
Token ID20
Feature activation-3.36e-01

Pos logit contributions
 proport+0.278
 suspic+0.272
 comr+0.240
 fortun+0.231
stress+0.218
Neg logit contributions
llah-0.186
ible-0.170
enegger-0.169
 IPM-0.163
esters-0.162
Token a
Token ID257
Feature activation+1.72e-01

Pos logit contributions
llah+0.425
ible+0.396
enegger+0.393
 IPM+0.381
esters+0.378
Neg logit contributions
 proport-0.546
 suspic-0.531
 comr-0.465
 fortun-0.443
stress-0.414
Token model
Token ID2746
Feature activation-1.24e+00

Pos logit contributions
 proport+0.169
 suspic+0.164
 comr+0.144
 fortun+0.137
stress+0.129
Neg logit contributions
llah-0.127
ible-0.119
enegger-0.117
 IPM-0.114
osal-0.112
Token of
Token ID286
Feature activation-9.41e-02

Pos logit contributions
llah+0.882
ible+0.824
enegger+0.813
 IPM+0.789
esters+0.778
Neg logit contributions
 proport-1.247
 suspic-1.220
 comr-1.066
 fortun-1.019
stress-0.956
Token Pont
Token ID26345
Feature activation-1.95e+00

Pos logit contributions
llah+0.071
ible+0.066
enegger+0.066
 IPM+0.064
esters+0.063
Neg logit contributions
 proport-0.091
 suspic-0.089
 comr-0.078
 fortun-0.074
stress-0.070
Tokeniac
Token ID9607
Feature activation-9.47e-01

Pos logit contributions
llah+1.702
ible+1.614
enegger+1.596
 IPM+1.554
esters+1.549
Neg logit contributions
 proport-1.665
 suspic-1.612
 comr-1.379
 fortun-1.300
��-1.203
Token GT
Token ID7963
Feature activation-7.44e+00

Pos logit contributions
llah+0.702
ible+0.657
enegger+0.647
 IPM+0.631
esters+0.623
Neg logit contributions
 proport-0.932
 suspic-0.912
 comr-0.796
 fortun-0.762
stress-0.713
TokenO
Token ID46
Feature activation-5.21e-01

Pos logit contributions
llah+5.015
ible+4.800
enegger+4.651
esters+4.623
 IPM+4.491
Neg logit contributions
 proport-7.460
 suspic-7.324
 comr-6.414
 fortun-6.108
stress-5.700
Token sold
Token ID2702
Feature activation+5.60e-01

Pos logit contributions
llah+0.383
ible+0.355
enegger+0.352
 IPM+0.343
esters+0.339
Neg logit contributions
 proport-0.517
 suspic-0.505
 comr-0.443
 fortun-0.424
stress-0.397
Token from
Token ID422
Feature activation+3.90e-01

Pos logit contributions
 proport+0.566
 suspic+0.554
 comr+0.489
 fortun+0.466
stress+0.435
Neg logit contributions
llah-0.404
ible-0.376
enegger-0.372
 IPM-0.358
esters-0.357
Token 1969
Token ID16450
Feature activation-3.39e+00

Pos logit contributions
 proport+0.383
 suspic+0.373
 comr+0.327
 fortun+0.313
stress+0.292
Neg logit contributions
llah-0.293
ible-0.271
enegger-0.269
 IPM-0.262
esters-0.259
Token till
Token ID10597
Feature activation-5.88e-01

Pos logit contributions
llah+2.166
ible+2.033
enegger+1.993
 IPM+1.919
esters+1.909
Neg logit contributions
 proport-3.665
 suspic-3.579
 comr-3.195
 fortun-3.041
stress-2.847
Token 160
Token ID13454
Feature activation-9.41e-01

Pos logit contributions
llah+0.172
ible+0.159
enegger+0.158
 IPM+0.153
esters+0.151
Neg logit contributions
 proport-0.237
 suspic-0.232
 comr-0.204
 fortun-0.196
stress-0.183
Token Texture
Token ID44409
Feature activation-3.20e+00

Pos logit contributions
llah+0.697
ible+0.647
enegger+0.637
 IPM+0.624
esters+0.611
Neg logit contributions
 proport-0.933
 suspic-0.913
 comr-0.802
 fortun-0.766
stress-0.715
Token fill
Token ID6070
Feature activation-1.25e+00

Pos logit contributions
llah+1.959
ible+1.850
cible+1.723
 IPM+1.718
RESULTS+1.706
Neg logit contributions
 proport-3.502
 suspic-3.450
 comr-3.068
 fortun-2.923
��-2.733
Token-
Token ID12
Feature activation+3.79e-04

Pos logit contributions
llah+0.953
ible+0.905
enegger+0.872
esters+0.865
 IPM+0.863
Neg logit contributions
 proport-1.193
 suspic-1.171
 comr-1.029
 fortun-0.976
��-0.891
Tokenrate
Token ID4873
Feature activation+2.39e-01

Pos logit contributions
 proport+0.000
 suspic+0.000
 comr+0.000
 fortun+0.000
��+0.000
Neg logit contributions
llah-0.000
ible-0.000
enegger-0.000
esters-0.000
osal-0.000
Token GT
Token ID7963
Feature activation-7.41e+00

Pos logit contributions
 proport+0.224
 suspic+0.219
 comr+0.190
 fortun+0.182
stress+0.168
Neg logit contributions
llah-0.190
ible-0.178
enegger-0.175
 IPM-0.172
esters-0.170
Token/
Token ID14
Feature activation-1.38e+00

Pos logit contributions
llah+5.217
ible+4.999
enegger+4.830
 IPM+4.779
esters+4.758
Neg logit contributions
 proport-7.193
 suspic-7.036
 comr-6.279
 fortun-5.953
stress-5.426
Tokens
Token ID82
Feature activation-8.30e-01

Pos logit contributions
llah+0.902
ible+0.832
enegger+0.816
 IPM+0.797
esters+0.789
Neg logit contributions
 proport-1.477
 suspic-1.447
 comr-1.286
 fortun-1.235
stress-1.152
Token 72
Token ID7724
Feature activation+2.34e-01

Pos logit contributions
llah+0.570
ible+0.529
enegger+0.519
 IPM+0.510
esters+0.497
Neg logit contributions
 proport-0.862
 suspic-0.847
 comr-0.749
 fortun-0.718
stress-0.674
Token GT
Token ID7963
Feature activation-7.55e+00

Pos logit contributions
 proport+0.226
 suspic+0.221
 comr+0.193
 fortun+0.185
stress+0.172
Neg logit contributions
llah-0.179
ible-0.166
enegger-0.164
 IPM-0.160
esters-0.158
Token/
Token ID14
Feature activation-1.46e+00

Pos logit contributions
llah+4.872
ible+4.620
 IPM+4.477
enegger+4.383
esters+4.377
Neg logit contributions
 proport-7.679
 suspic-7.555
 comr-6.755
 fortun-6.476
stress-5.934
Token/
Token ID14
Feature activation-1.65e+00

Pos logit contributions
llah+5.292
ible+4.981
 IPM+4.801
enegger+4.789
osal+4.671
Neg logit contributions
 proport-7.762
 suspic-7.614
 comr-6.714
 fortun-6.331
��-5.725
Tokens
Token ID82
Feature activation-1.48e+00

Pos logit contributions
llah+0.942
enegger+0.847
ible+0.838
 IPM+0.808
esters+0.788
Neg logit contributions
 proport-1.896
 suspic-1.861
 comr-1.665
 fortun-1.615
stress-1.554
Token 120
Token ID7982
Feature activation-9.09e-01

Pos logit contributions
llah+1.248
ible+1.172
enegger+1.158
 IPM+1.143
esters+1.117
Neg logit contributions
 proport-1.322
 suspic-1.289
 comr-1.112
 fortun-1.054
stress-0.969
Token.
Token ID13
Feature activation+2.69e-01

Pos logit contributions
llah+0.560
ible+0.512
enegger+0.504
 IPM+0.491
esters+0.480
Neg logit contributions
 proport-1.010
 suspic-0.994
 comr-0.884
 fortun-0.853
stress-0.802
Token5
Token ID20
Feature activation-3.36e-01

Pos logit contributions
 proport+0.278
 suspic+0.272
 comr+0.240
 fortun+0.231
stress+0.218
Neg logit contributions
llah-0.186
ible-0.170
enegger-0.169
 IPM-0.163
esters-0.162
Token GT
Token ID7963
Feature activation-7.29e+00

Pos logit contributions
llah+0.120
ible+0.102
enegger+0.100
 IPM+0.095
esters+0.091
Neg logit contributions
 proport-0.460
 suspic-0.453
 comr-0.414
 fortun-0.402
stress-0.383
Token/
Token ID14
Feature activation-1.69e+00

Pos logit contributions
llah+5.132
ible+4.858
 IPM+4.663
enegger+4.645
osal+4.530
Neg logit contributions
 proport-7.688
 suspic-7.532
 comr-6.630
 fortun-6.224
��-5.658
Tokens
Token ID82
Feature activation-1.47e+00

Pos logit contributions
llah+0.971
enegger+0.878
ible+0.862
 IPM+0.837
esters+0.812
Neg logit contributions
 proport-1.903
 suspic-1.866
 comr-1.669
 fortun-1.624
stress-1.574
Token 180
Token ID11546
Feature activation+1.05e+00

Pos logit contributions
llah+1.221
ible+1.146
enegger+1.134
 IPM+1.116
esters+1.093
Neg logit contributions
 proport-1.323
 suspic-1.292
 comr-1.118
 fortun-1.060
stress-0.976
Token.
Token ID13
Feature activation+3.42e-01

Pos logit contributions
 proport+1.133
 suspic+1.108
 comr+0.984
 fortun+0.946
stress+0.890
Neg logit contributions
llah-0.688
ible-0.628
enegger-0.624
 IPM-0.602
esters-0.595
Token7
Token ID22
Feature activation-6.68e-01

Pos logit contributions
 proport+0.348
 suspic+0.340
 comr+0.300
 fortun+0.288
stress+0.271
Neg logit contributions
llah-0.242
ible-0.222
enegger-0.221
 IPM-0.214
esters-0.212
Token family
Token ID1641
Feature activation-1.73e+00

Pos logit contributions
 proport+0.206
 suspic+0.201
 comr+0.175
 fortun+0.168
stress+0.157
Neg logit contributions
llah-0.166
ible-0.154
enegger-0.153
 IPM-0.148
esters-0.147
Token,
Token ID11
Feature activation-1.26e-02

Pos logit contributions
llah+1.202
ible+1.101
enegger+1.087
esters+1.041
+1.040
Neg logit contributions
 proport-1.799
 suspic-1.756
 comr-1.539
 fortun-1.486
stress-1.399
Token fighting
Token ID4330
Feature activation+7.77e-01

Pos logit contributions
llah+0.009
ible+0.009
enegger+0.009
 IPM+0.008
esters+0.008
Neg logit contributions
 proport-0.012
 suspic-0.012
 comr-0.011
 fortun-0.010
stress-0.010
Token,
Token ID11
Feature activation+8.75e-02

Pos logit contributions
 proport+0.744
 suspic+0.725
 comr+0.634
 fortun+0.606
stress+0.564
Neg logit contributions
llah-0.601
ible-0.557
enegger-0.554
 IPM-0.538
esters-0.532
Token and
Token ID290
Feature activation-1.27e-01

Pos logit contributions
 proport+0.086
 suspic+0.084
 comr+0.073
 fortun+0.070
stress+0.066
Neg logit contributions
llah-0.066
ible-0.061
enegger-0.060
 IPM-0.058
esters-0.058
Token FO
Token ID11895
Feature activation-7.16e+00

Pos logit contributions
llah+0.095
ible+0.088
enegger+0.087
 IPM+0.085
esters+0.084
Neg logit contributions
 proport-0.124
 suspic-0.121
 comr-0.105
 fortun-0.101
stress-0.095
TokenOD
Token ID3727
Feature activation-2.16e+00

Pos logit contributions
llah+4.886
ible+4.501
enegger+4.338
 IPM+4.240
osal+4.236
Neg logit contributions
 proport-7.310
 suspic-7.138
 comr-6.362
 fortun-6.011
stress-5.736
Token!
Token ID0
Feature activation-1.97e+00

Pos logit contributions
llah+1.495
ible+1.378
enegger+1.364
 IPM+1.315
esters+1.303
Neg logit contributions
 proport-2.238
 suspic-2.184
 comr-1.924
 fortun-1.846
stress-1.732
Token Oh
Token ID3966
Feature activation-2.12e+00

Pos logit contributions
llah+1.562
ible+1.445
enegger+1.433
 IPM+1.397
+1.377
Neg logit contributions
 proport-1.858
 suspic-1.812
 comr-1.574
 fortun-1.497
stress-1.390
Token crap
Token ID18824
Feature activation-1.12e+00

Pos logit contributions
llah+1.434
ible+1.325
enegger+1.305
 IPM+1.247
esters+1.243
Neg logit contributions
 proport-2.243
 suspic-2.170
 comr-1.925
 fortun-1.834
stress-1.731
Token
Token ID1399
Feature activation+5.39e-01

Pos logit contributions
llah+0.803
ible+0.739
enegger+0.732
 IPM+0.703
esters+0.700
Neg logit contributions
 proport-1.148
 suspic-1.118
 comr-0.986
 fortun-0.943
stress-0.880
Tokenk
Token ID74
Feature activation+4.52e-01

Pos logit contributions
llah+0.104
ible+0.095
enegger+0.095
 IPM+0.090
esters+0.090
Neg logit contributions
 proport-0.162
 suspic-0.158
 comr-0.140
 fortun-0.134
stress-0.125
Tokenong
Token ID506
Feature activation+1.36e+00

Pos logit contributions
 proport+0.453
 suspic+0.447
 comr+0.396
 fortun+0.388
stress+0.381
Neg logit contributions
llah-0.297
enegger-0.278
 IPM-0.269
ible-0.266
esters-0.259
Token/
Token ID14
Feature activation-1.60e+00

Pos logit contributions
 proport+1.305
 suspic+1.272
 comr+1.113
 fortun+1.063
stress+0.987
Neg logit contributions
llah-1.048
ible-0.973
enegger-0.965
 IPM-0.939
esters-0.929
Tokena
Token ID64
Feature activation+1.19e+00

Pos logit contributions
llah+1.455
ible+1.377
enegger+1.356
 IPM+1.329
osal+1.320
Neg logit contributions
 proport-1.315
 suspic-1.271
 comr-1.090
 fortun-1.025
��-0.922
Token-
Token ID12
Feature activation-2.58e-01

Pos logit contributions
 proport+1.180
 suspic+1.152
 comr+1.012
 fortun+0.969
stress+0.904
Neg logit contributions
llah-0.878
ible-0.811
enegger-0.803
 IPM-0.781
esters-0.773
Tokenflex
Token ID32880
Feature activation-7.08e+00

Pos logit contributions
llah+0.226
ible+0.213
enegger+0.209
 IPM+0.205
esters+0.203
Neg logit contributions
 proport-0.221
 suspic-0.215
 comr-0.184
 fortun-0.175
stress-0.158
Tokenible
Token ID856
Feature activation-2.14e+00

Pos logit contributions
ible+4.906
llah+4.853
osal+4.493
enegger+4.493
obic+4.367
Neg logit contributions
 proport-6.990
 suspic-6.918
 comr-6.120
 fortun-5.783
��-5.472
Token-
Token ID12
Feature activation-2.96e-01

Pos logit contributions
llah+1.430
ible+1.346
enegger+1.291
 IPM+1.263
osal+1.255
Neg logit contributions
 proport-2.272
 suspic-2.231
 comr-1.969
 fortun-1.893
��-1.764
Tokenlimit
Token ID32374
Feature activation+7.24e-02

Pos logit contributions
llah+0.241
ible+0.226
enegger+0.222
 IPM+0.217
esters+0.216
Neg logit contributions
 proport-0.272
 suspic-0.265
 comr-0.230
 fortun-0.219
stress-0.200
Token-
Token ID12
Feature activation-3.41e-01

Pos logit contributions
 proport+0.075
 suspic+0.073
 comr+0.065
 fortun+0.062
stress+0.058
Neg logit contributions
llah-0.050
ible-0.047
enegger-0.046
 IPM-0.045
osal-0.044
Tokentr
Token ID2213
Feature activation+5.47e-01

Pos logit contributions
llah+0.309
ible+0.293
enegger+0.288
 IPM+0.282
osal+0.281
Neg logit contributions
 proport-0.283
 suspic-0.275
 comr-0.235
 fortun-0.221
��-0.199
Token/
Token ID14
Feature activation-1.69e+00

Pos logit contributions
llah+5.132
ible+4.858
 IPM+4.663
enegger+4.645
osal+4.530
Neg logit contributions
 proport-7.688
 suspic-7.532
 comr-6.630
 fortun-6.224
��-5.658
Tokens
Token ID82
Feature activation-1.47e+00

Pos logit contributions
llah+0.971
enegger+0.878
ible+0.862
 IPM+0.837
esters+0.812
Neg logit contributions
 proport-1.903
 suspic-1.866
 comr-1.669
 fortun-1.624
stress-1.574
Token 180
Token ID11546
Feature activation+1.05e+00

Pos logit contributions
llah+1.221
ible+1.146
enegger+1.134
 IPM+1.116
esters+1.093
Neg logit contributions
 proport-1.323
 suspic-1.292
 comr-1.118
 fortun-1.060
stress-0.976
Token.
Token ID13
Feature activation+3.42e-01

Pos logit contributions
 proport+1.133
 suspic+1.108
 comr+0.984
 fortun+0.946
stress+0.890
Neg logit contributions
llah-0.688
ible-0.628
enegger-0.624
 IPM-0.602
esters-0.595
Token7
Token ID22
Feature activation-6.68e-01

Pos logit contributions
 proport+0.348
 suspic+0.340
 comr+0.300
 fortun+0.288
stress+0.271
Neg logit contributions
llah-0.242
ible-0.222
enegger-0.221
 IPM-0.214
esters-0.212
Token GT
Token ID7963
Feature activation-7.06e+00

Pos logit contributions
llah+0.231
ible+0.197
enegger+0.192
 IPM+0.183
esters+0.173
Neg logit contributions
 proport-0.920
 suspic-0.909
 comr-0.829
 fortun-0.805
stress-0.769
Token/
Token ID14
Feature activation-1.70e+00

Pos logit contributions
llah+4.999
ible+4.727
 IPM+4.535
enegger+4.523
osal+4.410
Neg logit contributions
 proport-7.447
 suspic-7.293
 comr-6.412
 fortun-6.011
��-5.471
Tokens
Token ID82
Feature activation-1.24e+00

Pos logit contributions
llah+0.980
enegger+0.887
ible+0.871
 IPM+0.845
osal+0.820
Neg logit contributions
 proport-1.914
 suspic-1.877
 comr-1.680
 fortun-1.635
stress-1.586
Token 257
Token ID36100
Feature activation+3.69e-01

Pos logit contributions
llah+1.003
ible+0.940
enegger+0.930
 IPM+0.913
esters+0.893
Neg logit contributions
 proport-1.149
 suspic-1.124
 comr-0.977
 fortun-0.929
stress-0.860
Token.
Token ID13
Feature activation+1.95e-01

Pos logit contributions
 proport+0.395
 suspic+0.387
 comr+0.343
 fortun+0.330
stress+0.310
Neg logit contributions
llah-0.245
ible-0.225
enegger-0.222
 IPM-0.215
esters-0.212
Token1
Token ID16
Feature activation-6.01e-02

Pos logit contributions
 proport+0.203
 suspic+0.198
 comr+0.175
 fortun+0.168
stress+0.158
Neg logit contributions
llah-0.134
ible-0.123
enegger-0.122
 IPM-0.119
esters-0.117
Token scale
Token ID5046
Feature activation-4.44e-01

Pos logit contributions
llah+0.237
ible+0.220
enegger+0.216
 IPM+0.211
osal+0.208
Neg logit contributions
 proport-0.305
 suspic-0.298
 comr-0.260
 fortun-0.249
stress-0.233
Token and
Token ID290
Feature activation+5.16e-01

Pos logit contributions
llah+0.320
ible+0.299
enegger+0.288
 IPM+0.284
esters+0.280
Neg logit contributions
 proport-0.446
 suspic-0.439
 comr-0.384
 fortun-0.370
stress-0.345
Token violence
Token ID3685
Feature activation+5.51e-01

Pos logit contributions
 proport+0.497
 suspic+0.487
 comr+0.424
 fortun+0.405
stress+0.379
Neg logit contributions
llah-0.395
ible-0.367
enegger-0.360
 IPM-0.353
esters-0.348
Token of
Token ID286
Feature activation-2.16e-01

Pos logit contributions
 proport+0.547
 suspic+0.536
 comr+0.470
 fortun+0.450
stress+0.420
Neg logit contributions
llah-0.407
ible-0.376
enegger-0.372
 IPM-0.362
esters-0.358
Token the
Token ID262
Feature activation-1.64e-01

Pos logit contributions
llah+0.171
ible+0.159
enegger+0.157
 IPM+0.154
esters+0.152
Neg logit contributions
 proport-0.203
 suspic-0.198
 comr-0.173
 fortun-0.165
stress-0.153
Token forc
Token ID24686
Feature activation-6.96e+00

Pos logit contributions
llah+0.128
ible+0.119
enegger+0.118
 IPM+0.115
esters+0.114
Neg logit contributions
 proport-0.155
 suspic-0.151
 comr-0.132
 fortun-0.126
stress-0.118
Tokenible
Token ID856
Feature activation-2.19e+00

Pos logit contributions
ible+0.009
llah-0.140
enegger-0.538
cible-0.555
osal-0.629
Neg logit contributions
 proport-12.135
 suspic-11.995
 comr-11.275
 fortun-10.904
��-10.518
Token recruitment
Token ID19624
Feature activation+7.26e-02

Pos logit contributions
llah+1.564
ible+1.451
enegger+1.413
 IPM+1.387
esters+1.370
Neg logit contributions
 proport-2.215
 suspic-2.164
 comr-1.904
 fortun-1.832
stress-1.719
Token by
Token ID416
Feature activation+6.33e-01

Pos logit contributions
 proport+0.071
 suspic+0.070
 comr+0.061
 fortun+0.058
stress+0.054
Neg logit contributions
llah-0.054
ible-0.050
enegger-0.050
 IPM-0.049
esters-0.048
Token al
Token ID435
Feature activation+6.41e-01

Pos logit contributions
 proport+0.649
 suspic+0.634
 comr+0.559
 fortun+0.537
stress+0.502
Neg logit contributions
llah-0.448
ible-0.411
enegger-0.410
 IPM-0.396
esters-0.392
Token-
Token ID12
Feature activation+8.68e-02

Pos logit contributions
 proport+0.614
 suspic+0.598
 comr+0.526
 fortun+0.509
stress+0.480
Neg logit contributions
llah-0.481
enegger-0.446
ible-0.440
 IPM-0.427
esters-0.426
Token David
Token ID3271
Feature activation+4.48e-01

Pos logit contributions
 proport+1.045
 suspic+1.020
 comr+0.897
 fortun+0.860
stress+0.804
Neg logit contributions
llah-0.762
ible-0.702
enegger-0.699
 IPM-0.677
esters-0.669
Token De
Token ID1024
Feature activation+2.09e+00

Pos logit contributions
 proport+0.393
 suspic+0.384
 comr+0.329
 fortun+0.313
stress+0.287
Neg logit contributions
llah-0.386
ible-0.361
enegger-0.357
 IPM-0.349
esters-0.346
TokenCast
Token ID19248
Feature activation-1.22e+00

Pos logit contributions
 proport+2.220
 suspic+2.171
 comr+1.927
 fortun+1.856
stress+1.747
Neg logit contributions
llah-1.388
ible-1.266
enegger-1.262
 IPM-1.222
esters-1.201
Tokenro
Token ID305
Feature activation-1.32e+00

Pos logit contributions
llah+0.936
ible+0.870
enegger+0.847
 IPM+0.826
osal+0.825
Neg logit contributions
 proport-1.177
 suspic-1.158
 comr-1.013
 fortun-0.966
��-0.893
Token and
Token ID290
Feature activation-1.47e-01

Pos logit contributions
llah+0.901
ible+0.825
enegger+0.818
 IPM+0.788
esters+0.787
Neg logit contributions
 proport-1.391
 suspic-1.362
 comr-1.207
 fortun-1.157
stress-1.081
Token Maur
Token ID18867
Feature activation-6.96e+00

Pos logit contributions
llah+0.108
ible+0.100
enegger+0.099
 IPM+0.096
esters+0.095
Neg logit contributions
 proport-0.146
 suspic-0.142
 comr-0.125
 fortun-0.119
stress-0.112
Tokenk
Token ID74
Feature activation+6.77e-01

Pos logit contributions
llah+4.512
ible+4.079
esters+3.912
enegger+3.904
obic+3.880
Neg logit contributions
 proport-7.408
 suspic-7.404
 comr-6.549
 fortun-6.304
��-5.910
Tokenice
Token ID501
Feature activation-1.43e-01

Pos logit contributions
 proport+0.570
 suspic+0.556
 comr+0.473
 fortun+0.452
stress+0.408
Neg logit contributions
llah-0.607
ible-0.571
enegger-0.566
 IPM-0.548
osal-0.547
Token P
Token ID350
Feature activation+2.44e-01

Pos logit contributions
llah+0.108
ible+0.100
enegger+0.099
 IPM+0.097
esters+0.096
Neg logit contributions
 proport-0.140
 suspic-0.136
 comr-0.119
 fortun-0.114
stress-0.106
Tokenounce
Token ID8652
Feature activation-2.78e+00

Pos logit contributions
 proport+0.214
 suspic+0.209
 comr+0.180
 fortun+0.171
stress+0.157
Neg logit contributions
llah-0.208
ible-0.194
enegger-0.193
 IPM-0.188
esters-0.187
Tokeny
Token ID88
Feature activation+1.14e+00

Pos logit contributions
llah+1.935
ible+1.780
enegger+1.775
 IPM+1.717
esters+1.696
Neg logit contributions
 proport-2.866
 suspic-2.800
 comr-2.477
 fortun-2.377
stress-2.229
Token/
Token ID14
Feature activation-1.70e+00

Pos logit contributions
llah+4.999
ible+4.727
 IPM+4.535
enegger+4.523
osal+4.410
Neg logit contributions
 proport-7.447
 suspic-7.293
 comr-6.412
 fortun-6.011
��-5.471
Tokens
Token ID82
Feature activation-1.24e+00

Pos logit contributions
llah+0.980
enegger+0.887
ible+0.871
 IPM+0.845
osal+0.820
Neg logit contributions
 proport-1.914
 suspic-1.877
 comr-1.680
 fortun-1.635
stress-1.586
Token 257
Token ID36100
Feature activation+3.69e-01

Pos logit contributions
llah+1.003
ible+0.940
enegger+0.930
 IPM+0.913
esters+0.893
Neg logit contributions
 proport-1.149
 suspic-1.124
 comr-0.977
 fortun-0.929
stress-0.860
Token.
Token ID13
Feature activation+1.95e-01

Pos logit contributions
 proport+0.395
 suspic+0.387
 comr+0.343
 fortun+0.330
stress+0.310
Neg logit contributions
llah-0.245
ible-0.225
enegger-0.222
 IPM-0.215
esters-0.212
Token1
Token ID16
Feature activation-6.01e-02

Pos logit contributions
 proport+0.203
 suspic+0.198
 comr+0.175
 fortun+0.168
stress+0.158
Neg logit contributions
llah-0.134
ible-0.123
enegger-0.122
 IPM-0.119
esters-0.117
Token GT
Token ID7963
Feature activation-6.94e+00

Pos logit contributions
llah+0.023
ible+0.020
enegger+0.019
 IPM+0.019
esters+0.018
Neg logit contributions
 proport-0.081
 suspic-0.080
 comr-0.073
 fortun-0.070
stress-0.067
Token/
Token ID14
Feature activation-1.57e+00

Pos logit contributions
llah+4.968
ible+4.695
enegger+4.513
 IPM+4.511
osal+4.381
Neg logit contributions
 proport-7.239
 suspic-7.084
 comr-6.225
 fortun-5.844
��-5.319
Tokens
Token ID82
Feature activation-1.39e+00

Pos logit contributions
llah+0.908
enegger+0.822
ible+0.805
 IPM+0.784
osal+0.761
Neg logit contributions
 proport-1.754
 suspic-1.721
 comr-1.539
 fortun-1.500
stress-1.459
Token Memory
Token ID14059
Feature activation+1.64e+00

Pos logit contributions
llah+1.125
ible+1.060
enegger+1.045
 IPM+1.032
osal+1.003
Neg logit contributions
 proport-1.279
 suspic-1.253
 comr-1.089
 fortun-1.031
stress-0.953
Token Clock
Token ID21328
Feature activation+1.98e+00

Pos logit contributions
 proport+1.532
 suspic+1.482
 comr+1.293
 fortun+1.239
stress+1.157
Neg logit contributions
llah-1.314
enegger-1.216
ible-1.192
osal-1.154
esters-1.153
Token 7000
Token ID50205
Feature activation-1.40e+00

Pos logit contributions
 proport+1.859
 suspic+1.806
 comr+1.580
 fortun+1.510
stress+1.423
Neg logit contributions
llah-1.561
enegger-1.438
ible-1.432
 IPM-1.382
esters-1.376
Token,
Token ID11
Feature activation-1.12e-01

Pos logit contributions
llah+0.526
ible+0.485
enegger+0.480
 IPM+0.468
esters+0.461
Neg logit contributions
 proport-0.763
 suspic-0.746
 comr-0.658
 fortun-0.631
stress-0.591
Token a
Token ID257
Feature activation-4.70e-01

Pos logit contributions
llah+0.081
ible+0.075
enegger+0.075
 IPM+0.072
esters+0.072
Neg logit contributions
 proport-0.112
 suspic-0.110
 comr-0.097
 fortun-0.093
stress-0.087
Token major
Token ID1688
Feature activation-1.27e+00

Pos logit contributions
llah+0.363
ible+0.339
enegger+0.335
 IPM+0.324
esters+0.323
Neg logit contributions
 proport-0.449
 suspic-0.438
 comr-0.382
 fortun-0.364
stress-0.341
Token maker
Token ID16009
Feature activation+1.23e+00

Pos logit contributions
llah+0.930
ible+0.872
enegger+0.859
 IPM+0.835
esters+0.826
Neg logit contributions
 proport-1.264
 suspic-1.237
 comr-1.085
 fortun-1.034
stress-0.974
Token of
Token ID286
Feature activation-1.67e-01

Pos logit contributions
 proport+1.210
 suspic+1.185
 comr+1.037
 fortun+0.993
stress+0.929
Neg logit contributions
llah-0.919
ible-0.856
enegger-0.843
 IPM-0.819
esters-0.814
Token Honey
Token ID21788
Feature activation-6.89e+00

Pos logit contributions
llah+0.114
ible+0.105
enegger+0.103
 IPM+0.101
esters+0.099
Neg logit contributions
 proport-0.176
 suspic-0.172
 comr-0.152
 fortun-0.146
stress-0.137
Tokencomb
Token ID24011
Feature activation-3.23e-02

Pos logit contributions
llah+4.269
ible+4.009
enegger+3.877
cible+3.759
esters+3.739
Neg logit contributions
 proport-7.539
 suspic-7.377
 comr-6.557
 fortun-6.322
��-5.805
Token tablets
Token ID17255
Feature activation+1.83e+00

Pos logit contributions
llah+0.024
ible+0.022
enegger+0.022
 IPM+0.022
esters+0.021
Neg logit contributions
 proport-0.032
 suspic-0.031
 comr-0.027
 fortun-0.026
stress-0.024
Token,
Token ID11
Feature activation-2.32e-01

Pos logit contributions
 proport+1.792
 suspic+1.744
 comr+1.528
 fortun+1.464
stress+1.369
Neg logit contributions
llah-1.378
ible-1.266
enegger-1.261
 IPM-1.228
esters-1.210
Token argue
Token ID7267
Feature activation-1.54e+00

Pos logit contributions
llah+0.163
ible+0.150
enegger+0.149
 IPM+0.144
esters+0.142
Neg logit contributions
 proport-0.238
 suspic-0.233
 comr-0.205
 fortun-0.197
stress-0.185
Token they
Token ID484
Feature activation-1.05e+00

Pos logit contributions
llah+1.103
ible+1.029
enegger+1.006
 IPM+0.987
esters+0.972
Neg logit contributions
 proport-1.561
 suspic-1.527
 comr-1.350
 fortun-1.288
stress-1.208
Token
Token ID250
Feature activation-3.46e-02

Pos logit contributions
 proport+0.192
 suspic+0.187
 comr+0.164
 fortun+0.156
stress+0.145
Neg logit contributions
llah-0.162
ible-0.151
enegger-0.149
 IPM-0.144
esters-0.143
Tokengreat
Token ID18223
Feature activation+2.63e+00

Pos logit contributions
llah+0.030
ible+0.028
enegger+0.028
 IPM+0.027
esters+0.027
Neg logit contributions
 proport-0.030
 suspic-0.029
 comr-0.025
 fortun-0.024
stress-0.022
Token,
Token ID11
Feature activation-1.66e-01

Pos logit contributions
 proport+2.570
 suspic+2.508
 comr+2.198
 fortun+2.109
stress+1.965
Neg logit contributions
llah-1.979
ible-1.823
enegger-1.820
 IPM-1.771
esters-1.751
Token
Token ID447
Feature activation-1.88e-01

Pos logit contributions
llah+0.121
ible+0.112
enegger+0.111
 IPM+0.108
esters+0.107
Neg logit contributions
 proport-0.167
 suspic-0.163
 comr-0.144
 fortun-0.137
stress-0.128
Token
Token ID251
Feature activation+2.02e-01

Pos logit contributions
llah+0.152
ible+0.141
enegger+0.140
 IPM+0.136
esters+0.135
Neg logit contributions
 proport-0.173
 suspic-0.170
 comr-0.148
 fortun-0.141
stress-0.130
Token McDonnell
Token ID39441
Feature activation-6.88e+00

Pos logit contributions
 proport+0.234
 suspic+0.229
 comr+0.205
 fortun+0.198
stress+0.187
Neg logit contributions
llah-0.115
ible-0.104
enegger-0.103
 IPM-0.099
esters-0.098
Token said
Token ID531
Feature activation-1.26e+00

Pos logit contributions
llah+3.934
enegger+3.826
ible+3.643
+3.390
esters+3.376
Neg logit contributions
 proport-7.560
 suspic-7.433
 comr-6.663
 fortun-6.406
��-6.039
Token in
Token ID287
Feature activation-7.75e-01

Pos logit contributions
llah+0.859
ible+0.792
enegger+0.790
 IPM+0.754
esters+0.749
Neg logit contributions
 proport-1.316
 suspic-1.292
 comr-1.149
 fortun-1.095
stress-1.020
Token response
Token ID2882
Feature activation-3.13e-02

Pos logit contributions
llah+0.619
ible+0.577
enegger+0.576
 IPM+0.556
esters+0.550
Neg logit contributions
 proport-0.726
 suspic-0.706
 comr-0.615
 fortun-0.586
stress-0.538
Token to
Token ID284
Feature activation-3.24e-01

Pos logit contributions
llah+0.021
ible+0.019
enegger+0.019
 IPM+0.018
esters+0.018
Neg logit contributions
 proport-0.033
 suspic-0.033
 comr-0.029
 fortun-0.028
stress-0.026
Token a
Token ID257
Feature activation+4.81e-02

Pos logit contributions
llah+0.258
ible+0.239
enegger+0.238
 IPM+0.231
esters+0.229
Neg logit contributions
 proport-0.305
 suspic-0.296
 comr-0.258
 fortun-0.247
stress-0.228
Token of
Token ID286
Feature activation-2.86e-01

Pos logit contributions
llah+0.828
ible+0.776
enegger+0.756
 IPM+0.739
esters+0.731
Neg logit contributions
 proport-1.145
 suspic-1.124
 comr-0.985
 fortun-0.943
��-0.875
Token Stamford
Token ID47604
Feature activation+4.26e+00

Pos logit contributions
llah+0.219
ible+0.203
enegger+0.201
 IPM+0.196
esters+0.194
Neg logit contributions
 proport-0.277
 suspic-0.269
 comr-0.236
 fortun-0.225
stress-0.210
Token Bridge
Token ID10290
Feature activation-7.35e-01

Pos logit contributions
 proport+3.680
 suspic+3.585
 comr+3.079
 fortun+2.925
stress+2.706
Neg logit contributions
llah-3.678
ible-3.440
enegger-3.430
 IPM-3.326
esters-3.295
Token,
Token ID11
Feature activation+8.50e-02

Pos logit contributions
llah+0.554
ible+0.509
enegger+0.501
 IPM+0.497
esters+0.488
Neg logit contributions
 proport-0.719
 suspic-0.698
 comr-0.616
 fortun-0.585
stress-0.545
Token the
Token ID262
Feature activation-1.08e+00

Pos logit contributions
 proport+0.086
 suspic+0.084
 comr+0.074
 fortun+0.070
stress+0.066
Neg logit contributions
llah-0.062
ible-0.057
enegger-0.056
 IPM-0.055
esters-0.054
Token nort
Token ID17605
Feature activation-6.84e+00

Pos logit contributions
llah+0.802
ible+0.739
enegger+0.724
 IPM+0.717
esters+0.701
Neg logit contributions
 proport-1.065
 suspic-1.037
 comr-0.912
 fortun-0.868
stress-0.813
Tokenher
Token ID372
Feature activation-4.31e-01

Pos logit contributions
llah+4.886
ible+4.547
enegger+4.454
esters+4.429
osal+4.288
Neg logit contributions
 proport-6.911
 suspic-6.847
 comr-5.988
 fortun-5.724
��-5.279
Tokenners
Token ID2741
Feature activation-1.80e+00

Pos logit contributions
llah+0.331
ible+0.306
enegger+0.304
 IPM+0.296
esters+0.292
Neg logit contributions
 proport-0.415
 suspic-0.404
 comr-0.354
 fortun-0.338
stress-0.316
Token were
Token ID547
Feature activation-6.97e-01

Pos logit contributions
llah+1.245
ible+1.145
enegger+1.128
 IPM+1.106
esters+1.089
Neg logit contributions
 proport-1.857
 suspic-1.817
 comr-1.606
 fortun-1.535
stress-1.442
Token remarkably
Token ID21196
Feature activation-4.88e-01

Pos logit contributions
llah+0.497
ible+0.459
enegger+0.454
 IPM+0.443
esters+0.438
Neg logit contributions
 proport-0.709
 suspic-0.691
 comr-0.610
 fortun-0.583
stress-0.549
Token absent
Token ID13717
Feature activation+1.53e+00

Pos logit contributions
llah+0.372
ible+0.344
enegger+0.342
 IPM+0.332
esters+0.329
Neg logit contributions
 proport-0.472
 suspic-0.461
 comr-0.404
 fortun-0.386
stress-0.360
Token frequent
Token ID10792
Feature activation-1.95e+00

Pos logit contributions
 proport+0.441
 suspic+0.431
 comr+0.376
 fortun+0.359
stress+0.334
Neg logit contributions
llah-0.360
ible-0.336
enegger-0.332
 IPM-0.324
esters-0.319
Token Dinosaur
Token ID47808
Feature activation+2.35e+00

Pos logit contributions
llah+1.628
ible+1.542
enegger+1.518
 IPM+1.480
esters+1.468
Neg logit contributions
 proport-1.720
 suspic-1.684
 comr-1.445
 fortun-1.371
stress-1.274
Token Jr
Token ID7504
Feature activation-3.09e+00

Pos logit contributions
 proport+2.615
 suspic+2.562
 comr+2.283
 fortun+2.199
stress+2.073
Neg logit contributions
llah-1.458
ible-1.324
enegger-1.312
 IPM-1.265
esters-1.249
Token.
Token ID13
Feature activation+8.64e-01

Pos logit contributions
llah+2.080
ible+1.925
enegger+1.885
esters+1.821
osal+1.792
Neg logit contributions
 proport-3.218
 suspic-3.169
 comr-2.793
 fortun-2.683
stress-2.516
Token collaborator
Token ID50160
Feature activation-2.24e+00

Pos logit contributions
 proport+0.820
 suspic+0.800
 comr+0.697
 fortun+0.666
stress+0.620
Neg logit contributions
llah-0.675
ible-0.627
enegger-0.622
 IPM-0.604
esters-0.599
Token Maur
Token ID18867
Feature activation-6.82e+00

Pos logit contributions
llah+1.615
ible+1.507
enegger+1.469
 IPM+1.451
esters+1.418
Neg logit contributions
 proport-2.260
 suspic-2.207
 comr-1.935
 fortun-1.844
stress-1.717
Tokena
Token ID64
Feature activation+1.69e+00

Pos logit contributions
llah+4.936
ible+4.576
enegger+4.349
esters+4.306
osal+4.294
Neg logit contributions
 proport-6.785
 suspic-6.782
 comr-5.821
 fortun-5.614
��-5.186
Token Jasper
Token ID42992
Feature activation+1.26e+00

Pos logit contributions
 proport+1.641
 suspic+1.603
 comr+1.403
 fortun+1.341
stress+1.248
Neg logit contributions
llah-1.287
ible-1.194
enegger-1.184
 IPM-1.149
esters-1.139
Token,
Token ID11
Feature activation-2.31e-01

Pos logit contributions
 proport+1.250
 suspic+1.221
 comr+1.073
 fortun+1.027
stress+0.958
Neg logit contributions
llah-0.930
ible-0.859
enegger-0.853
 IPM-0.826
esters-0.818
Token an
Token ID281
Feature activation-1.30e+00

Pos logit contributions
llah+0.167
ible+0.156
enegger+0.154
 IPM+0.151
osal+0.147
Neg logit contributions
 proport-0.231
 suspic-0.226
 comr-0.198
 fortun-0.190
stress-0.177
Token essay
Token ID14268
Feature activation-1.69e+00

Pos logit contributions
llah+0.933
ible+0.864
enegger+0.853
 IPM+0.834
osal+0.820
Neg logit contributions
 proport-1.305
 suspic-1.275
 comr-1.125
 fortun-1.075
stress-1.010
Token traffic
Token ID4979
Feature activation-2.90e-01

Pos logit contributions
 proport+1.150
 suspic+1.120
 comr+0.975
 fortun+0.930
stress+0.865
Neg logit contributions
llah-0.983
ible-0.914
enegger-0.907
 IPM-0.884
esters-0.874
Token control
Token ID1630
Feature activation+3.39e-01

Pos logit contributions
llah+0.236
ible+0.222
enegger+0.218
 IPM+0.213
esters+0.211
Neg logit contributions
 proport-0.267
 suspic-0.258
 comr-0.224
 fortun-0.213
stress-0.197
Token and
Token ID290
Feature activation+8.50e-02

Pos logit contributions
 proport+0.349
 suspic+0.341
 comr+0.301
 fortun+0.288
stress+0.270
Neg logit contributions
llah-0.237
ible-0.220
enegger-0.216
 IPM-0.211
esters-0.208
Token surveillance
Token ID8452
Feature activation+3.04e+00

Pos logit contributions
 proport+0.080
 suspic+0.078
 comr+0.068
 fortun+0.065
stress+0.060
Neg logit contributions
llah-0.067
ible-0.062
enegger-0.061
 IPM-0.061
esters-0.059
Token.
Token ID13
Feature activation-4.75e-01

Pos logit contributions
 proport+2.987
 suspic+2.914
 comr+2.563
 fortun+2.456
stress+2.293
Neg logit contributions
llah-2.261
enegger-2.081
ible-2.065
 IPM-2.003
esters-1.998
Token McDonnell
Token ID39441
Feature activation-6.80e+00

Pos logit contributions
llah+0.359
ible+0.332
enegger+0.330
 IPM+0.321
esters+0.317
Neg logit contributions
 proport-0.464
 suspic-0.454
 comr-0.397
 fortun-0.380
stress-0.353
Token
Token ID447
Feature activation-4.89e-01

Pos logit contributions
llah+4.610
enegger+4.442
ible+4.339
esters+4.069
 IPM+4.050
Neg logit contributions
 proport-6.843
 suspic-6.660
 comr-5.986
 fortun-5.659
��-5.315
Token
Token ID247
Feature activation-3.63e-01

Pos logit contributions
llah+0.526
ible+0.497
enegger+0.493
 IPM+0.484
esters+0.481
Neg logit contributions
 proport-0.323
 suspic-0.313
 comr-0.255
 fortun-0.238
stress-0.210
Tokens
Token ID82
Feature activation-8.10e-01

Pos logit contributions
llah+0.213
ible+0.192
enegger+0.191
 IPM+0.182
esters+0.181
Neg logit contributions
 proport-0.416
 suspic-0.408
 comr-0.365
 fortun-0.352
stress-0.331
Token office
Token ID2607
Feature activation+1.04e+00

Pos logit contributions
llah+0.615
ible+0.571
enegger+0.568
 IPM+0.550
esters+0.543
Neg logit contributions
 proport-0.786
 suspic-0.766
 comr-0.669
 fortun-0.641
stress-0.599
Token later
Token ID1568
Feature activation-1.03e+00

Pos logit contributions
 proport+1.045
 suspic+1.021
 comr+0.898
 fortun+0.861
stress+0.806
Neg logit contributions
llah-0.749
ible-0.690
enegger-0.686
 IPM-0.665
esters-0.658
Token an
Token ID281
Feature activation-5.07e-01

Pos logit contributions
 proport+0.592
 suspic+0.576
 comr+0.502
 fortun+0.479
stress+0.445
Neg logit contributions
llah-0.506
ible-0.471
enegger-0.467
 IPM-0.455
esters-0.450
Token incompetent
Token ID33840
Feature activation-1.50e-01

Pos logit contributions
llah+0.399
ible+0.372
enegger+0.368
 IPM+0.359
esters+0.354
Neg logit contributions
 proport-0.478
 suspic-0.465
 comr-0.407
 fortun-0.387
stress-0.361
Token fool
Token ID9192
Feature activation-1.63e+00

Pos logit contributions
llah+0.117
ible+0.109
enegger+0.108
 IPM+0.105
esters+0.104
Neg logit contributions
 proport-0.142
 suspic-0.139
 comr-0.121
 fortun-0.115
stress-0.108
Token.
Token ID13
Feature activation-4.67e-02

Pos logit contributions
llah+1.153
ible+1.070
enegger+1.061
 IPM+1.017
esters+1.010
Neg logit contributions
 proport-1.669
 suspic-1.631
 comr-1.444
 fortun-1.374
stress-1.284
Token Even
Token ID3412
Feature activation-1.26e+00

Pos logit contributions
llah+0.037
ible+0.034
enegger+0.034
 IPM+0.033
esters+0.033
Neg logit contributions
 proport-0.044
 suspic-0.043
 comr-0.037
 fortun-0.036
stress-0.033
Token GT
Token ID7963
Feature activation-6.74e+00

Pos logit contributions
llah+0.914
ible+0.854
enegger+0.848
 IPM+0.824
esters+0.808
Neg logit contributions
 proport-1.262
 suspic-1.225
 comr-1.086
 fortun-1.029
stress-0.968
Token did
Token ID750
Feature activation+2.90e-01

Pos logit contributions
llah+4.717
ible+4.387
enegger+4.340
esters+4.175
 IPM+4.174
Neg logit contributions
 proport-6.833
 suspic-6.610
 comr-5.870
 fortun-5.539
stress-5.210
Token a
Token ID257
Feature activation-1.32e-01

Pos logit contributions
 proport+0.287
 suspic+0.280
 comr+0.246
 fortun+0.236
stress+0.220
Neg logit contributions
llah-0.215
ible-0.199
enegger-0.197
 IPM-0.192
esters-0.190
Token better
Token ID1365
Feature activation-1.13e+00

Pos logit contributions
llah+0.101
ible+0.093
enegger+0.092
 IPM+0.090
esters+0.089
Neg logit contributions
 proport-0.128
 suspic-0.125
 comr-0.110
 fortun-0.104
stress-0.098
Token job
Token ID1693
Feature activation-1.09e-02

Pos logit contributions
llah+0.949
ible+0.894
enegger+0.881
 IPM+0.863
esters+0.854
Neg logit contributions
 proport-1.007
 suspic-0.978
 comr-0.851
 fortun-0.802
stress-0.746
Token at
Token ID379
Feature activation-6.86e-01

Pos logit contributions
llah+0.008
ible+0.007
enegger+0.007
 IPM+0.007
esters+0.007
Neg logit contributions
 proport-0.011
 suspic-0.011
 comr-0.009
 fortun-0.009
stress-0.008
Token of
Token ID286
Feature activation+1.59e-02

Pos logit contributions
llah+0.617
ible+0.574
enegger+0.561
 IPM+0.551
esters+0.544
Neg logit contributions
 proport-0.858
 suspic-0.840
 comr-0.739
 fortun-0.709
stress-0.657
Token the
Token ID262
Feature activation+2.15e-02

Pos logit contributions
 proport+0.015
 suspic+0.015
 comr+0.013
 fortun+0.013
stress+0.012
Neg logit contributions
llah-0.012
ible-0.011
enegger-0.011
 IPM-0.011
esters-0.011
Token city
Token ID1748
Feature activation+3.62e-02

Pos logit contributions
 proport+0.022
 suspic+0.021
 comr+0.019
 fortun+0.018
stress+0.017
Neg logit contributions
llah-0.015
ible-0.014
enegger-0.014
 IPM-0.014
osal-0.014
Token's
Token ID338
Feature activation-2.68e-01

Pos logit contributions
 proport+0.033
 suspic+0.033
 comr+0.028
 fortun+0.027
��+0.025
Neg logit contributions
llah-0.029
ible-0.027
enegger-0.027
 IPM-0.026
esters-0.026
Token famous
Token ID5863
Feature activation+7.84e-01

Pos logit contributions
llah+0.201
ible+0.187
enegger+0.185
 IPM+0.180
osal+0.177
Neg logit contributions
 proport-0.263
 suspic-0.257
 comr-0.224
 fortun-0.214
stress-0.202
Token Cock
Token ID23769
Feature activation-6.72e+00

Pos logit contributions
 proport+0.762
 suspic+0.744
 comr+0.650
 fortun+0.621
stress+0.581
Neg logit contributions
llah-0.596
ible-0.552
enegger-0.548
 IPM-0.533
esters-0.527
Tokeners
Token ID364
Feature activation-6.36e-01

Pos logit contributions
llah+5.143
ible+4.872
enegger+4.683
osal+4.585
esters+4.582
Neg logit contributions
 proport-6.390
 suspic-6.238
 comr-5.433
 fortun-5.124
��-4.786
Token Roses
Token ID41244
Feature activation+7.83e-01

Pos logit contributions
llah+0.478
ible+0.443
enegger+0.439
 IPM+0.425
esters+0.421
Neg logit contributions
 proport-0.625
 suspic-0.610
 comr-0.535
 fortun-0.511
stress-0.477
Token business
Token ID1597
Feature activation-1.81e-01

Pos logit contributions
 proport+0.745
 suspic+0.727
 comr+0.635
 fortun+0.607
stress+0.565
Neg logit contributions
llah-0.611
ible-0.566
enegger-0.563
 IPM-0.547
esters-0.541
Token.
Token ID13
Feature activation+1.71e-01

Pos logit contributions
llah+0.133
ible+0.123
enegger+0.122
 IPM+0.119
esters+0.117
Neg logit contributions
 proport-0.180
 suspic-0.176
 comr-0.154
 fortun-0.148
stress-0.138
Token
Token ID198
Feature activation-3.34e-01

Pos logit contributions
 proport+0.173
 suspic+0.170
 comr+0.149
 fortun+0.143
stress+0.133
Neg logit contributions
llah-0.124
ible-0.114
enegger-0.113
 IPM-0.110
esters-0.109
Token also
Token ID635
Feature activation+1.08e+00

Pos logit contributions
 proport+1.652
 suspic+1.596
 comr+1.384
 fortun+1.324
stress+1.210
Neg logit contributions
llah-1.542
ible-1.449
enegger-1.426
 IPM-1.394
osal-1.374
Token Trump
Token ID1301
Feature activation+6.68e-02

Pos logit contributions
 proport+1.033
 suspic+1.002
 comr+0.878
 fortun+0.836
stress+0.778
Neg logit contributions
llah-0.851
ible-0.789
enegger-0.783
 IPM-0.763
osal-0.752
Token hints
Token ID20269
Feature activation-3.51e+00

Pos logit contributions
 proport+0.063
 suspic+0.062
 comr+0.054
 fortun+0.052
stress+0.048
Neg logit contributions
llah-0.052
ible-0.048
enegger-0.048
 IPM-0.047
osal-0.046
Token he
Token ID339
Feature activation+5.56e-01

Pos logit contributions
llah+2.300
ible+2.088
enegger+2.024
 IPM+1.978
osal+1.970
Neg logit contributions
 proport-3.791
 suspic-3.651
 comr-3.290
 fortun-3.148
stress-2.948
Token taped
Token ID36114
Feature activation-1.25e+00

Pos logit contributions
 proport+0.577
 suspic+0.564
 comr+0.499
 fortun+0.478
stress+0.449
Neg logit contributions
llah-0.386
ible-0.354
enegger-0.352
 IPM-0.341
esters-0.337
Token Comey
Token ID12388
Feature activation+4.52e+00

Pos logit contributions
llah+0.970
ible+0.895
enegger+0.877
 IPM+0.864
esters+0.855
Neg logit contributions
 proport-1.192
 suspic-1.148
 comr-1.012
 fortun-0.955
stress-0.893
Token conversations
Token ID10275
Feature activation-4.47e-01

Pos logit contributions
 proport+4.326
 suspic+4.265
 comr+3.687
 fortun+3.548
stress+3.302
Neg logit contributions
llah-3.423
ible-3.197
enegger-3.189
 IPM-3.072
esters-3.049
Token in
Token ID287
Feature activation-9.28e-02

Pos logit contributions
llah+0.335
ible+0.309
enegger+0.306
 IPM+0.299
esters+0.295
Neg logit contributions
 proport-0.439
 suspic-0.428
 comr-0.377
 fortun-0.360
stress-0.335
Token veiled
Token ID45694
Feature activation-5.00e-01

Pos logit contributions
llah+0.069
ible+0.064
enegger+0.063
 IPM+0.062
esters+0.061
Neg logit contributions
 proport-0.091
 suspic-0.089
 comr-0.078
 fortun-0.075
stress-0.069
Token threat
Token ID2372
Feature activation+9.45e-01

Pos logit contributions
llah+0.384
ible+0.363
enegger+0.354
 IPM+0.346
osal+0.343
Neg logit contributions
 proport-0.476
 suspic-0.460
 comr-0.404
 fortun-0.386
stress-0.358
Token President
Token ID1992
Feature activation+1.02e+00

Pos logit contributions
 proport+0.952
 suspic+0.930
 comr+0.819
 fortun+0.784
stress+0.732
Neg logit contributions
llah-0.687
ible-0.633
enegger-0.627
 IPM-0.609
esters-0.602
Token.
Token ID13
Feature activation-3.46e-01

Pos logit contributions
 proport+2.497
 suspic+2.433
 comr+2.134
 fortun+2.058
stress+1.927
Neg logit contributions
llah-1.819
ible-1.664
enegger-1.663
 IPM-1.614
osal-1.593
Token<|endoftext|>
Token ID50256
Feature activation+1.43e-01

Pos logit contributions
llah+0.259
ible+0.239
enegger+0.238
 IPM+0.232
esters+0.229
Neg logit contributions
 proport-0.343
 suspic-0.335
 comr-0.294
 fortun-0.281
stress-0.261
TokenIll
Token ID21478
Feature activation+4.26e+00

Pos logit contributions
 proport+0.139
 suspic+0.135
 comr+0.118
 fortun+0.113
stress+0.104
Neg logit contributions
llah-0.110
ible-0.102
enegger-0.101
 IPM-0.098
esters-0.098
Tokenust
Token ID436
Feature activation+1.11e+00

Pos logit contributions
 proport+2.897
 suspic+2.793
 comr+2.291
 fortun+2.158
stress+1.934
Neg logit contributions
llah-4.450
enegger-4.194
ible-4.184
 IPM-4.117
esters-4.068
Tokenrious
Token ID32527
Feature activation-5.49e-01

Pos logit contributions
 proport+0.776
 suspic+0.755
 comr+0.622
 fortun+0.579
stress+0.517
Neg logit contributions
llah-1.148
ible-1.091
enegger-1.080
 IPM-1.054
esters-1.052
Token Illum
Token ID39256
Feature activation+5.50e+00

Pos logit contributions
llah+0.412
ible+0.382
enegger+0.378
 IPM+0.370
esters+0.364
Neg logit contributions
 proport-0.538
 suspic-0.525
 comr-0.460
 fortun-0.438
stress-0.411
Tokenination
Token ID1883
Feature activation-3.57e-01

Pos logit contributions
 proport+3.544
 suspic+3.416
 comr+2.760
 fortun+2.605
stress+2.343
Neg logit contributions
llah-5.909
enegger-5.558
ible-5.543
 IPM-5.458
esters-5.378
Token:
Token ID25
Feature activation+1.46e+00

Pos logit contributions
llah+0.264
ible+0.246
enegger+0.240
 IPM+0.237
esters+0.233
Neg logit contributions
 proport-0.354
 suspic-0.345
 comr-0.304
 fortun-0.288
stress-0.268
Token Incredible
Token ID33832
Feature activation+2.36e+00

Pos logit contributions
 proport+1.403
 suspic+1.368
 comr+1.196
 fortun+1.141
stress+1.063
Neg logit contributions
llah-1.133
ible-1.050
enegger-1.043
 IPM-1.016
esters-1.004
Token TR
Token ID7579
Feature activation-7.01e-01

Pos logit contributions
 proport+2.286
 suspic+2.231
 comr+1.952
 fortun+1.871
stress+1.743
Neg logit contributions
llah-1.797
ible-1.657
enegger-1.652
 IPM-1.599
esters-1.587
TokenON
Token ID1340
Feature activation-2.35e-01

Pos logit contributions
llah+0.487
ible+0.450
enegger+0.441
esters+0.429
 IPM+0.429
Neg logit contributions
 proport-0.726
 suspic-0.710
 comr-0.627
 fortun-0.597
stress-0.562
Tokenpair
Token ID24874
Feature activation+3.38e-01

Pos logit contributions
llah+0.571
ible+0.528
enegger+0.521
 IPM+0.509
esters+0.504
Neg logit contributions
 proport-0.776
 suspic-0.757
 comr-0.664
 fortun-0.637
stress-0.591
Token but
Token ID475
Feature activation+2.02e+00

Pos logit contributions
 proport+0.342
 suspic+0.334
 comr+0.294
 fortun+0.282
stress+0.264
Neg logit contributions
llah-0.244
ible-0.224
enegger-0.223
 IPM-0.216
esters-0.214
Token require
Token ID2421
Feature activation-7.07e-01

Pos logit contributions
 proport+2.069
 suspic+2.014
 comr+1.779
 fortun+1.710
stress+1.601
Neg logit contributions
llah-1.441
enegger-1.314
ible-1.305
 IPM-1.254
esters-1.248
Token out
Token ID503
Feature activation+5.56e-01

Pos logit contributions
llah+0.536
ible+0.499
enegger+0.490
 IPM+0.484
esters+0.475
Neg logit contributions
 proport-0.687
 suspic-0.671
 comr-0.587
 fortun-0.560
stress-0.524
Tokenboard
Token ID3526
Feature activation-1.60e+00

Pos logit contributions
 proport+0.566
 suspic+0.555
 comr+0.488
 fortun+0.467
stress+0.434
Neg logit contributions
llah-0.397
ible-0.367
enegger-0.362
 IPM-0.353
esters-0.349
Token amplification
Token ID50250
Feature activation+4.46e+00

Pos logit contributions
llah+1.261
ible+1.174
enegger+1.158
 IPM+1.140
esters+1.120
Neg logit contributions
 proport-1.504
 suspic-1.467
 comr-1.276
 fortun-1.219
stress-1.136
Token and
Token ID290
Feature activation+1.22e-01

Pos logit contributions
 proport+4.250
 suspic+4.118
 comr+3.610
 fortun+3.488
stress+3.251
Neg logit contributions
llah-3.411
enegger-3.180
ible-3.068
esters-3.001
osal-2.986
Token electronics
Token ID17075
Feature activation+2.47e-01

Pos logit contributions
 proport+0.119
 suspic+0.116
 comr+0.102
 fortun+0.097
stress+0.091
Neg logit contributions
llah-0.092
ible-0.085
enegger-0.084
 IPM-0.082
esters-0.081
Token.
Token ID13
Feature activation-3.38e-01

Pos logit contributions
 proport+0.250
 suspic+0.244
 comr+0.215
 fortun+0.206
stress+0.193
Neg logit contributions
llah-0.177
ible-0.163
enegger-0.162
 IPM-0.157
esters-0.155
Token A
Token ID317
Feature activation-1.50e-01

Pos logit contributions
llah+0.278
ible+0.257
enegger+0.257
 IPM+0.248
esters+0.247
Neg logit contributions
 proport-0.306
 suspic-0.298
 comr-0.259
 fortun-0.248
stress-0.230
Token pair
Token ID5166
Feature activation+1.56e-01

Pos logit contributions
llah+0.114
ible+0.106
enegger+0.105
 IPM+0.102
esters+0.101
Neg logit contributions
 proport-0.145
 suspic-0.141
 comr-0.124
 fortun-0.118
stress-0.110
Token.
Token ID13
Feature activation+4.19e-02

Pos logit contributions
llah+0.058
ible+0.053
enegger+0.052
 IPM+0.051
osal+0.050
Neg logit contributions
 proport-0.086
 suspic-0.085
 comr-0.075
 fortun-0.072
stress-0.067
Token An
Token ID1052
Feature activation-3.24e-01

Pos logit contributions
 proport+0.039
 suspic+0.038
 comr+0.033
 fortun+0.031
stress+0.029
Neg logit contributions
llah-0.034
ible-0.031
enegger-0.031
 IPM-0.030
esters-0.030
Token array
Token ID7177
Feature activation+9.32e-01

Pos logit contributions
llah+0.225
ible+0.206
enegger+0.205
 IPM+0.199
esters+0.196
Neg logit contributions
 proport-0.335
 suspic-0.328
 comr-0.290
 fortun-0.278
stress-0.261
Token of
Token ID286
Feature activation-1.99e-01

Pos logit contributions
 proport+0.835
 suspic+0.814
 comr+0.703
 fortun+0.682
stress+0.643
Neg logit contributions
llah-0.754
enegger-0.706
ible-0.690
 IPM-0.683
esters-0.680
Token online
Token ID2691
Feature activation+1.63e+00

Pos logit contributions
llah+0.144
ible+0.133
enegger+0.132
 IPM+0.128
esters+0.126
Neg logit contributions
 proport-0.201
 suspic-0.195
 comr-0.173
 fortun-0.165
stress-0.154
Token stores
Token ID7000
Feature activation+5.28e+00

Pos logit contributions
 proport+1.364
 suspic+1.326
 comr+1.133
 fortun+1.075
stress+0.988
Neg logit contributions
llah-1.459
ible-1.365
enegger-1.359
 IPM-1.326
esters-1.315
Token offer
Token ID2897
Feature activation-1.87e+00

Pos logit contributions
 proport+5.307
 suspic+5.193
 comr+4.528
 fortun+4.417
stress+4.168
Neg logit contributions
llah-3.759
enegger-3.441
ible-3.362
 IPM-3.304
obic-3.273
Token a
Token ID257
Feature activation+3.59e-01

Pos logit contributions
llah+1.367
ible+1.275
enegger+1.244
 IPM+1.219
osal+1.196
Neg logit contributions
 proport-1.874
 suspic-1.819
 comr-1.606
 fortun-1.529
��-1.434
Token huge
Token ID3236
Feature activation+9.30e-01

Pos logit contributions
 proport+0.329
 suspic+0.320
 comr+0.278
 fortun+0.265
stress+0.246
Neg logit contributions
llah-0.293
ible-0.272
enegger-0.271
 IPM-0.264
esters-0.261
Token range
Token ID2837
Feature activation+1.06e+00

Pos logit contributions
 proport+0.888
 suspic+0.867
 comr+0.756
 fortun+0.724
stress+0.674
Neg logit contributions
llah-0.723
ible-0.667
enegger-0.666
 IPM-0.646
esters-0.641
Token of
Token ID286
Feature activation+3.35e-01

Pos logit contributions
 proport+1.041
 suspic+1.019
 comr+0.893
 fortun+0.855
stress+0.795
Neg logit contributions
llah-0.800
ible-0.742
enegger-0.735
 IPM-0.711
osal-0.707
TokenI
Token ID40
Feature activation+6.72e-01

Pos logit contributions
 proport+0.048
 suspic+0.047
 comr+0.041
 fortun+0.039
stress+0.036
Neg logit contributions
llah-0.038
ible-0.036
enegger-0.035
 IPM-0.034
esters-0.034
Token liked
Token ID8288
Feature activation-7.57e-01

Pos logit contributions
 proport+0.690
 suspic+0.675
 comr+0.593
 fortun+0.570
stress+0.537
Neg logit contributions
llah-0.472
ible-0.435
enegger-0.432
 IPM-0.420
esters-0.415
Token the
Token ID262
Feature activation-2.08e-01

Pos logit contributions
llah+0.551
ible+0.512
enegger+0.501
 IPM+0.493
esters+0.486
Neg logit contributions
 proport-0.758
 suspic-0.737
 comr-0.649
 fortun-0.617
stress-0.582
Token movie
Token ID3807
Feature activation+2.48e+00

Pos logit contributions
llah+0.151
ible+0.140
enegger+0.138
 IPM+0.135
esters+0.132
Neg logit contributions
 proport-0.208
 suspic-0.203
 comr-0.178
 fortun-0.171
stress-0.160
Token The
Token ID383
Feature activation+1.28e+00

Pos logit contributions
 proport+2.411
 suspic+2.354
 comr+2.061
 fortun+1.973
stress+1.841
Neg logit contributions
llah-1.878
ible-1.736
enegger-1.726
 IPM-1.676
esters-1.658
Token Pur
Token ID9330
Feature activation+4.59e+00

Pos logit contributions
 proport+1.068
 suspic+1.037
 comr+0.885
 fortun+0.836
stress+0.767
Neg logit contributions
llah-1.158
ible-1.088
enegger-1.078
 IPM-1.055
esters-1.044
Tokenge
Token ID469
Feature activation-6.21e-01

Pos logit contributions
 proport+3.932
 suspic+3.848
 comr+3.366
 fortun+3.268
stress+3.252
Neg logit contributions
llah-3.683
enegger-3.504
 IPM-3.350
ible-3.335
RESULTS-3.225
Token but
Token ID475
Feature activation+2.19e+00

Pos logit contributions
llah+0.454
ible+0.420
enegger+0.417
 IPM+0.402
esters+0.401
Neg logit contributions
 proport-0.623
 suspic-0.605
 comr-0.533
 fortun-0.510
stress-0.474
Token with
Token ID351
Feature activation+1.92e-01

Pos logit contributions
 proport+2.247
 suspic+2.200
 comr+1.937
 fortun+1.865
stress+1.742
Neg logit contributions
llah-1.530
ible-1.403
enegger-1.397
 IPM-1.352
esters-1.339
Token everything
Token ID2279
Feature activation+1.62e+00

Pos logit contributions
 proport+0.185
 suspic+0.180
 comr+0.158
 fortun+0.150
stress+0.141
Neg logit contributions
llah-0.148
ible-0.137
enegger-0.136
 IPM-0.132
esters-0.130
Token it
Token ID340
Feature activation-1.73e-01

Pos logit contributions
 proport+1.624
 suspic+1.588
 comr+1.393
 fortun+1.336
stress+1.248
Neg logit contributions
llah-1.185
ible-1.093
enegger-1.088
 IPM-1.054
esters-1.043
Token Italian
Token ID8200
Feature activation-2.16e+00

Pos logit contributions
 proport+2.688
 suspic+2.622
 comr+2.307
 fortun+2.205
stress+2.062
Neg logit contributions
llah-2.027
ible-1.863
enegger-1.858
 IPM-1.795
esters-1.780
Token volunteers
Token ID11661
Feature activation+9.34e-01

Pos logit contributions
llah+1.622
ible+1.530
enegger+1.510
 IPM+1.485
esters+1.459
Neg logit contributions
 proport-2.084
 suspic-2.042
 comr-1.773
 fortun-1.708
stress-1.575
Token Storm
Token ID8865
Feature activation-1.62e+00

Pos logit contributions
 proport+0.964
 suspic+0.941
 comr+0.832
 fortun+0.799
stress+0.750
Neg logit contributions
llah-0.654
ible-0.599
enegger-0.596
 IPM-0.576
esters-0.570
Token Brigade
Token ID26012
Feature activation-2.01e-01

Pos logit contributions
llah+1.211
ible+1.131
enegger+1.121
 IPM+1.080
osal+1.073
Neg logit contributions
 proport-1.596
 suspic-1.560
 comr-1.363
 fortun-1.305
stress-1.206
Token were
Token ID547
Feature activation-3.01e-01

Pos logit contributions
llah+0.142
ible+0.131
enegger+0.130
 IPM+0.126
esters+0.124
Neg logit contributions
 proport-0.206
 suspic-0.201
 comr-0.177
 fortun-0.170
stress-0.159
Token sent
Token ID1908
Feature activation+1.35e+00

Pos logit contributions
llah+0.228
ible+0.211
enegger+0.210
 IPM+0.204
esters+0.202
Neg logit contributions
 proport-0.292
 suspic-0.285
 comr-0.250
 fortun-0.239
stress-0.223
Token to
Token ID284
Feature activation+2.98e-01

Pos logit contributions
 proport+1.408
 suspic+1.377
 comr+1.217
 fortun+1.169
stress+1.096
Neg logit contributions
llah-0.929
ible-0.852
enegger-0.846
 IPM-0.819
esters-0.810
Token the
Token ID262
Feature activation+1.25e-01

Pos logit contributions
 proport+0.297
 suspic+0.291
 comr+0.255
 fortun+0.245
stress+0.228
Neg logit contributions
llah-0.217
ible-0.201
enegger-0.199
 IPM-0.194
esters-0.191
Token An
Token ID1052
Feature activation+4.58e-01

Pos logit contributions
 proport+0.123
 suspic+0.121
 comr+0.105
 fortun+0.101
stress+0.094
Neg logit contributions
llah-0.093
ible-0.086
enegger-0.085
 IPM-0.083
esters-0.082
Tokenz
Token ID89
Feature activation+5.38e-01

Pos logit contributions
 proport+0.432
 suspic+0.421
 comr+0.367
 fortun+0.349
stress+0.324
Neg logit contributions
llah-0.363
ible-0.338
enegger-0.334
 IPM-0.325
esters-0.323
Tokenio
Token ID952
Feature activation+1.70e+00

Pos logit contributions
 proport+0.520
 suspic+0.507
 comr+0.444
 fortun+0.424
stress+0.394
Neg logit contributions
llah-0.414
ible-0.386
enegger-0.382
 IPM-0.370
esters-0.368
Token the
Token ID262
Feature activation-5.26e-02

Pos logit contributions
 proport+0.018
 suspic+0.017
 comr+0.015
 fortun+0.015
stress+0.014
Neg logit contributions
llah-0.014
ible-0.013
enegger-0.013
 IPM-0.013
esters-0.012
Token Democratic
Token ID4390
Feature activation+2.48e+00

Pos logit contributions
llah+0.040
ible+0.037
enegger+0.036
 IPM+0.035
esters+0.035
Neg logit contributions
 proport-0.051
 suspic-0.050
 comr-0.044
 fortun-0.042
stress-0.039
Token Party
Token ID3615
Feature activation+5.32e-01

Pos logit contributions
 proport+2.114
 suspic+2.056
 comr+1.763
 fortun+1.673
stress+1.537
Neg logit contributions
llah-2.185
enegger-2.039
ible-2.036
 IPM-1.977
esters-1.964
Token was
Token ID373
Feature activation+4.59e-01

Pos logit contributions
 proport+0.553
 suspic+0.541
 comr+0.478
 fortun+0.458
stress+0.430
Neg logit contributions
llah-0.368
ible-0.339
enegger-0.335
 IPM-0.327
esters-0.322
Token going
Token ID1016
Feature activation+1.10e+00

Pos logit contributions
 proport+0.454
 suspic+0.443
 comr+0.392
 fortun+0.372
stress+0.349
Neg logit contributions
llah-0.339
ible-0.315
enegger-0.310
 IPM-0.302
esters-0.299
Token to
Token ID284
Feature activation+1.67e-01

Pos logit contributions
 proport+1.183
 suspic+1.154
 comr+1.038
 fortun+0.994
stress+0.935
Neg logit contributions
llah-0.711
ible-0.659
enegger-0.642
 IPM-0.623
esters-0.620
Token come
Token ID1282
Feature activation-1.17e-01

Pos logit contributions
 proport+0.160
 suspic+0.157
 comr+0.137
 fortun+0.131
stress+0.122
Neg logit contributions
llah-0.129
ible-0.119
enegger-0.117
 IPM-0.115
esters-0.113
Token down
Token ID866
Feature activation+7.22e-01

Pos logit contributions
llah+0.077
ible+0.071
enegger+0.069
esters+0.067
 IPM+0.067
Neg logit contributions
 proport-0.125
 suspic-0.122
 comr-0.109
 fortun-0.104
stress-0.097
Token to
Token ID284
Feature activation+1.29e-02

Pos logit contributions
 proport+0.770
 suspic+0.758
 comr+0.673
 fortun+0.645
stress+0.608
Neg logit contributions
llah-0.476
ible-0.440
enegger-0.428
 IPM-0.417
esters-0.414
Token Hillary
Token ID5073
Feature activation+1.56e+00

Pos logit contributions
 proport+0.013
 suspic+0.012
 comr+0.011
 fortun+0.010
stress+0.010
Neg logit contributions
llah-0.010
ible-0.009
enegger-0.009
 IPM-0.009
osal-0.008
Token Clinton
Token ID2605
Feature activation+2.00e+00

Pos logit contributions
 proport+1.438
 suspic+1.403
 comr+1.221
 fortun+1.163
stress+1.079
Neg logit contributions
llah-1.259
ible-1.171
enegger-1.160
 IPM-1.135
esters-1.122
Token booth
Token ID18600
Feature activation+1.68e+00

Pos logit contributions
llah+0.957
ible+0.885
enegger+0.862
 IPM+0.839
cible+0.829
Neg logit contributions
 proport-1.418
 suspic-1.379
 comr-1.222
 fortun-1.173
��-1.100
Token,
Token ID11
Feature activation+3.67e-01

Pos logit contributions
 proport+1.657
 suspic+1.618
 comr+1.420
 fortun+1.360
stress+1.271
Neg logit contributions
llah-1.243
ible-1.146
enegger-1.141
 IPM-1.107
esters-1.095
Token Bour
Token ID20576
Feature activation+3.35e-01

Pos logit contributions
 proport+0.365
 suspic+0.355
 comr+0.312
 fortun+0.299
stress+0.279
Neg logit contributions
llah-0.272
ible-0.251
enegger-0.249
 IPM-0.243
esters-0.239
Tokendain
Token ID27162
Feature activation-7.04e-01

Pos logit contributions
 proport+0.337
 suspic+0.332
 comr+0.295
 fortun+0.284
stress+0.278
Neg logit contributions
llah-0.225
ible-0.205
enegger-0.205
 IPM-0.203
esters-0.197
Token puts
Token ID7584
Feature activation+9.78e-01

Pos logit contributions
llah+0.536
ible+0.498
enegger+0.494
 IPM+0.480
esters+0.476
Neg logit contributions
 proport-0.683
 suspic-0.665
 comr-0.584
 fortun-0.556
stress-0.519
Token on
Token ID319
Feature activation+7.50e-01

Pos logit contributions
 proport+0.964
 suspic+0.938
 comr+0.825
 fortun+0.789
stress+0.735
Neg logit contributions
llah-0.731
ible-0.677
enegger-0.671
 IPM-0.654
esters-0.645
Token a
Token ID257
Feature activation+2.69e-01

Pos logit contributions
 proport+0.701
 suspic+0.682
 comr+0.594
 fortun+0.566
stress+0.525
Neg logit contributions
llah-0.596
ible-0.557
enegger-0.552
 IPM-0.539
esters-0.534
Token pair
Token ID5166
Feature activation+4.07e-01

Pos logit contributions
 proport+0.261
 suspic+0.255
 comr+0.223
 fortun+0.213
stress+0.199
Neg logit contributions
llah-0.203
ible-0.189
enegger-0.187
 IPM-0.182
esters-0.180
Token of
Token ID286
Feature activation+3.07e-01

Pos logit contributions
 proport+0.368
 suspic+0.360
 comr+0.313
 fortun+0.302
stress+0.286
Neg logit contributions
llah-0.326
enegger-0.304
ible-0.300
 IPM-0.292
esters-0.292
Token reading
Token ID3555
Feature activation+1.87e+00

Pos logit contributions
 proport+0.293
 suspic+0.285
 comr+0.249
 fortun+0.238
stress+0.221
Neg logit contributions
llah-0.239
ible-0.223
enegger-0.221
 IPM-0.215
esters-0.212
Token glasses
Token ID15232
Feature activation+1.16e+00

Pos logit contributions
 proport+1.658
 suspic+1.613
 comr+1.391
 fortun+1.322
stress+1.221
Neg logit contributions
llah-1.587
ible-1.487
enegger-1.472
 IPM-1.440
esters-1.427
Token a
Token ID257
Feature activation+4.27e-01

Pos logit contributions
llah+0.907
ible+0.846
enegger+0.842
 IPM+0.819
esters+0.816
Neg logit contributions
 proport-0.947
 suspic-0.920
 comr-0.797
 fortun-0.756
stress-0.697
Token Dream
Token ID7610
Feature activation+1.10e+00

Pos logit contributions
 proport+0.482
 suspic+0.471
 comr+0.422
 fortun+0.406
stress+0.381
Neg logit contributions
llah-0.260
ible-0.235
enegger-0.232
 IPM-0.224
esters-0.222
Token
Token ID1399
Feature activation+3.71e-01

Pos logit contributions
 proport+1.109
 suspic+1.084
 comr+0.954
 fortun+0.915
stress+0.853
Neg logit contributions
llah-0.797
ible-0.735
enegger-0.730
 IPM-0.705
esters-0.699
Token a
Token ID257
Feature activation+1.29e-02

Pos logit contributions
 proport+0.365
 suspic+0.356
 comr+0.313
 fortun+0.299
stress+0.279
Neg logit contributions
llah-0.278
ible-0.257
enegger-0.255
 IPM-0.247
esters-0.245
Token kick
Token ID4829
Feature activation-6.29e-01

Pos logit contributions
 proport+0.013
 suspic+0.012
 comr+0.011
 fortun+0.010
stress+0.010
Neg logit contributions
llah-0.010
ible-0.009
enegger-0.009
 IPM-0.009
esters-0.009
Token-
Token ID12
Feature activation+4.58e-01

Pos logit contributions
llah+0.501
ible+0.467
enegger+0.464
 IPM+0.450
osal+0.445
Neg logit contributions
 proport-0.587
 suspic-0.574
 comr-0.499
 fortun-0.476
stress-0.438
Tokenas
Token ID292
Feature activation+2.26e+00

Pos logit contributions
 proport+0.390
 suspic+0.379
 comr+0.325
 fortun+0.309
stress+0.284
Neg logit contributions
llah-0.404
ible-0.378
enegger-0.376
 IPM-0.366
esters-0.363
Token movie
Token ID3807
Feature activation+2.56e+00

Pos logit contributions
 proport+2.255
 suspic+2.208
 comr+1.939
 fortun+1.861
stress+1.748
Neg logit contributions
llah-1.650
ible-1.505
enegger-1.503
 IPM-1.461
esters-1.442
Token.
Token ID13
Feature activation-5.29e-03

Pos logit contributions
 proport+2.508
 suspic+2.438
 comr+2.139
 fortun+2.049
stress+1.922
Neg logit contributions
llah-1.925
ible-1.769
enegger-1.757
 IPM-1.715
esters-1.700
Token And
Token ID843
Feature activation+6.03e-01

Pos logit contributions
llah+0.004
ible+0.004
enegger+0.004
 IPM+0.004
esters+0.004
Neg logit contributions
 proport-0.005
 suspic-0.005
 comr-0.004
 fortun-0.004
stress-0.004
Token who
Token ID508
Feature activation-1.31e+00

Pos logit contributions
 proport+0.603
 suspic+0.589
 comr+0.518
 fortun+0.496
stress+0.464
Neg logit contributions
llah-0.440
ible-0.406
enegger-0.404
 IPM-0.391
esters-0.387
Token rise
Token ID4485
Feature activation-7.92e-01

Pos logit contributions
llah+0.169
ible+0.158
enegger+0.156
 IPM+0.153
esters+0.151
Neg logit contributions
 proport-0.186
 suspic-0.183
 comr-0.159
 fortun-0.151
stress-0.138
Token,
Token ID11
Feature activation-1.23e-01

Pos logit contributions
llah+0.564
ible+0.526
enegger+0.515
 IPM+0.501
esters+0.497
Neg logit contributions
 proport-0.802
 suspic-0.787
 comr-0.695
 fortun-0.664
stress-0.619
Token that
Token ID326
Feature activation-5.69e-01

Pos logit contributions
llah+0.090
ible+0.083
enegger+0.082
 IPM+0.080
esters+0.079
Neg logit contributions
 proport-0.123
 suspic-0.120
 comr-0.105
 fortun-0.101
stress-0.094
Token's
Token ID338
Feature activation-1.19e+00

Pos logit contributions
llah+0.433
ible+0.406
enegger+0.398
 IPM+0.389
esters+0.386
Neg logit contributions
 proport-0.546
 suspic-0.535
 comr-0.468
 fortun-0.447
��-0.417
Token a
Token ID257
Feature activation-6.82e-02

Pos logit contributions
llah+0.895
ible+0.837
enegger+0.821
 IPM+0.809
esters+0.799
Neg logit contributions
 proport-1.149
 suspic-1.123
 comr-0.986
 fortun-0.940
stress-0.878
Token huge
Token ID3236
Feature activation+2.49e-01

Pos logit contributions
llah+0.054
ible+0.050
enegger+0.049
 IPM+0.048
esters+0.048
Neg logit contributions
 proport-0.064
 suspic-0.062
 comr-0.055
 fortun-0.052
stress-0.048
Token rise
Token ID4485
Feature activation-3.11e-01

Pos logit contributions
 proport+0.246
 suspic+0.241
 comr+0.212
 fortun+0.203
stress+0.189
Neg logit contributions
llah-0.184
ible-0.170
enegger-0.169
 IPM-0.164
esters-0.162
Token,
Token ID11
Feature activation-1.04e-01

Pos logit contributions
llah+0.222
ible+0.205
enegger+0.203
 IPM+0.196
esters+0.194
Neg logit contributions
 proport-0.317
 suspic-0.311
 comr-0.274
 fortun-0.262
stress-0.245
Token if
Token ID611
Feature activation-4.64e-01

Pos logit contributions
llah+0.076
ible+0.070
enegger+0.070
 IPM+0.068
esters+0.067
Neg logit contributions
 proport-0.103
 suspic-0.101
 comr-0.089
 fortun-0.085
stress-0.079
Token you
Token ID345
Feature activation-9.96e-01

Pos logit contributions
llah+0.341
ible+0.316
enegger+0.312
 IPM+0.305
esters+0.300
Neg logit contributions
 proport-0.462
 suspic-0.452
 comr-0.396
 fortun-0.380
stress-0.355
Token think
Token ID892
Feature activation-1.34e+00

Pos logit contributions
llah+0.693
enegger+0.635
ible+0.633
 IPM+0.610
esters+0.605
Neg logit contributions
 proport-1.032
 suspic-1.007
 comr-0.888
 fortun-0.855
stress-0.802
Token have
Token ID423
Feature activation+2.82e-01

Pos logit contributions
 proport+1.492
 suspic+1.455
 comr+1.274
 fortun+1.218
stress+1.137
Neg logit contributions
llah-1.176
ible-1.088
enegger-1.081
 IPM-1.050
esters-1.039
Token deemed
Token ID10762
Feature activation-1.70e+00

Pos logit contributions
 proport+0.270
 suspic+0.263
 comr+0.231
 fortun+0.220
stress+0.205
Neg logit contributions
llah-0.218
ible-0.203
enegger-0.201
 IPM-0.195
esters-0.193
Token UN
Token ID4725
Feature activation+2.22e+00

Pos logit contributions
llah+1.259
ible+1.181
enegger+1.152
osal+1.122
 IPM+1.122
Neg logit contributions
 proport-1.676
 suspic-1.618
 comr-1.432
 fortun-1.376
stress-1.276
TokenFOR
Token ID13775
Feature activation+1.36e+00

Pos logit contributions
 proport+2.202
 suspic+2.159
 comr+1.890
 fortun+1.813
stress+1.698
Neg logit contributions
llah-1.624
ible-1.496
enegger-1.492
 IPM-1.444
esters-1.432
TokenG
Token ID38
Feature activation-1.39e-01

Pos logit contributions
 proport+1.353
 suspic+1.333
 comr+1.157
 fortun+1.123
stress+1.037
Neg logit contributions
llah-1.012
enegger-0.922
ible-0.906
 IPM-0.880
esters-0.879
TokenIV
Token ID3824
Feature activation-1.02e+00

Pos logit contributions
llah+0.100
enegger+0.090
ible+0.089
 IPM+0.087
esters+0.087
Neg logit contributions
 proport-0.142
 suspic-0.140
 comr-0.122
 fortun-0.118
stress-0.110
TokenABLE
Token ID17534
Feature activation-1.52e+00

Pos logit contributions
llah+0.598
enegger+0.535
ible+0.534
 IPM+0.511
esters+0.508
Neg logit contributions
 proport-1.173
 suspic-1.149
 comr-1.029
 fortun-0.993
stress-0.938
Token (
Token ID357
Feature activation-1.17e+00

Pos logit contributions
llah+1.051
ible+0.972
enegger+0.964
 IPM+0.927
osal+0.916
Neg logit contributions
 proport-1.575
 suspic-1.541
 comr-1.365
 fortun-1.302
stress-1.224
Tokenthough
Token ID2016
Feature activation+8.21e-01

Pos logit contributions
llah+1.010
ible+0.945
enegger+0.938
 IPM+0.911
esters+0.908
Neg logit contributions
 proport-1.018
 suspic-0.986
 comr-0.851
 fortun-0.805
stress-0.736
Token that
Token ID326
Feature activation-4.14e-01

Pos logit contributions
 proport+0.832
 suspic+0.812
 comr+0.715
 fortun+0.686
stress+0.642
Neg logit contributions
llah-0.590
ible-0.543
enegger-0.540
 IPM-0.523
esters-0.517
Token hasn
Token ID5818
Feature activation-2.66e-01

Pos logit contributions
llah+0.303
ible+0.280
enegger+0.278
 IPM+0.269
esters+0.266
Neg logit contributions
 proport-0.413
 suspic-0.402
 comr-0.355
 fortun-0.339
stress-0.317
TokenUR
Token ID4261
Feature activation+5.10e-01

Pos logit contributions
 proport+0.835
 suspic+0.812
 comr+0.708
 fortun+0.691
stress+0.649
Neg logit contributions
llah-0.650
enegger-0.610
ible-0.603
cible-0.578
 IPM-0.572
Token --
Token ID1377
Feature activation+1.40e+00

Pos logit contributions
 proport+0.502
 suspic+0.491
 comr+0.431
 fortun+0.410
stress+0.383
Neg logit contributions
llah-0.384
ible-0.354
enegger-0.349
 IPM-0.344
esters-0.336
Token With
Token ID2080
Feature activation+1.93e-01

Pos logit contributions
 proport+1.403
 suspic+1.371
 comr+1.206
 fortun+1.156
stress+1.082
Neg logit contributions
llah-1.013
ible-0.933
enegger-0.927
 IPM-0.899
esters-0.890
Token barely
Token ID8523
Feature activation-3.47e+00

Pos logit contributions
 proport+0.190
 suspic+0.185
 comr+0.163
 fortun+0.155
stress+0.145
Neg logit contributions
llah-0.144
ible-0.133
enegger-0.132
 IPM-0.129
esters-0.127
Token a
Token ID257
Feature activation-1.27e-01

Pos logit contributions
llah+2.677
ible+2.523
enegger+2.453
 IPM+2.448
esters+2.399
Neg logit contributions
 proport-3.271
 suspic-3.176
 comr-2.792
 fortun-2.623
stress-2.469
Token month
Token ID1227
Feature activation-6.36e-01

Pos logit contributions
llah+0.093
ible+0.086
enegger+0.085
 IPM+0.083
esters+0.082
Neg logit contributions
 proport-0.127
 suspic-0.124
 comr-0.109
 fortun-0.104
stress-0.098
Token leading
Token ID3756
Feature activation+1.04e+00

Pos logit contributions
llah+0.384
ible+0.352
enegger+0.345
esters+0.331
 IPM+0.330
Neg logit contributions
 proport-0.718
 suspic-0.704
 comr-0.631
 fortun-0.603
stress-0.569
Token up
Token ID510
Feature activation+2.77e-02

Pos logit contributions
 proport+1.236
 suspic+1.212
 comr+1.088
 fortun+1.052
stress+0.997
Neg logit contributions
llah-0.571
ible-0.509
enegger-0.508
 IPM-0.487
esters-0.476
Token to
Token ID284
Feature activation-3.17e-01

Pos logit contributions
 proport+0.030
 suspic+0.029
 comr+0.026
 fortun+0.025
stress+0.023
Neg logit contributions
llah-0.018
ible-0.017
enegger-0.017
 IPM-0.016
esters-0.016
Token her
Token ID607
Feature activation+1.44e+00

Pos logit contributions
llah+0.240
ible+0.222
enegger+0.219
 IPM+0.214
esters+0.212
Neg logit contributions
 proport-0.311
 suspic-0.303
 comr-0.265
 fortun-0.253
stress-0.237
Token retirement
Token ID10737
Feature activation+8.69e-01

Pos logit contributions
 proport+1.415
 suspic+1.381
 comr+1.211
 fortun+1.161
stress+1.082
Neg logit contributions
llah-1.081
ible-0.998
enegger-0.993
 IPM-0.963
esters-0.955
Token one
Token ID530
Feature activation+5.94e-01

Pos logit contributions
llah+0.362
ible+0.336
enegger+0.333
 IPM+0.324
esters+0.321
Neg logit contributions
 proport-0.481
 suspic-0.469
 comr-0.412
 fortun-0.394
stress-0.370
Token of
Token ID286
Feature activation-1.70e-01

Pos logit contributions
 proport+0.585
 suspic+0.572
 comr+0.503
 fortun+0.480
stress+0.450
Neg logit contributions
llah-0.442
ible-0.411
enegger-0.403
 IPM-0.393
osal-0.390
Token many
Token ID867
Feature activation+3.31e-01

Pos logit contributions
llah+0.129
ible+0.120
enegger+0.119
 IPM+0.116
esters+0.115
Neg logit contributions
 proport-0.165
 suspic-0.161
 comr-0.141
 fortun-0.134
stress-0.125
Token House
Token ID2097
Feature activation+1.04e+00

Pos logit contributions
 proport+0.337
 suspic+0.329
 comr+0.290
 fortun+0.278
stress+0.261
Neg logit contributions
llah-0.236
ible-0.217
enegger-0.215
 IPM-0.209
esters-0.207
Token Democrats
Token ID4956
Feature activation+1.52e+00

Pos logit contributions
 proport+1.055
 suspic+1.030
 comr+0.908
 fortun+0.870
stress+0.814
Neg logit contributions
llah-0.749
ible-0.689
enegger-0.685
 IPM-0.664
esters-0.656
Token to
Token ID284
Feature activation-2.07e-01

Pos logit contributions
 proport+1.548
 suspic+1.513
 comr+1.332
 fortun+1.280
stress+1.197
Neg logit contributions
llah-1.082
ible-0.991
enegger-0.989
 IPM-0.955
osal-0.943
Token vote
Token ID3015
Feature activation-2.12e+00

Pos logit contributions
llah+0.146
ible+0.134
enegger+0.133
 IPM+0.129
esters+0.127
Neg logit contributions
 proport-0.213
 suspic-0.208
 comr-0.184
 fortun-0.177
stress-0.165
Token against
Token ID1028
Feature activation-5.48e-01

Pos logit contributions
llah+1.352
ible+1.237
enegger+1.201
 IPM+1.177
esters+1.159
Neg logit contributions
 proport-2.311
 suspic-2.257
 comr-2.024
 fortun-1.938
stress-1.820
Token the
Token ID262
Feature activation-1.31e-01

Pos logit contributions
llah+0.421
ible+0.394
enegger+0.388
 IPM+0.380
esters+0.376
Neg logit contributions
 proport-0.525
 suspic-0.513
 comr-0.452
 fortun-0.428
stress-0.399
Token bill
Token ID2855
Feature activation-9.51e-01

Pos logit contributions
llah+0.090
ible+0.083
enegger+0.082
 IPM+0.080
esters+0.079
Neg logit contributions
 proport-0.136
 suspic-0.133
 comr-0.117
 fortun-0.113
stress-0.106
Token.
Token ID13
Feature activation+9.07e-02

Pos logit contributions
llah+0.674
ible+0.620
enegger+0.616
 IPM+0.594
esters+0.590
Neg logit contributions
 proport-0.973
 suspic-0.953
 comr-0.842
 fortun-0.806
stress-0.752
Token?
Token ID30
Feature activation-4.80e-01

Pos logit contributions
llah+0.076
ible+0.070
enegger+0.068
 IPM+0.067
esters+0.066
Neg logit contributions
 proport-0.119
 suspic-0.117
 comr-0.103
 fortun-0.099
stress-0.093
Token And
Token ID843
Feature activation+7.97e-01

Pos logit contributions
llah+0.373
ible+0.347
enegger+0.344
 IPM+0.336
esters+0.331
Neg logit contributions
 proport-0.459
 suspic-0.448
 comr-0.391
 fortun-0.372
stress-0.346
Token what
Token ID644
Feature activation-1.73e+00

Pos logit contributions
 proport+0.790
 suspic+0.772
 comr+0.678
 fortun+0.650
stress+0.607
Neg logit contributions
llah-0.590
ible-0.544
enegger-0.541
 IPM-0.524
esters-0.519
Token better
Token ID1365
Feature activation-1.80e+00

Pos logit contributions
llah+0.999
ible+0.917
enegger+0.885
 IPM+0.877
esters+0.865
Neg logit contributions
 proport-1.976
 suspic-1.916
 comr-1.714
 fortun-1.654
��-1.582
Token way
Token ID835
Feature activation-1.14e-01

Pos logit contributions
llah+1.502
ible+1.438
enegger+1.392
 IPM+1.385
osal+1.364
Neg logit contributions
 proport-1.581
 suspic-1.533
 comr-1.313
 fortun-1.243
��-1.165
Token to
Token ID284
Feature activation-3.58e-01

Pos logit contributions
llah+0.074
ible+0.068
enegger+0.067
 IPM+0.065
esters+0.065
Neg logit contributions
 proport-0.122
 suspic-0.119
 comr-0.106
 fortun-0.102
stress-0.095
Token get
Token ID651
Feature activation+7.26e-01

Pos logit contributions
llah+0.260
ible+0.241
enegger+0.237
 IPM+0.232
esters+0.228
Neg logit contributions
 proport-0.361
 suspic-0.352
 comr-0.309
 fortun-0.297
stress-0.276
Token people
Token ID661
Feature activation+9.27e-01

Pos logit contributions
 proport+0.712
 suspic+0.695
 comr+0.608
 fortun+0.582
stress+0.545
Neg logit contributions
llah-0.543
ible-0.505
enegger-0.499
 IPM-0.487
esters-0.480
Token to
Token ID284
Feature activation-4.96e-02

Pos logit contributions
 proport+0.944
 suspic+0.921
 comr+0.813
 fortun+0.779
stress+0.729
Neg logit contributions
llah-0.661
ible-0.612
enegger-0.603
 IPM-0.587
esters-0.580
Token pay
Token ID1414
Feature activation-3.47e-01

Pos logit contributions
llah+0.035
ible+0.032
enegger+0.032
 IPM+0.031
esters+0.030
Neg logit contributions
 proport-0.051
 suspic-0.050
 comr-0.044
 fortun-0.042
stress-0.040
Token attention
Token ID3241
Feature activation+1.91e+00

Pos logit contributions
llah+0.365
ible+0.348
enegger+0.344
 IPM+0.338
esters+0.335
Neg logit contributions
 proport-0.236
 suspic-0.226
 comr-0.187
 fortun-0.174
��-0.155
Token natural
Token ID3288
Feature activation+3.40e-01

Pos logit contributions
 proport+0.761
 suspic+0.743
 comr+0.652
 fortun+0.624
stress+0.581
Neg logit contributions
llah-0.592
ible-0.547
enegger-0.544
 IPM-0.528
esters-0.522
Token enemy
Token ID4472
Feature activation+1.93e+00

Pos logit contributions
 proport+0.310
 suspic+0.302
 comr+0.262
 fortun+0.250
stress+0.232
Neg logit contributions
llah-0.279
ible-0.260
enegger-0.258
 IPM-0.251
esters-0.249
Token,
Token ID11
Feature activation-1.48e-01

Pos logit contributions
 proport+1.907
 suspic+1.864
 comr+1.637
 fortun+1.571
stress+1.467
Neg logit contributions
llah-1.430
ible-1.319
enegger-1.314
 IPM-1.275
esters-1.261
Token the
Token ID262
Feature activation-6.83e-01

Pos logit contributions
llah+0.113
ible+0.105
enegger+0.103
 IPM+0.101
esters+0.100
Neg logit contributions
 proport-0.144
 suspic-0.140
 comr-0.123
 fortun-0.116
stress-0.109
Token British
Token ID3517
Feature activation-1.66e+00

Pos logit contributions
llah+0.470
ible+0.434
enegger+0.427
 IPM+0.417
esters+0.409
Neg logit contributions
 proport-0.711
 suspic-0.692
 comr-0.613
 fortun-0.582
stress-0.553
Token crown
Token ID12389
Feature activation-2.55e+00

Pos logit contributions
llah+1.222
ible+1.139
enegger+1.121
 IPM+1.105
esters+1.071
Neg logit contributions
 proport-1.631
 suspic-1.598
 comr-1.400
 fortun-1.334
stress-1.255
Token,
Token ID11
Feature activation-3.21e-01

Pos logit contributions
llah+1.906
ible+1.793
enegger+1.742
 IPM+1.702
osal+1.665
Neg logit contributions
 proport-2.498
 suspic-2.446
 comr-2.127
 fortun-2.035
stress-1.899
Token to
Token ID284
Feature activation-8.93e-01

Pos logit contributions
llah+0.229
ible+0.211
enegger+0.209
 IPM+0.203
esters+0.201
Neg logit contributions
 proport-0.327
 suspic-0.319
 comr-0.282
 fortun-0.269
stress-0.253
Token defeat
Token ID7433
Feature activation-8.41e-01

Pos logit contributions
llah+0.648
ible+0.597
enegger+0.591
 IPM+0.574
esters+0.568
Neg logit contributions
 proport-0.900
 suspic-0.878
 comr-0.773
 fortun-0.741
stress-0.693
Token a
Token ID257
Feature activation-2.54e-01

Pos logit contributions
llah+0.624
ible+0.579
enegger+0.569
 IPM+0.557
esters+0.548
Neg logit contributions
 proport-0.836
 suspic-0.811
 comr-0.716
 fortun-0.679
stress-0.638
Token greater
Token ID3744
Feature activation-5.34e-01

Pos logit contributions
llah+0.183
ible+0.170
enegger+0.166
 IPM+0.163
esters+0.160
Neg logit contributions
 proport-0.255
 suspic-0.248
 comr-0.220
 fortun-0.208
stress-0.197
Token of
Token ID286
Feature activation-3.33e-02

Pos logit contributions
llah+1.347
ible+1.250
enegger+1.213
 IPM+1.190
esters+1.188
Neg logit contributions
 proport-1.869
 suspic-1.836
 comr-1.595
 fortun-1.533
stress-1.426
Token the
Token ID262
Feature activation-5.34e-04

Pos logit contributions
llah+0.025
ible+0.023
enegger+0.023
 IPM+0.023
esters+0.023
Neg logit contributions
 proport-0.032
 suspic-0.031
 comr-0.027
 fortun-0.026
stress-0.025
Token D
Token ID360
Feature activation-3.89e-01

Pos logit contributions
llah+0.000
ible+0.000
enegger+0.000
 IPM+0.000
esters+0.000
Neg logit contributions
 proport-0.001
 suspic-0.001
 comr-0.000
 fortun-0.000
stress-0.000
Token-
Token ID12
Feature activation+4.81e-02

Pos logit contributions
llah+0.287
ible+0.268
enegger+0.259
 IPM+0.256
esters+0.255
Neg logit contributions
 proport-0.389
 suspic-0.380
 comr-0.332
 fortun-0.317
stress-0.294
TokenDay
Token ID12393
Feature activation-6.53e-01

Pos logit contributions
 proport+0.053
 suspic+0.053
 comr+0.046
 fortun+0.045
stress+0.042
Neg logit contributions
llah-0.030
ible-0.028
enegger-0.027
esters-0.027
cible-0.026
Token land
Token ID1956
Feature activation-4.64e+00

Pos logit contributions
llah+0.348
ible+0.319
 IPM+0.305
enegger+0.299
esters+0.295
Neg logit contributions
 proport-0.779
 suspic-0.766
 comr-0.687
 fortun-0.661
stress-0.623
Tokenings
Token ID654
Feature activation-1.47e+00

Pos logit contributions
llah+1.897
ible+1.762
osal+1.542
cible+1.536
esters+1.496
Neg logit contributions
 proport-6.019
 suspic-5.987
 comr-5.458
 fortun-5.273
��-4.968
Token.
Token ID13
Feature activation+1.00e-01

Pos logit contributions
llah+1.002
ible+0.934
enegger+0.912
 IPM+0.888
osal+0.881
Neg logit contributions
 proport-1.528
 suspic-1.502
 comr-1.329
 fortun-1.270
stress-1.181
Token
Token ID198
Feature activation-4.90e-01

Pos logit contributions
 proport+0.103
 suspic+0.101
 comr+0.089
 fortun+0.085
stress+0.079
Neg logit contributions
llah-0.071
ible-0.065
enegger-0.065
 IPM-0.062
esters-0.062
Token
Token ID198
Feature activation-1.68e-01

Pos logit contributions
llah+0.384
enegger+0.359
ible+0.350
 IPM+0.342
esters+0.341
Neg logit contributions
 proport-0.442
 suspic-0.431
 comr-0.377
 fortun-0.367
stress-0.355
TokenThe
Token ID464
Feature activation+2.51e-01

Pos logit contributions
llah+0.128
ible+0.119
enegger+0.118
 IPM+0.115
esters+0.114
Neg logit contributions
 proport-0.164
 suspic-0.159
 comr-0.139
 fortun-0.133
stress-0.123
Token,
Token ID11
Feature activation-2.88e-01

Pos logit contributions
llah+3.427
ible+3.090
enegger+2.968
cible+2.885
osal+2.878
Neg logit contributions
 proport-5.505
 suspic-5.451
 comr-4.854
 fortun-4.628
stress-4.350
Token Gh
Token ID11972
Feature activation-5.99e+00

Pos logit contributions
llah+0.198
ible+0.182
enegger+0.180
 IPM+0.175
esters+0.173
Neg logit contributions
 proport-0.301
 suspic-0.294
 comr-0.260
 fortun-0.250
stress-0.235
Tokenout
Token ID448
Feature activation+2.53e-01

Pos logit contributions
llah+4.532
ible+4.456
osal+4.316
raq+4.171
obic+4.159
Neg logit contributions
 proport-5.807
 suspic-5.657
 comr-5.044
 fortun-4.682
��-4.304
Tokena
Token ID64
Feature activation+6.33e-01

Pos logit contributions
 proport+0.230
 suspic+0.224
 comr+0.194
 fortun+0.185
stress+0.172
Neg logit contributions
llah-0.208
ible-0.193
enegger-0.192
 IPM-0.187
esters-0.186
Token,
Token ID11
Feature activation-4.74e-01

Pos logit contributions
 proport+0.643
 suspic+0.629
 comr+0.554
 fortun+0.531
stress+0.497
Neg logit contributions
llah-0.454
ible-0.417
enegger-0.414
 IPM-0.401
esters-0.397
Token Damascus
Token ID21028
Feature activation-4.72e+00

Pos logit contributions
llah+0.332
ible+0.305
enegger+0.303
 IPM+0.293
esters+0.290
Neg logit contributions
 proport-0.488
 suspic-0.477
 comr-0.421
 fortun-0.404
stress-0.379
Token,
Token ID11
Feature activation-4.74e-01

Pos logit contributions
llah+3.137
ible+2.824
enegger+2.753
 IPM+2.658
esters+2.654
Neg logit contributions
 proport-4.993
 suspic-4.898
 comr-4.363
 fortun-4.173
stress-3.918
Token A
Token ID317
Feature activation-1.09e+00

Pos logit contributions
llah+0.324
ible+0.297
enegger+0.294
 IPM+0.285
esters+0.281
Neg logit contributions
 proport-0.497
 suspic-0.487
 comr-0.430
 fortun-0.413
stress-0.387
Tokenby
Token ID1525
Feature activation+1.85e+00

Pos logit contributions
llah+0.721
ible+0.663
enegger+0.637
osal+0.621
 IPM+0.620
Neg logit contributions
 proport-1.171
 suspic-1.154
 comr-1.021
 fortun-0.974
stress-0.915
Tokenan
Token ID272
Feature activation-3.04e-01

Pos logit contributions
 proport+1.661
 suspic+1.618
 comr+1.399
 fortun+1.339
stress+1.243
Neg logit contributions
llah-1.525
enegger-1.420
ible-1.418
 IPM-1.384
esters-1.364
Token,
Token ID11
Feature activation-4.17e-01

Pos logit contributions
llah+0.217
ible+0.199
enegger+0.196
 IPM+0.190
esters+0.188
Neg logit contributions
 proport-0.311
 suspic-0.304
 comr-0.269
 fortun-0.257
stress-0.240
TokenED
Token ID1961
Feature activation+8.43e-02

Pos logit contributions
 proport+0.535
 suspic+0.521
 comr+0.456
 fortun+0.435
stress+0.404
Neg logit contributions
llah-0.428
ible-0.397
enegger-0.394
 IPM-0.383
esters-0.379
TokenMON
Token ID27857
Feature activation-5.96e-01

Pos logit contributions
 proport+0.090
 suspic+0.088
 comr+0.079
 fortun+0.076
stress+0.071
Neg logit contributions
llah-0.055
ible-0.051
enegger-0.050
 IPM-0.049
esters-0.048
TokenTON
Token ID11357
Feature activation-2.86e+00

Pos logit contributions
llah+0.177
ible+0.142
enegger+0.140
 IPM+0.128
esters+0.124
Neg logit contributions
 proport-0.856
 suspic-0.842
 comr-0.772
 fortun-0.750
stress-0.718
Token
Token ID784
Feature activation+4.67e-01

Pos logit contributions
llah+2.076
ible+1.944
enegger+1.909
 IPM+1.882
esters+1.833
Neg logit contributions
 proport-2.859
 suspic-2.799
 comr-2.458
 fortun-2.327
stress-2.175
Token Omar
Token ID24980
Feature activation-1.70e+00

Pos logit contributions
 proport+0.440
 suspic+0.430
 comr+0.374
 fortun+0.357
stress+0.331
Neg logit contributions
llah-0.370
ible-0.344
enegger-0.342
 IPM-0.333
esters-0.329
Token Kh
Token ID5311
Feature activation-4.44e+00

Pos logit contributions
llah+1.165
ible+1.073
enegger+1.035
 IPM+1.006
osal+1.006
Neg logit contributions
 proport-1.784
 suspic-1.762
 comr-1.548
 fortun-1.485
stress-1.394
Tokenadr
Token ID41909
Feature activation-4.34e+00

Pos logit contributions
llah+3.294
ible+3.179
obic+2.947
osal+2.917
enegger+2.911
Neg logit contributions
 proport-4.506
 suspic-4.406
 comr-3.886
 fortun-3.612
��-3.327
Token has
Token ID468
Feature activation+3.79e-01

Pos logit contributions
llah+2.980
ible+2.747
enegger+2.714
 IPM+2.613
esters+2.592
Neg logit contributions
 proport-4.459
 suspic-4.321
 comr-3.851
 fortun-3.638
��-3.451
Token agreed
Token ID4987
Feature activation-1.09e+00

Pos logit contributions
 proport+0.372
 suspic+0.363
 comr+0.318
 fortun+0.304
stress+0.284
Neg logit contributions
llah-0.285
ible-0.263
enegger-0.262
 IPM-0.254
esters-0.251
Token to
Token ID284
Feature activation-2.77e-01

Pos logit contributions
llah+0.703
ible+0.651
enegger+0.632
 IPM+0.613
esters+0.605
Neg logit contributions
 proport-1.182
 suspic-1.153
 comr-1.022
 fortun-0.986
stress-0.925
Token remain
Token ID3520
Feature activation-2.88e+00

Pos logit contributions
llah+0.209
ible+0.194
enegger+0.192
 IPM+0.187
esters+0.185
Neg logit contributions
 proport-0.271
 suspic-0.265
 comr-0.232
 fortun-0.222
stress-0.207
Tokenathing
Token ID26927
Feature activation-1.27e+00

Pos logit contributions
llah+0.057
ible+0.053
enegger+0.053
 IPM+0.051
esters+0.051
Neg logit contributions
 proport-0.062
 suspic-0.061
 comr-0.052
 fortun-0.050
stress-0.046
Token system
Token ID1080
Feature activation-4.58e-01

Pos logit contributions
llah+0.942
ible+0.870
enegger+0.853
 IPM+0.836
osal+0.827
Neg logit contributions
 proport-1.250
 suspic-1.224
 comr-1.075
 fortun-1.030
stress-0.962
Token used
Token ID973
Feature activation+8.00e-01

Pos logit contributions
llah+0.329
ible+0.303
enegger+0.300
 IPM+0.292
esters+0.288
Neg logit contributions
 proport-0.463
 suspic-0.453
 comr-0.399
 fortun-0.383
stress-0.358
Token by
Token ID416
Feature activation+1.10e+00

Pos logit contributions
 proport+0.766
 suspic+0.748
 comr+0.653
 fortun+0.625
stress+0.582
Neg logit contributions
llah-0.619
ible-0.573
enegger-0.570
 IPM-0.554
esters-0.548
Token the
Token ID262
Feature activation-2.73e-01

Pos logit contributions
 proport+1.076
 suspic+1.050
 comr+0.920
 fortun+0.881
stress+0.822
Neg logit contributions
llah-0.831
ible-0.768
enegger-0.763
 IPM-0.741
esters-0.733
Token Mau
Token ID28931
Feature activation-5.00e+00

Pos logit contributions
llah+0.200
ible+0.185
enegger+0.183
 IPM+0.179
esters+0.176
Neg logit contributions
 proport-0.272
 suspic-0.265
 comr-0.233
 fortun-0.223
stress-0.210
Token Mau
Token ID28931
Feature activation-5.30e+00

Pos logit contributions
llah+1.845
ible+1.518
 IPM+1.441
esters+1.347
osal+1.315
Neg logit contributions
 proport-6.719
 suspic-6.650
 comr-6.068
 fortun-5.926
stress-5.684
Token,
Token ID11
Feature activation-3.64e-01

Pos logit contributions
llah+3.519
ible+3.198
 IPM+3.080
enegger+3.077
esters+3.054
Neg logit contributions
 proport-5.509
 suspic-5.460
 comr-4.843
 fortun-4.645
stress-4.355
Token and
Token ID290
Feature activation-3.98e-01

Pos logit contributions
llah+0.258
ible+0.237
enegger+0.235
 IPM+0.228
esters+0.226
Neg logit contributions
 proport-0.372
 suspic-0.363
 comr-0.320
 fortun-0.307
stress-0.288
Token denied
Token ID6699
Feature activation-9.38e-01

Pos logit contributions
llah+0.283
ible+0.261
enegger+0.258
 IPM+0.251
esters+0.248
Neg logit contributions
 proport-0.405
 suspic-0.396
 comr-0.349
 fortun-0.334
stress-0.314
Token having
Token ID1719
Feature activation-5.59e-01

Pos logit contributions
llah+0.701
ible+0.650
enegger+0.635
 IPM+0.627
esters+0.618
Neg logit contributions
 proport-0.917
 suspic-0.895
 comr-0.788
 fortun-0.750
stress-0.708
Token
Token ID198
Feature activation-7.62e-01

Pos logit contributions
llah+0.478
ible+0.443
enegger+0.438
 IPM+0.427
esters+0.421
Neg logit contributions
 proport-0.629
 suspic-0.615
 comr-0.539
 fortun-0.514
stress-0.478
Token
Token ID198
Feature activation-4.00e-01

Pos logit contributions
llah+0.595
enegger+0.556
ible+0.543
 IPM+0.531
esters+0.529
Neg logit contributions
 proport-0.691
 suspic-0.675
 comr-0.589
 fortun-0.574
stress-0.553
Token@
Token ID31
Feature activation-1.15e+00

Pos logit contributions
llah+0.306
ible+0.283
enegger+0.281
 IPM+0.273
esters+0.270
Neg logit contributions
 proport-0.388
 suspic-0.378
 comr-0.331
 fortun-0.316
stress-0.295
TokenAnn
Token ID18858
Feature activation+1.18e+00

Pos logit contributions
llah+0.848
ible+0.783
enegger+0.767
 IPM+0.752
esters+0.744
Neg logit contributions
 proport-1.152
 suspic-1.121
 comr-0.983
 fortun-0.941
stress-0.872
TokenC
Token ID34
Feature activation-6.88e-01

Pos logit contributions
 proport+1.138
 suspic+1.111
 comr+0.971
 fortun+0.928
stress+0.864
Neg logit contributions
llah-0.906
ible-0.839
enegger-0.833
 IPM-0.809
esters-0.802
Tokenoul
Token ID2852
Feature activation-4.41e+00

Pos logit contributions
llah+0.543
ible+0.504
enegger+0.499
 IPM+0.484
esters+0.482
Neg logit contributions
 proport-0.653
 suspic-0.636
 comr-0.555
 fortun-0.530
stress-0.491
Tokenter
Token ID353
Feature activation-1.04e+00

Pos logit contributions
llah+3.729
ible+3.546
enegger+3.425
esters+3.417
osal+3.364
Neg logit contributions
 proport-3.914
 suspic-3.788
 comr-3.326
 fortun-3.078
��-2.826
Token HAVE
Token ID21515
Feature activation-9.96e-01

Pos logit contributions
llah+0.771
ible+0.713
enegger+0.709
 IPM+0.685
esters+0.678
Neg logit contributions
 proport-1.040
 suspic-1.014
 comr-0.891
 fortun-0.848
stress-0.791
Token YOU
Token ID7013
Feature activation+4.43e-01

Pos logit contributions
llah+0.728
ible+0.670
enegger+0.665
 IPM+0.647
esters+0.637
Neg logit contributions
 proport-0.998
 suspic-0.975
 comr-0.857
 fortun-0.821
stress-0.768
Token SE
Token ID7946
Feature activation-9.11e-01

Pos logit contributions
 proport+0.467
 suspic+0.457
 comr+0.405
 fortun+0.389
stress+0.365
Neg logit contributions
llah-0.300
ible-0.274
enegger-0.272
 IPM-0.263
esters-0.261
TokenEN
Token ID1677
Feature activation+1.45e+00

Pos logit contributions
llah+0.525
ible+0.474
enegger+0.465
 IPM+0.454
osal+0.440
Neg logit contributions
 proport-1.053
 suspic-1.034
 comr-0.926
 fortun-0.890
stress-0.843