TOP ACTIVATIONS
MAX = 3.815

government faces aboriginal opposition to Kinder Morgan s Trans
a white , straight , cis g endered , American man
also features unusual men 's ur inals in the shape of
of self to others as masculine , feminine , both ,
dinner at El Gau cho , Erik Johnson grabbed
people to use the proper bathroom , saying ,
the story begins Cur iously , that
45 366 . Topics : community - and -
into them ". Topics : marine - biology ,
to appear at his university disciplinary hearing . He contends their
Tweet Subscribe via RSS or daily email Contact the
students to access co - cur ricular activities to supplement their
hard core " and more masculine . Through this decade or
similar range , such as Alpha Delta Phi ($ 400 per
, who had scored a hat - tr ick , and
racial , religious or sexual slur , quick to lose a
When Gu cc ifer 2 . 0 took credit
appeared to be a grease pencil ." " As
News 24 . Topics : beef - c attle
Committee . F emin ist groups financed include the

MIN ACTIVATIONS
MIN = -2.929

, Great Depression <|endoftext|> W ALTH AM , Mass . --
do is to determine how much R FI is being generated
Stella didn 't know how much it had worsened , didn
2 - 3 ). The general - circ ulation models ,
s younger brother Vin od , brother - in
, but there is not much I can do . As
that the reference to Sh av iv ( 2008 ) should
121 months . On the flip side , there seems to
would have created just too much tension , knowing you were
on just to see how much R FI is getting into
not a backup system . Rest ores are a non -
of the two . Not much fun to go to the
don 't ever really see much about the past there .
manually keep track of how much text can go in each
said Drew T . Sh ind ell , professor of climate
s silly . Not much to grasp at here
transparent ly to you . Rest assured , the techn ologists
It would have created just too much tension , knowing you
them the size of my thumb ). Now throw it on
the fans were not missing much action , with the conditions

INTERVAL 2.129 - 3.815
CONTAINS 0.034%

federal government . Er n est o Gal ar
Sciences in Memory of Alfred Nobel , founder of the Nobel
, who had scored a hat - tr ick , and
, the intersection of Y onge and E gl inton will
red and yellow peppers , cour get tes , basil and

INTERVAL 0.443 - 2.129
CONTAINS 15.699%

).[ 188 ] The party with majority support in the House
the earth from Armenia , Arts akh , and Jav
s micro circuitry it is not impossible . It is also
unsupported on your device Media caption Prof Re iner R umm
he said . Something s going to

INTERVAL -1.243 - 0.443
CONTAINS 82.867%

when D NR biologists take groups of people to dens during
Government should immediately bring amendments to the present Motor Vehicle Act
users to install and remove . MS I exclusive Un locked
, the powerful set their seal on
Morning . 16 W . Madison St . Baltimore , MD

INTERVAL -2.929 - -1.243
CONTAINS 1.399%

In reality the photo was taken by Reuters in
It also means that all law students , regardless of their
support Clinton . Back during the early parts of
о р я и
FI is getting into the radio . The following is a
Token government
Token ID1230
Feature activation+5.32e-02

Pos logit contributions
rolet+0.154
orth+0.148
oppy+0.140
 NTS+0.136
olls+0.134
Neg logit contributions
xual-0.168
 menstru-0.155
Bir-0.145
20439-0.142
pees-0.141
Token faces
Token ID6698
Feature activation-7.84e-01

Pos logit contributions
xual+0.120
 menstru+0.114
Bir+0.106
pees+0.104
 ferment+0.103
Neg logit contributions
rolet-0.099
orth-0.095
oppy-0.088
 NTS-0.084
olls-0.084
Token aboriginal
Token ID48328
Feature activation+6.66e-01

Pos logit contributions
rolet+1.470
orth+1.415
oppy+1.323
 NTS+1.286
olls+1.284
Neg logit contributions
xual-1.737
 menstru-1.602
Bir-1.520
pees-1.488
20439-1.479
Token opposition
Token ID5471
Feature activation+3.35e-01

Pos logit contributions
xual+1.426
 menstru+1.344
Bir+1.247
pees+1.220
 ferment+1.219
Neg logit contributions
rolet-1.320
orth-1.265
oppy-1.194
olls-1.128
 NTS-1.125
Token to
Token ID284
Feature activation-8.93e-02

Pos logit contributions
xual+0.768
 menstru+0.730
Bir+0.680
 ferment+0.666
pees+0.666
Neg logit contributions
rolet-0.611
orth-0.582
oppy-0.546
olls-0.515
 NTS-0.513
Token Kinder
Token ID46832
Feature activation+3.82e+00

Pos logit contributions
rolet+0.178
orth+0.172
oppy+0.162
olls+0.156
 NTS+0.155
Neg logit contributions
xual-0.191
 menstru-0.176
Bir-0.165
20439-0.160
pees-0.160
Token Morgan
Token ID10805
Feature activation+3.40e-01

Pos logit contributions
xual+7.745
 menstru+7.684
Bir+7.178
 ferment+6.941
pees+6.915
Neg logit contributions
rolet-7.459
orth-6.949
oppy-6.599
olls-6.250
rays-6.241
Token
Token ID447
Feature activation-3.04e-01

Pos logit contributions
xual+0.729
 menstru+0.681
Bir+0.630
pees+0.619
20439+0.617
Neg logit contributions
rolet-0.677
orth-0.654
oppy-0.616
olls-0.584
 NTS-0.584
Token
Token ID247
Feature activation-1.01e-01

Pos logit contributions
rolet+0.745
orth+0.720
oppy+0.686
olls+0.662
rays+0.661
Neg logit contributions
xual-0.498
 menstru-0.465
Bir-0.413
 ferment-0.412
20439-0.402
Tokens
Token ID82
Feature activation-1.29e-01

Pos logit contributions
rolet+0.181
orth+0.179
oppy+0.163
 NTS+0.156
rays+0.154
Neg logit contributions
xual-0.233
 menstru-0.222
Bir-0.205
 ferment-0.203
20439-0.202
Token Trans
Token ID3602
Feature activation+1.20e+00

Pos logit contributions
rolet+0.246
orth+0.238
oppy+0.224
olls+0.215
 NTS+0.213
Neg logit contributions
xual-0.289
 menstru-0.265
Bir-0.248
pees-0.244
20439-0.244
Token a
Token ID257
Feature activation+6.12e-01

Pos logit contributions
rolet+0.702
orth+0.686
oppy+0.642
 NTS+0.624
rays+0.609
Neg logit contributions
xual-0.746
 menstru-0.685
Bir-0.643
pees-0.637
20439-0.632
Token white
Token ID2330
Feature activation+4.35e-01

Pos logit contributions
xual+1.279
 menstru+1.202
Bir+1.112
pees+1.100
20439+1.097
Neg logit contributions
rolet-1.234
orth-1.183
oppy-1.120
 NTS-1.064
olls-1.058
Token,
Token ID11
Feature activation+3.88e-01

Pos logit contributions
xual+0.839
 menstru+0.784
Bir+0.722
pees+0.714
20439+0.712
Neg logit contributions
rolet-0.942
orth-0.912
oppy-0.866
 NTS-0.829
olls-0.814
Token straight
Token ID3892
Feature activation+9.49e-01

Pos logit contributions
xual+0.728
 menstru+0.673
Bir+0.624
pees+0.616
20439+0.615
Neg logit contributions
rolet-0.863
orth-0.837
oppy-0.792
 NTS-0.763
olls-0.751
Token,
Token ID11
Feature activation+1.07e-01

Pos logit contributions
xual+1.911
 menstru+1.798
Bir+1.656
pees+1.626
 ferment+1.624
Neg logit contributions
rolet-1.993
orth-1.915
oppy-1.814
 NTS-1.717
olls-1.715
Token cis
Token ID33325
Feature activation+3.32e+00

Pos logit contributions
xual+0.205
 menstru+0.188
Bir+0.176
20439+0.174
pees+0.174
Neg logit contributions
rolet-0.233
orth-0.227
oppy-0.214
 NTS-0.207
olls-0.202
Tokeng
Token ID70
Feature activation+3.70e-01

Pos logit contributions
xual+6.633
 menstru+6.231
Bir+5.678
 ferment+5.587
pees+5.477
Neg logit contributions
rolet-6.959
orth-6.536
oppy-6.343
olls-6.095
 NTS-5.909
Tokenendered
Token ID30398
Feature activation+1.90e+00

Pos logit contributions
xual+0.532
 menstru+0.487
Bir+0.429
pees+0.428
 ferment+0.418
Neg logit contributions
rolet-0.993
orth-0.972
oppy-0.924
olls-0.882
 NTS-0.880
Token,
Token ID11
Feature activation+2.55e-01

Pos logit contributions
xual+3.691
 menstru+3.484
Bir+3.187
 ferment+3.130
pees+3.097
Neg logit contributions
rolet-4.140
orth-3.947
oppy-3.768
olls-3.575
 NTS-3.543
Token American
Token ID1605
Feature activation-5.77e-02

Pos logit contributions
xual+0.478
 menstru+0.441
Bir+0.410
pees+0.405
20439+0.403
Neg logit contributions
rolet-0.564
orth-0.549
oppy-0.518
 NTS-0.499
olls-0.490
Token man
Token ID582
Feature activation+7.62e-01

Pos logit contributions
rolet+0.122
orth+0.119
oppy+0.112
 NTS+0.108
igl+0.106
Neg logit contributions
xual-0.112
 menstru-0.106
Bir-0.097
pees-0.097
20439-0.096
Token also
Token ID635
Feature activation+6.45e-01

Pos logit contributions
xual+0.796
 menstru+0.752
Bir+0.701
20439+0.697
pees+0.687
Neg logit contributions
rolet-0.615
orth-0.590
oppy-0.549
olls-0.520
rays-0.513
Token features
Token ID3033
Feature activation+9.21e-01

Pos logit contributions
xual+1.376
 menstru+1.282
Bir+1.198
20439+1.192
pees+1.173
Neg logit contributions
rolet-1.283
orth-1.244
oppy-1.160
olls-1.108
rays-1.100
Token unusual
Token ID8468
Feature activation+2.09e-01

Pos logit contributions
xual+1.906
 menstru+1.793
Bir+1.655
pees+1.621
 ferment+1.617
Neg logit contributions
rolet-1.894
orth-1.814
oppy-1.721
olls-1.627
 NTS-1.620
Token men
Token ID1450
Feature activation+1.15e+00

Pos logit contributions
xual+0.425
 menstru+0.393
Bir+0.364
20439+0.360
pees+0.357
Neg logit contributions
rolet-0.438
orth-0.423
oppy-0.402
olls-0.380
 NTS-0.377
Token's
Token ID338
Feature activation-6.96e-02

Pos logit contributions
xual+2.266
 menstru+2.143
Bir+1.958
 ferment+1.933
pees+1.928
Neg logit contributions
rolet-2.449
orth-2.333
oppy-2.215
 NTS-2.103
olls-2.100
Token ur
Token ID2956
Feature activation+3.16e+00

Pos logit contributions
rolet+0.142
orth+0.137
oppy+0.131
olls+0.123
 NTS+0.121
Neg logit contributions
xual-0.145
 menstru-0.132
Bir-0.124
20439-0.123
pees-0.121
Tokeninals
Token ID6897
Feature activation+5.30e-01

Pos logit contributions
xual+4.896
 menstru+4.473
pees+4.187
Bir+4.038
 ferment+3.926
Neg logit contributions
rolet-7.902
orth-7.529
oppy-7.256
 NTS-6.924
olls-6.853
Token in
Token ID287
Feature activation+4.33e-01

Pos logit contributions
xual+1.220
 menstru+1.157
Bir+1.080
20439+1.058
pees+1.055
Neg logit contributions
rolet-0.962
orth-0.920
oppy-0.863
olls-0.812
 NTS-0.806
Token the
Token ID262
Feature activation+2.95e-01

Pos logit contributions
xual+0.905
 menstru+0.844
Bir+0.787
20439+0.778
pees+0.770
Neg logit contributions
rolet-0.869
orth-0.841
oppy-0.800
 NTS-0.754
olls-0.751
Token shape
Token ID5485
Feature activation+1.38e+00

Pos logit contributions
xual+0.636
 menstru+0.589
Bir+0.552
20439+0.551
pees+0.544
Neg logit contributions
rolet-0.576
orth-0.557
oppy-0.529
 NTS-0.499
olls-0.497
Token of
Token ID286
Feature activation-1.40e-01

Pos logit contributions
xual+3.489
 menstru+3.340
Bir+3.127
 ferment+3.085
pees+3.069
Neg logit contributions
rolet-2.205
orth-2.065
oppy-1.929
olls-1.782
 NTS-1.769
Token of
Token ID286
Feature activation-3.76e-01

Pos logit contributions
rolet+0.474
orth+0.444
oppy+0.417
olls+0.388
 NTS+0.385
Neg logit contributions
xual-0.702
 menstru-0.669
Bir-0.624
 ferment-0.616
pees-0.611
Token self
Token ID2116
Feature activation-4.20e-01

Pos logit contributions
orth+0.722
rolet+0.714
oppy+0.668
olls+0.646
 NTS+0.641
Neg logit contributions
xual-0.778
 menstru-0.717
Bir-0.697
20439-0.692
pees-0.688
Token to
Token ID284
Feature activation+3.07e-01

Pos logit contributions
rolet+0.723
orth+0.700
oppy+0.645
olls+0.607
rays+0.605
Neg logit contributions
xual-0.988
 menstru-0.940
Bir-0.886
pees-0.874
20439-0.868
Token others
Token ID1854
Feature activation+3.56e-01

Pos logit contributions
xual+0.635
 menstru+0.592
Bir+0.564
pees+0.552
20439+0.550
Neg logit contributions
rolet-0.615
orth-0.603
oppy-0.560
olls-0.536
rays-0.530
Token as
Token ID355
Feature activation+1.39e-01

Pos logit contributions
xual+0.833
 menstru+0.791
Bir+0.746
pees+0.734
 ferment+0.728
Neg logit contributions
rolet-0.625
orth-0.600
oppy-0.557
olls-0.525
 NTS-0.522
Token masculine
Token ID27543
Feature activation+2.94e+00

Pos logit contributions
xual+0.248
 menstru+0.226
Bir+0.214
pees+0.214
20439+0.210
Neg logit contributions
rolet-0.314
orth-0.309
oppy-0.291
 NTS-0.282
olls-0.280
Token,
Token ID11
Feature activation+1.65e-01

Pos logit contributions
xual+6.175
 menstru+5.757
Bir+5.209
 ferment+5.191
pees+5.057
Neg logit contributions
rolet-5.993
orth-5.521
oppy-5.412
olls-5.029
 NTS-4.989
Token feminine
Token ID23564
Feature activation+1.71e+00

Pos logit contributions
xual+0.244
 menstru+0.222
Bir+0.202
pees+0.199
20439+0.195
Neg logit contributions
rolet-0.430
orth-0.419
oppy-0.397
rays-0.382
olls-0.381
Token,
Token ID11
Feature activation+1.68e-01

Pos logit contributions
xual+3.549
 menstru+3.366
 ferment+3.036
Bir+3.009
tur+2.923
Neg logit contributions
rolet-3.538
orth-3.276
oppy-3.172
olls-3.005
 NTS-2.956
Token both
Token ID1111
Feature activation-3.38e-02

Pos logit contributions
xual+0.335
 menstru+0.310
Bir+0.292
pees+0.290
20439+0.288
Neg logit contributions
rolet-0.351
orth-0.343
oppy-0.322
 NTS-0.306
rays-0.305
Token,
Token ID11
Feature activation+4.38e-02

Pos logit contributions
rolet+0.063
orth+0.060
oppy+0.056
olls+0.053
 NTS+0.053
Neg logit contributions
xual-0.075
 menstru-0.071
Bir-0.067
pees-0.066
20439-0.065
Token
Token ID447
Feature activation-7.54e-02

Pos logit contributions
rolet+1.083
orth+1.038
oppy+0.977
olls+0.921
 NTS+0.919
Neg logit contributions
xual-1.181
 menstru-1.109
Bir-1.032
pees-1.015
20439-1.013
Token
Token ID247
Feature activation+2.53e-01

Pos logit contributions
rolet+0.195
orth+0.188
oppy+0.181
olls+0.174
rays+0.173
Neg logit contributions
xual-0.114
 menstru-0.105
Bir-0.094
20439-0.092
 ferment-0.092
Token dinner
Token ID8073
Feature activation+3.67e-01

Pos logit contributions
xual+0.529
 menstru+0.500
Bir+0.462
 ferment+0.454
pees+0.452
Neg logit contributions
rolet-0.514
orth-0.490
oppy-0.465
olls-0.439
 NTS-0.437
Token at
Token ID379
Feature activation-3.95e-02

Pos logit contributions
xual+0.816
 menstru+0.774
Bir+0.719
 ferment+0.706
pees+0.704
Neg logit contributions
rolet-0.698
orth-0.664
oppy-0.627
olls-0.589
 NTS-0.587
Token El
Token ID2574
Feature activation+1.77e+00

Pos logit contributions
rolet+0.077
orth+0.073
oppy+0.069
olls+0.065
 NTS+0.065
Neg logit contributions
xual-0.087
 menstru-0.082
Bir-0.076
pees-0.074
20439-0.074
Token Gau
Token ID35094
Feature activation+2.86e+00

Pos logit contributions
xual+3.898
 menstru+3.740
Bir+3.518
 ferment+3.430
pees+3.428
Neg logit contributions
rolet-3.263
orth-3.065
oppy-2.923
 NTS-2.734
olls-2.731
Tokencho
Token ID6679
Feature activation-1.46e-01

Pos logit contributions
xual+4.879
 menstru+4.712
Bir+4.287
pees+4.243
 ferment+4.211
Neg logit contributions
rolet-6.533
orth-6.349
oppy-6.165
olls-5.800
 NTS-5.723
Token,
Token ID11
Feature activation-1.42e-01

Pos logit contributions
rolet+0.271
orth+0.261
oppy+0.243
olls+0.230
 NTS+0.230
Neg logit contributions
xual-0.328
 menstru-0.310
Bir-0.289
20439-0.285
pees-0.283
Token Erik
Token ID22722
Feature activation-1.98e-01

Pos logit contributions
rolet+0.274
orth+0.261
oppy+0.247
 NTS+0.233
olls+0.231
Neg logit contributions
xual-0.312
 menstru-0.294
Bir-0.274
pees-0.269
20439-0.267
Token Johnson
Token ID5030
Feature activation+7.31e-02

Pos logit contributions
rolet+0.368
orth+0.352
oppy+0.331
olls+0.311
 NTS+0.308
Neg logit contributions
xual-0.451
 menstru-0.426
Bir-0.394
20439-0.390
pees-0.390
Token grabbed
Token ID13176
Feature activation-5.23e-01

Pos logit contributions
xual+0.166
 menstru+0.157
Bir+0.146
 ferment+0.144
pees+0.144
Neg logit contributions
rolet-0.135
orth-0.129
oppy-0.121
olls-0.114
 NTS-0.113
Token people
Token ID661
Feature activation+5.78e-01

Pos logit contributions
xual+2.544
 menstru+2.391
Bir+2.172
 ferment+2.125
pees+2.117
Neg logit contributions
rolet-3.274
orth-3.140
oppy-3.001
olls-2.851
 NTS-2.843
Token to
Token ID284
Feature activation+4.34e-01

Pos logit contributions
xual+1.298
 menstru+1.231
Bir+1.144
 ferment+1.125
pees+1.122
Neg logit contributions
rolet-1.084
orth-1.031
oppy-0.972
olls-0.913
 NTS-0.909
Token use
Token ID779
Feature activation-2.05e-01

Pos logit contributions
xual+0.981
 menstru+0.897
Bir+0.858
20439+0.857
pees+0.843
Neg logit contributions
rolet-0.807
orth-0.771
oppy-0.719
olls-0.689
 NTS-0.680
Token the
Token ID262
Feature activation-6.25e-02

Pos logit contributions
rolet+0.428
orth+0.413
oppy+0.390
olls+0.376
 NTS+0.375
Neg logit contributions
xual-0.415
 menstru-0.380
Bir-0.356
20439-0.351
 ferment-0.351
Token proper
Token ID1774
Feature activation+8.12e-01

Pos logit contributions
rolet+0.133
orth+0.128
oppy+0.122
 NTS+0.117
olls+0.116
Neg logit contributions
xual-0.124
 menstru-0.114
Bir-0.106
pees-0.105
 ferment-0.104
Token bathroom
Token ID12436
Feature activation+2.84e+00

Pos logit contributions
xual+1.495
 menstru+1.386
Bir+1.267
 ferment+1.243
pees+1.243
Neg logit contributions
rolet-1.853
orth-1.784
oppy-1.701
olls-1.620
 NTS-1.620
Token,
Token ID11
Feature activation-6.33e-02

Pos logit contributions
xual+6.125
 menstru+5.951
Bir+5.428
pees+5.361
 ferment+5.352
Neg logit contributions
rolet-5.439
orth-5.041
oppy-4.872
rays-4.475
 NTS-4.458
Token saying
Token ID2282
Feature activation-1.28e-01

Pos logit contributions
rolet+0.114
orth+0.110
oppy+0.103
 NTS+0.098
olls+0.096
Neg logit contributions
xual-0.145
 menstru-0.134
Bir-0.127
pees-0.125
20439-0.125
Token,
Token ID11
Feature activation-2.58e-01

Pos logit contributions
rolet+0.238
orth+0.226
oppy+0.213
 NTS+0.202
olls+0.202
Neg logit contributions
xual-0.287
 menstru-0.267
Bir-0.252
pees-0.250
 ferment-0.248
Token
Token ID564
Feature activation+8.27e-02

Pos logit contributions
rolet+0.566
orth+0.543
oppy+0.518
olls+0.490
 NTS+0.487
Neg logit contributions
xual-0.499
 menstru-0.472
Bir-0.431
 ferment-0.421
pees-0.419
Token
Token ID250
Feature activation-3.33e-01

Pos logit contributions
xual+0.167
 menstru+0.156
Bir+0.141
 ferment+0.141
pees+0.139
Neg logit contributions
rolet-0.175
orth-0.167
oppy-0.159
olls-0.150
 NTS-0.149
Token the
Token ID262
Feature activation+1.57e-01

Pos logit contributions
xual+1.930
 menstru+1.823
Bir+1.689
 ferment+1.657
pees+1.655
Neg logit contributions
rolet-1.805
orth-1.727
oppy-1.636
olls-1.543
 NTS-1.542
Token story
Token ID1621
Feature activation+1.52e-01

Pos logit contributions
xual+0.355
 menstru+0.336
Bir+0.314
pees+0.308
20439+0.308
Neg logit contributions
rolet-0.289
orth-0.276
oppy-0.260
 NTS-0.247
olls-0.245
Token begins
Token ID6140
Feature activation-3.07e-01

Pos logit contributions
xual+0.344
 menstru+0.324
Bir+0.304
20439+0.296
pees+0.295
Neg logit contributions
rolet-0.280
orth-0.270
oppy-0.255
 NTS-0.240
olls-0.239
Token
Token ID198
Feature activation+1.16e-01

Pos logit contributions
rolet+0.540
orth+0.512
oppy+0.479
 NTS+0.452
olls+0.450
Neg logit contributions
xual-0.725
 menstru-0.685
Bir-0.642
pees-0.631
20439-0.629
Token
Token ID198
Feature activation+2.07e-01

Pos logit contributions
xual+0.274
 menstru+0.257
pees+0.237
 ferment+0.236
Bir+0.236
Neg logit contributions
rolet-0.208
orth-0.200
oppy-0.186
 NTS-0.176
olls-0.175
TokenCur
Token ID26628
Feature activation+2.74e+00

Pos logit contributions
xual+0.431
 menstru+0.401
 ferment+0.365
Bir+0.361
pees+0.360
Neg logit contributions
rolet-0.429
orth-0.415
oppy-0.391
olls-0.370
rays-0.369
Tokeniously
Token ID6819
Feature activation+1.48e+00

Pos logit contributions
xual+4.340
 menstru+4.036
Bir+3.622
pees+3.565
 ferment+3.498
Neg logit contributions
rolet-6.797
orth-6.451
oppy-6.218
 NTS-5.979
olls-5.925
Token,
Token ID11
Feature activation+1.15e-01

Pos logit contributions
xual+2.868
 menstru+2.718
Bir+2.475
 ferment+2.426
pees+2.407
Neg logit contributions
rolet-3.198
orth-3.034
oppy-2.903
olls-2.760
 NTS-2.725
Token that
Token ID326
Feature activation+1.01e-01

Pos logit contributions
xual+0.251
 menstru+0.236
Bir+0.220
20439+0.217
 ferment+0.217
Neg logit contributions
rolet-0.219
orth-0.211
oppy-0.200
 NTS-0.190
olls-0.189
Token
Token ID447
Feature activation+4.72e-01

Pos logit contributions
xual+0.222
 menstru+0.207
Bir+0.193
pees+0.191
20439+0.190
Neg logit contributions
rolet-0.194
orth-0.187
oppy-0.176
olls-0.166
 NTS-0.166
Token
Token ID247
Feature activation+5.81e-01

Pos logit contributions
xual+0.680
 menstru+0.626
Bir+0.554
 ferment+0.538
pees+0.537
Neg logit contributions
rolet-1.267
orth-1.223
oppy-1.176
olls-1.127
 NTS-1.122
Token45
Token ID2231
Feature activation+3.44e-01

Pos logit contributions
rolet+0.636
orth+0.622
oppy+0.577
 NTS+0.559
olls+0.555
Neg logit contributions
xual-0.670
 menstru-0.632
pees-0.574
 ferment-0.573
Bir-0.561
Token 366
Token ID44856
Feature activation+1.11e+00

Pos logit contributions
xual+0.715
 menstru+0.675
Bir+0.621
pees+0.615
 ferment+0.612
Neg logit contributions
rolet-0.700
orth-0.674
oppy-0.634
 NTS-0.606
olls-0.604
Token.
Token ID13
Feature activation+4.79e-01

Pos logit contributions
xual+2.493
 menstru+2.368
Bir+2.198
 ferment+2.162
pees+2.151
Neg logit contributions
rolet-2.089
orth-1.980
oppy-1.875
olls-1.752
 NTS-1.744
Token
Token ID198
Feature activation+5.94e-02

Pos logit contributions
xual+1.015
 menstru+0.961
Bir+0.891
 ferment+0.871
pees+0.867
Neg logit contributions
rolet-0.959
orth-0.912
oppy-0.866
olls-0.812
 NTS-0.811
Token
Token ID198
Feature activation+1.66e-01

Pos logit contributions
xual+0.142
 menstru+0.132
pees+0.123
 ferment+0.122
Bir+0.122
Neg logit contributions
rolet-0.104
orth-0.101
oppy-0.093
 NTS-0.088
olls-0.088
TokenTopics
Token ID25902
Feature activation+2.73e+00

Pos logit contributions
xual+0.331
 menstru+0.310
 ferment+0.281
Bir+0.281
pees+0.278
Neg logit contributions
rolet-0.355
orth-0.344
oppy-0.325
olls-0.310
rays-0.307
Token:
Token ID25
Feature activation+1.03e+00

Pos logit contributions
xual+5.674
 menstru+5.436
Bir+5.013
 ferment+4.872
20439+4.815
Neg logit contributions
rolet-5.479
orth-5.096
oppy-4.967
olls-4.639
 NTS-4.545
Token community
Token ID2055
Feature activation-2.50e-01

Pos logit contributions
xual+2.119
 menstru+2.011
Bir+1.846
 ferment+1.818
pees+1.802
Neg logit contributions
rolet-2.136
orth-2.035
oppy-1.937
olls-1.825
 NTS-1.820
Token-
Token ID12
Feature activation+1.83e-01

Pos logit contributions
rolet+0.394
orth+0.379
oppy+0.349
olls+0.328
rays+0.321
Neg logit contributions
xual-0.635
 menstru-0.597
Bir-0.563
20439-0.559
pees-0.557
Tokenand
Token ID392
Feature activation-9.14e-02

Pos logit contributions
xual+0.389
 menstru+0.367
Bir+0.340
 ferment+0.333
20439+0.331
Neg logit contributions
rolet-0.363
orth-0.350
oppy-0.330
olls-0.312
rays-0.308
Token-
Token ID12
Feature activation+5.15e-01

Pos logit contributions
rolet+0.146
orth+0.140
oppy+0.129
olls+0.120
 NTS+0.118
Neg logit contributions
xual-0.230
 menstru-0.218
Bir-0.205
pees-0.202
20439-0.202
Token into
Token ID656
Feature activation+9.38e-01

Pos logit contributions
xual+0.091
 menstru+0.085
Bir+0.081
pees+0.080
20439+0.080
Neg logit contributions
rolet-0.066
orth-0.063
oppy-0.059
 NTS-0.056
olls-0.056
Token them
Token ID606
Feature activation-1.39e-01

Pos logit contributions
xual+1.885
 menstru+1.759
Bir+1.627
pees+1.597
20439+1.591
Neg logit contributions
rolet-1.983
orth-1.903
oppy-1.810
olls-1.721
 NTS-1.716
Token".
Token ID1911
Feature activation+5.07e-02

Pos logit contributions
rolet+0.235
orth+0.223
oppy+0.208
olls+0.196
 NTS+0.194
Neg logit contributions
xual-0.337
 menstru-0.320
Bir-0.302
pees-0.296
20439-0.294
Token
Token ID198
Feature activation+1.82e-01

Pos logit contributions
xual+0.117
 menstru+0.111
Bir+0.103
 ferment+0.102
pees+0.102
Neg logit contributions
rolet-0.092
orth-0.089
oppy-0.082
olls-0.078
 NTS-0.078
Token
Token ID198
Feature activation+2.00e-01

Pos logit contributions
xual+0.428
 menstru+0.401
pees+0.371
 ferment+0.369
Bir+0.369
Neg logit contributions
rolet-0.325
orth-0.314
oppy-0.291
 NTS-0.275
olls-0.273
TokenTopics
Token ID25902
Feature activation+2.70e+00

Pos logit contributions
xual+0.440
 menstru+0.416
Bir+0.383
 ferment+0.379
pees+0.378
Neg logit contributions
rolet-0.384
orth-0.367
oppy-0.346
olls-0.326
 NTS-0.324
Token:
Token ID25
Feature activation+9.53e-01

Pos logit contributions
xual+5.568
 menstru+5.336
Bir+4.934
 ferment+4.780
20439+4.736
Neg logit contributions
rolet-5.447
orth-5.068
oppy-4.945
olls-4.626
rays-4.508
Token marine
Token ID16050
Feature activation-7.21e-01

Pos logit contributions
xual+1.934
 menstru+1.845
Bir+1.679
 ferment+1.663
pees+1.638
Neg logit contributions
rolet-1.991
orth-1.892
oppy-1.803
olls-1.694
 NTS-1.683
Token-
Token ID12
Feature activation+1.30e-01

Pos logit contributions
rolet+1.303
orth+1.225
oppy+1.174
olls+1.094
 NTS+1.094
Neg logit contributions
xual-1.645
 menstru-1.592
Bir-1.467
 ferment-1.456
pees-1.427
Tokenbiology
Token ID43592
Feature activation-1.05e+00

Pos logit contributions
xual+0.309
 menstru+0.295
Bir+0.274
 ferment+0.270
pees+0.269
Neg logit contributions
rolet-0.229
orth-0.215
oppy-0.203
 NTS-0.189
olls-0.189
Token,
Token ID11
Feature activation+1.12e-01

Pos logit contributions
rolet+1.687
orth+1.665
oppy+1.511
olls+1.422
 NTS+1.422
Neg logit contributions
xual-2.602
 menstru-2.439
Bir-2.323
20439-2.285
pees-2.273
Token to
Token ID284
Feature activation+2.25e-02

Pos logit contributions
xual+0.540
 menstru+0.520
Bir+0.472
 ferment+0.466
pees+0.465
Neg logit contributions
rolet-0.489
orth-0.464
oppy-0.436
olls-0.412
 NTS-0.410
Token appear
Token ID1656
Feature activation-1.26e-01

Pos logit contributions
xual+0.050
 menstru+0.045
20439+0.044
Bir+0.044
pees+0.043
Neg logit contributions
rolet-0.043
orth-0.041
oppy-0.039
 NTS-0.037
olls-0.036
Token at
Token ID379
Feature activation-7.14e-01

Pos logit contributions
rolet+0.222
orth+0.215
oppy+0.200
olls+0.187
 NTS+0.187
Neg logit contributions
xual-0.295
 menstru-0.273
Bir-0.260
20439-0.258
pees-0.256
Token his
Token ID465
Feature activation-3.02e-01

Pos logit contributions
rolet+1.376
orth+1.321
oppy+1.257
 NTS+1.186
olls+1.183
Neg logit contributions
xual-1.560
 menstru-1.442
Bir-1.351
20439-1.336
pees-1.331
Token university
Token ID6403
Feature activation+5.00e-01

Pos logit contributions
rolet+0.523
orth+0.505
oppy+0.476
 NTS+0.448
olls+0.441
Neg logit contributions
xual-0.723
 menstru-0.663
20439-0.628
pees-0.626
Bir-0.625
Token disciplinary
Token ID24737
Feature activation+2.70e+00

Pos logit contributions
xual+1.105
 menstru+1.042
Bir+0.969
pees+0.953
 ferment+0.952
Neg logit contributions
rolet-0.954
orth-0.916
oppy-0.862
olls-0.809
 NTS-0.809
Token hearing
Token ID4854
Feature activation+9.44e-01

Pos logit contributions
xual+5.234
 menstru+5.220
 ferment+4.765
Bir+4.711
tur+4.534
Neg logit contributions
rolet-5.652
orth-5.235
oppy-5.028
olls-4.743
rays-4.696
Token.
Token ID13
Feature activation-1.51e-01

Pos logit contributions
xual+2.196
 menstru+2.091
Bir+1.945
 ferment+1.915
pees+1.907
Neg logit contributions
rolet-1.697
orth-1.605
oppy-1.513
olls-1.416
 NTS-1.405
Token He
Token ID679
Feature activation-5.37e-01

Pos logit contributions
rolet+0.280
orth+0.267
oppy+0.251
 NTS+0.241
olls+0.235
Neg logit contributions
xual-0.343
 menstru-0.324
 ferment-0.297
pees-0.297
Bir-0.297
Token contends
Token ID33799
Feature activation-5.96e-01

Pos logit contributions
rolet+0.960
orth+0.924
oppy+0.863
olls+0.821
rays+0.819
Neg logit contributions
xual-1.238
 menstru-1.144
Bir-1.087
20439-1.085
pees-1.056
Token their
Token ID511
Feature activation+3.01e-01

Pos logit contributions
rolet+1.040
orth+1.005
oppy+0.956
 NTS+0.921
rays+0.895
Neg logit contributions
xual-1.370
 menstru-1.268
Bir-1.209
pees-1.208
20439-1.200
TokenTweet
Token ID47845
Feature activation+6.50e-01

Pos logit contributions
xual+0.117
 menstru+0.110
Bir+0.100
 ferment+0.100
pees+0.099
Neg logit contributions
rolet-0.114
orth-0.110
oppy-0.103
olls-0.098
 NTS-0.097
Token
Token ID198
Feature activation+1.69e-01

Pos logit contributions
xual+1.387
 menstru+1.314
Bir+1.216
 ferment+1.197
pees+1.187
Neg logit contributions
rolet-1.283
orth-1.225
oppy-1.167
olls-1.092
 NTS-1.087
Token
Token ID198
Feature activation+3.11e-01

Pos logit contributions
xual+0.397
 menstru+0.373
pees+0.343
 ferment+0.342
Bir+0.342
Neg logit contributions
rolet-0.302
orth-0.291
oppy-0.270
 NTS-0.256
olls-0.255
TokenSubscribe
Token ID27125
Feature activation+1.72e+00

Pos logit contributions
xual+0.628
 menstru+0.592
Bir+0.543
 ferment+0.535
pees+0.532
Neg logit contributions
rolet-0.655
orth-0.628
oppy-0.595
olls-0.564
 NTS-0.561
Token via
Token ID2884
Feature activation+5.82e-01

Pos logit contributions
xual+3.577
 menstru+3.410
Bir+3.177
 ferment+3.116
pees+3.065
Neg logit contributions
rolet-3.406
orth-3.240
oppy-3.110
olls-2.905
rays-2.898
Token RSS
Token ID25012
Feature activation+2.69e+00

Pos logit contributions
xual+0.856
 menstru+0.794
Bir+0.705
 ferment+0.686
pees+0.680
Neg logit contributions
rolet-1.536
orth-1.481
oppy-1.426
olls-1.364
 NTS-1.359
Token or
Token ID393
Feature activation-6.06e-01

Pos logit contributions
xual+5.244
 menstru+5.029
Bir+4.685
 ferment+4.638
20439+4.546
Neg logit contributions
rolet-5.529
orth-5.289
oppy-5.003
 NTS-4.714
olls-4.688
Token daily
Token ID4445
Feature activation+1.08e+00

Pos logit contributions
rolet+1.164
orth+1.103
oppy+1.031
olls+0.987
 NTS+0.982
Neg logit contributions
xual-1.350
 menstru-1.264
Bir-1.175
pees-1.164
 ferment-1.147
Token email
Token ID3053
Feature activation+6.01e-01

Pos logit contributions
xual+2.434
 menstru+2.324
Bir+2.157
 ferment+2.127
pees+2.112
Neg logit contributions
rolet-1.995
orth-1.895
oppy-1.789
olls-1.676
 NTS-1.666
Token Contact
Token ID14039
Feature activation+3.18e-01

Pos logit contributions
xual+1.347
 menstru+1.277
Bir+1.186
 ferment+1.166
pees+1.163
Neg logit contributions
rolet-1.131
orth-1.076
oppy-1.015
olls-0.953
 NTS-0.950
Token the
Token ID262
Feature activation+1.06e-01

Pos logit contributions
xual+0.671
 menstru+0.636
Bir+0.588
 ferment+0.578
pees+0.574
Neg logit contributions
rolet-0.637
orth-0.609
oppy-0.577
olls-0.545
 NTS-0.540
Token students
Token ID2444
Feature activation+2.91e-01

Pos logit contributions
xual+0.687
 menstru+0.649
Bir+0.606
20439+0.599
pees+0.598
Neg logit contributions
rolet-0.507
orth-0.486
oppy-0.454
 NTS-0.430
olls-0.426
Token to
Token ID284
Feature activation+1.57e-01

Pos logit contributions
xual+0.660
 menstru+0.626
Bir+0.582
 ferment+0.572
pees+0.571
Neg logit contributions
rolet-0.539
orth-0.513
oppy-0.483
olls-0.452
 NTS-0.452
Token access
Token ID1895
Feature activation-3.05e-01

Pos logit contributions
xual+0.343
 menstru+0.314
20439+0.302
Bir+0.301
pees+0.295
Neg logit contributions
rolet-0.303
orth-0.290
oppy-0.270
 NTS-0.261
olls-0.256
Token co
Token ID763
Feature activation-7.98e-01

Pos logit contributions
rolet+0.591
orth+0.574
oppy+0.538
 NTS+0.519
olls+0.509
Neg logit contributions
xual-0.655
 menstru-0.614
Bir-0.571
20439-0.567
pees-0.560
Token-
Token ID12
Feature activation+7.03e-01

Pos logit contributions
rolet+1.352
orth+1.299
oppy+1.201
 NTS+1.115
olls+1.113
Neg logit contributions
xual-1.932
 menstru-1.839
Bir-1.704
 ferment-1.687
20439-1.679
Tokencur
Token ID22019
Feature activation+2.69e+00

Pos logit contributions
xual+1.433
 menstru+1.353
Bir+1.247
 ferment+1.223
pees+1.219
Neg logit contributions
rolet-1.462
orth-1.395
oppy-1.326
olls-1.253
 NTS-1.248
Tokenricular
Token ID41001
Feature activation+1.27e+00

Pos logit contributions
xual+5.200
 menstru+4.908
Bir+4.545
pees+4.458
 ferment+4.433
Neg logit contributions
rolet-5.736
orth-5.451
oppy-5.237
olls-4.940
 NTS-4.916
Token activities
Token ID4568
Feature activation+5.23e-01

Pos logit contributions
xual+2.723
 menstru+2.583
Bir+2.391
 ferment+2.350
pees+2.337
Neg logit contributions
rolet-2.498
orth-2.376
oppy-2.253
olls-2.121
 NTS-2.108
Token to
Token ID284
Feature activation+8.87e-02

Pos logit contributions
xual+1.217
 menstru+1.155
Bir+1.078
pees+1.061
 ferment+1.056
Neg logit contributions
rolet-0.935
orth-0.892
oppy-0.834
 NTS-0.787
olls-0.780
Token supplement
Token ID10327
Feature activation-6.65e-02

Pos logit contributions
xual+0.194
 menstru+0.179
Bir+0.170
20439+0.168
pees+0.166
Neg logit contributions
rolet-0.171
orth-0.165
oppy-0.154
 NTS-0.148
olls-0.145
Token their
Token ID511
Feature activation-6.60e-02

Pos logit contributions
rolet+0.145
orth+0.141
oppy+0.134
 NTS+0.128
olls+0.127
Neg logit contributions
xual-0.127
 menstru-0.119
Bir-0.110
20439-0.108
pees-0.107
Tokenhard
Token ID10424
Feature activation-8.72e-01

Pos logit contributions
xual+0.312
 menstru+0.293
Bir+0.267
 ferment+0.266
20439+0.264
Neg logit contributions
rolet-0.314
orth-0.305
oppy-0.286
rays-0.270
olls-0.270
Tokencore
Token ID7295
Feature activation-2.59e-01

Pos logit contributions
rolet+1.491
orth+1.425
oppy+1.330
 NTS+1.230
olls+1.226
Neg logit contributions
xual-2.091
 menstru-1.986
Bir-1.846
pees-1.833
20439-1.821
Token"
Token ID1
Feature activation+8.93e-02

Pos logit contributions
rolet+0.428
orth+0.413
oppy+0.383
 NTS+0.356
rays+0.353
Neg logit contributions
xual-0.627
 menstru-0.600
Bir-0.564
pees-0.560
20439-0.559
Token and
Token ID290
Feature activation+2.34e-01

Pos logit contributions
xual+0.204
 menstru+0.194
Bir+0.182
20439+0.180
pees+0.180
Neg logit contributions
rolet-0.160
orth-0.155
oppy-0.145
 NTS-0.137
olls-0.135
Token more
Token ID517
Feature activation+4.99e-01

Pos logit contributions
xual+0.503
 menstru+0.470
Bir+0.441
pees+0.440
20439+0.434
Neg logit contributions
rolet-0.455
orth-0.442
oppy-0.415
 NTS-0.395
olls-0.389
Token masculine
Token ID27543
Feature activation+2.66e+00

Pos logit contributions
xual+1.073
 menstru+1.008
Bir+0.940
pees+0.931
20439+0.924
Neg logit contributions
rolet-0.978
orth-0.943
oppy-0.886
 NTS-0.841
olls-0.831
Token.
Token ID13
Feature activation+2.09e-01

Pos logit contributions
xual+5.805
 menstru+5.486
 ferment+5.055
Bir+4.994
pees+4.886
Neg logit contributions
rolet-5.145
orth-4.813
oppy-4.583
olls-4.300
 NTS-4.249
Token Through
Token ID9561
Feature activation+2.64e-01

Pos logit contributions
xual+0.464
 menstru+0.441
pees+0.405
Bir+0.404
 ferment+0.402
Neg logit contributions
rolet-0.396
orth-0.382
oppy-0.359
 NTS-0.345
olls-0.336
Token this
Token ID428
Feature activation+3.47e-01

Pos logit contributions
xual+0.546
 menstru+0.513
Bir+0.482
pees+0.475
20439+0.472
Neg logit contributions
rolet-0.537
orth-0.515
oppy-0.491
olls-0.462
 NTS-0.462
Token decade
Token ID5707
Feature activation+7.84e-01

Pos logit contributions
xual+0.766
 menstru+0.714
Bir+0.673
pees+0.672
20439+0.662
Neg logit contributions
rolet-0.656
orth-0.633
oppy-0.601
 NTS-0.566
olls-0.559
Token or
Token ID393
Feature activation-7.75e-01

Pos logit contributions
xual+1.757
 menstru+1.667
Bir+1.551
 ferment+1.522
pees+1.520
Neg logit contributions
rolet-1.474
orth-1.403
oppy-1.325
olls-1.242
 NTS-1.239
Token similar
Token ID2092
Feature activation-6.63e-01

Pos logit contributions
xual+0.627
 menstru+0.586
Bir+0.545
20439+0.538
pees+0.536
Neg logit contributions
rolet-0.586
orth-0.563
oppy-0.533
 NTS-0.507
olls-0.502
Token range
Token ID2837
Feature activation+3.76e-01

Pos logit contributions
rolet+1.131
orth+1.080
oppy+1.008
 NTS+0.961
olls+0.934
Neg logit contributions
xual-1.601
 menstru-1.496
20439-1.413
Bir-1.412
pees-1.393
Token,
Token ID11
Feature activation+8.38e-02

Pos logit contributions
xual+0.854
 menstru+0.811
Bir+0.753
 ferment+0.742
pees+0.738
Neg logit contributions
rolet-0.693
orth-0.658
oppy-0.624
olls-0.580
 NTS-0.578
Token such
Token ID884
Feature activation-2.34e-01

Pos logit contributions
xual+0.193
 menstru+0.183
Bir+0.170
 ferment+0.168
pees+0.167
Neg logit contributions
rolet-0.152
orth-0.145
oppy-0.136
olls-0.128
 NTS-0.128
Token as
Token ID355
Feature activation-1.24e-01

Pos logit contributions
rolet+0.361
orth+0.344
oppy+0.318
 NTS+0.298
olls+0.297
Neg logit contributions
xual-0.600
 menstru-0.567
Bir-0.533
pees-0.528
20439-0.526
Token Alpha
Token ID12995
Feature activation+2.65e+00

Pos logit contributions
rolet+0.235
orth+0.225
oppy+0.212
 NTS+0.201
olls+0.199
Neg logit contributions
xual-0.275
 menstru-0.258
Bir-0.241
 ferment-0.236
20439-0.235
Token Delta
Token ID16978
Feature activation+1.69e+00

Pos logit contributions
xual+5.528
 menstru+5.243
Bir+4.898
 ferment+4.790
pees+4.750
Neg logit contributions
rolet-5.345
orth-4.961
oppy-4.780
olls-4.495
rays-4.423
Token Phi
Token ID47256
Feature activation+1.83e+00

Pos logit contributions
xual+3.714
 menstru+3.529
Bir+3.268
pees+3.210
 ferment+3.210
Neg logit contributions
rolet-3.255
orth-3.057
oppy-2.918
olls-2.735
rays-2.708
Token ($
Token ID7198
Feature activation-4.03e-01

Pos logit contributions
xual+3.966
 menstru+3.794
Bir+3.514
pees+3.456
 ferment+3.438
Neg logit contributions
rolet-3.507
orth-3.303
oppy-3.159
olls-2.955
rays-2.925
Token400
Token ID7029
Feature activation+7.45e-02

Pos logit contributions
rolet+0.953
orth+0.927
oppy+0.873
olls+0.840
rays+0.837
Neg logit contributions
xual-0.707
 menstru-0.666
 ferment-0.594
Bir-0.582
pees-0.574
Token per
Token ID583
Feature activation+5.57e-01

Pos logit contributions
xual+0.184
 menstru+0.175
Bir+0.164
 ferment+0.161
pees+0.161
Neg logit contributions
rolet-0.123
orth-0.116
oppy-0.109
olls-0.101
 NTS-0.101
Token,
Token ID11
Feature activation+6.34e-02

Pos logit contributions
rolet+0.821
orth+0.782
oppy+0.727
olls+0.690
 NTS+0.677
Neg logit contributions
xual-1.038
 menstru-0.972
Bir-0.907
pees-0.894
20439-0.892
Token who
Token ID508
Feature activation-8.77e-01

Pos logit contributions
xual+0.140
 menstru+0.131
Bir+0.122
pees+0.121
20439+0.120
Neg logit contributions
rolet-0.121
orth-0.117
oppy-0.110
 NTS-0.103
olls-0.103
Token had
Token ID550
Feature activation+1.09e-01

Pos logit contributions
rolet+1.618
orth+1.580
oppy+1.461
olls+1.401
 NTS+1.369
Neg logit contributions
xual-1.988
 menstru-1.817
20439-1.720
Bir-1.717
pees-1.703
Token scored
Token ID7781
Feature activation+1.32e+00

Pos logit contributions
xual+0.236
 menstru+0.220
Bir+0.206
20439+0.203
pees+0.203
Neg logit contributions
rolet-0.212
orth-0.204
oppy-0.192
olls-0.182
 NTS-0.182
Token a
Token ID257
Feature activation+9.80e-03

Pos logit contributions
xual+2.731
 menstru+2.572
Bir+2.374
pees+2.325
 ferment+2.323
Neg logit contributions
rolet-2.725
orth-2.609
oppy-2.475
olls-2.341
 NTS-2.336
Token hat
Token ID6877
Feature activation+2.65e+00

Pos logit contributions
xual+0.022
 menstru+0.021
Bir+0.019
pees+0.019
20439+0.019
Neg logit contributions
rolet-0.018
orth-0.018
oppy-0.017
olls-0.016
 NTS-0.016
Token-
Token ID12
Feature activation-2.95e-01

Pos logit contributions
xual+5.875
 menstru+5.588
Bir+5.250
 ferment+5.163
pees+5.121
Neg logit contributions
rolet-4.868
orth-4.564
oppy-4.367
olls-4.126
 NTS-4.117
Tokentr
Token ID2213
Feature activation-3.05e-02

Pos logit contributions
rolet+0.649
orth+0.629
oppy+0.592
olls+0.560
rays+0.559
Neg logit contributions
xual-0.573
 menstru-0.538
Bir-0.485
 ferment-0.483
20439-0.481
Tokenick
Token ID624
Feature activation-2.65e-01

Pos logit contributions
rolet+0.035
orth+0.033
oppy+0.031
olls+0.027
rays+0.025
Neg logit contributions
xual-0.091
 menstru-0.087
Bir-0.082
20439-0.082
 ferment-0.081
Token,
Token ID11
Feature activation-1.34e-01

Pos logit contributions
rolet+0.446
orth+0.427
oppy+0.398
olls+0.369
 NTS+0.367
Neg logit contributions
xual-0.646
 menstru-0.612
Bir-0.571
pees-0.569
20439-0.566
Token and
Token ID290
Feature activation+1.14e-01

Pos logit contributions
rolet+0.244
orth+0.235
oppy+0.222
 NTS+0.207
olls+0.206
Neg logit contributions
xual-0.307
 menstru-0.287
Bir-0.267
pees-0.264
20439-0.263
Token racial
Token ID8425
Feature activation+1.57e-01

Pos logit contributions
xual+0.092
 menstru+0.087
Bir+0.080
pees+0.080
20439+0.080
Neg logit contributions
rolet-0.085
orth-0.082
oppy-0.077
olls-0.073
 NTS-0.073
Token,
Token ID11
Feature activation+2.04e-01

Pos logit contributions
xual+0.278
 menstru+0.253
20439+0.233
Bir+0.232
pees+0.229
Neg logit contributions
rolet-0.369
orth-0.359
oppy-0.341
 NTS-0.327
olls-0.323
Token religious
Token ID4158
Feature activation-5.52e-01

Pos logit contributions
xual+0.441
 menstru+0.417
Bir+0.387
pees+0.380
 ferment+0.380
Neg logit contributions
rolet-0.398
orth-0.381
oppy-0.360
olls-0.339
 NTS-0.338
Token or
Token ID393
Feature activation-1.11e+00

Pos logit contributions
rolet+0.966
orth+0.940
oppy+0.875
 NTS+0.821
olls+0.815
Neg logit contributions
xual-1.293
 menstru-1.202
20439-1.138
pees-1.136
Bir-1.132
Token sexual
Token ID3206
Feature activation+7.69e-01

Pos logit contributions
rolet+2.248
orth+2.200
oppy+2.048
 NTS+1.987
olls+1.980
Neg logit contributions
xual-2.216
 menstru-2.044
pees-1.977
Bir-1.936
20439-1.919
Token slur
Token ID40066
Feature activation+2.61e+00

Pos logit contributions
xual+1.687
 menstru+1.591
Bir+1.481
pees+1.454
20439+1.451
Neg logit contributions
rolet-1.478
orth-1.417
oppy-1.337
olls-1.256
 NTS-1.253
Token,
Token ID11
Feature activation+1.69e-01

Pos logit contributions
xual+5.593
 menstru+5.313
Bir+4.884
 ferment+4.853
pees+4.824
Neg logit contributions
rolet-5.047
orth-4.729
oppy-4.581
olls-4.245
 NTS-4.209
Token quick
Token ID2068
Feature activation-1.14e+00

Pos logit contributions
xual+0.380
 menstru+0.360
Bir+0.335
pees+0.329
 ferment+0.328
Neg logit contributions
rolet-0.316
orth-0.302
oppy-0.285
olls-0.267
 NTS-0.267
Token to
Token ID284
Feature activation+3.30e-01

Pos logit contributions
rolet+2.151
orth+2.041
oppy+1.931
olls+1.811
 NTS+1.804
Neg logit contributions
xual-2.555
 menstru-2.429
Bir-2.252
 ferment-2.217
pees-2.205
Token lose
Token ID4425
Feature activation-9.03e-01

Pos logit contributions
xual+0.703
 menstru+0.660
Bir+0.618
pees+0.606
20439+0.605
Neg logit contributions
rolet-0.654
orth-0.627
oppy-0.591
olls-0.560
 NTS-0.557
Token a
Token ID257
Feature activation+8.79e-02

Pos logit contributions
rolet+1.626
orth+1.611
oppy+1.495
olls+1.416
rays+1.413
Neg logit contributions
xual-2.022
 menstru-1.904
Bir-1.806
20439-1.767
pees-1.763
Token
Token ID198
Feature activation-2.81e-01

Pos logit contributions
rolet+0.258
orth+0.246
oppy+0.234
olls+0.219
 NTS+0.218
Neg logit contributions
xual-0.284
 menstru-0.269
Bir-0.249
 ferment-0.245
pees-0.244
Token
Token ID198
Feature activation-2.04e-01

Pos logit contributions
rolet+0.492
orth+0.472
oppy+0.437
 NTS+0.419
olls+0.411
Neg logit contributions
xual-0.676
 menstru-0.631
pees-0.585
 ferment-0.583
20439-0.581
TokenWhen
Token ID2215
Feature activation-1.01e-01

Pos logit contributions
rolet+0.414
orth+0.399
oppy+0.375
olls+0.356
 NTS+0.354
Neg logit contributions
xual-0.434
 menstru-0.403
 ferment-0.367
pees-0.362
Bir-0.359
Token Gu
Token ID1962
Feature activation+1.38e+00

Pos logit contributions
rolet+0.165
orth+0.157
oppy+0.146
 NTS+0.137
olls+0.137
Neg logit contributions
xual-0.251
 menstru-0.238
Bir-0.223
pees-0.220
 ferment-0.219
Tokencc
Token ID535
Feature activation-3.16e-02

Pos logit contributions
xual+2.389
 menstru+2.239
Bir+2.036
 ferment+1.985
pees+1.978
Neg logit contributions
rolet-3.262
orth-3.125
oppy-2.993
 NTS-2.849
olls-2.848
Tokenifer
Token ID7087
Feature activation+2.60e+00

Pos logit contributions
rolet+0.076
orth+0.074
oppy+0.071
olls+0.067
igl+0.067
Neg logit contributions
xual-0.055
 menstru-0.051
Bir-0.046
 ferment-0.044
20439-0.044
Token 2
Token ID362
Feature activation-1.08e-01

Pos logit contributions
xual+5.162
 menstru+4.939
Bir+4.628
 ferment+4.538
tur+4.441
Neg logit contributions
rolet-5.306
orth-5.080
oppy-4.815
igl-4.521
olls-4.519
Token.
Token ID13
Feature activation+2.11e-01

Pos logit contributions
rolet+0.180
orth+0.174
oppy+0.162
 NTS+0.153
olls+0.151
Neg logit contributions
xual-0.264
 menstru-0.251
Bir-0.232
 ferment-0.230
pees-0.230
Token0
Token ID15
Feature activation-2.79e-01

Pos logit contributions
xual+0.446
 menstru+0.422
Bir+0.384
 ferment+0.382
pees+0.380
Neg logit contributions
rolet-0.424
orth-0.407
oppy-0.387
olls-0.364
 NTS-0.364
Token took
Token ID1718
Feature activation-1.05e+00

Pos logit contributions
rolet+0.485
orth+0.467
oppy+0.437
olls+0.409
 NTS+0.404
Neg logit contributions
xual-0.665
 menstru-0.625
Bir-0.584
20439-0.577
pees-0.574
Token credit
Token ID3884
Feature activation+3.06e-01

Pos logit contributions
rolet+1.745
orth+1.656
oppy+1.555
olls+1.467
 NTS+1.462
Neg logit contributions
xual-2.586
 menstru-2.431
Bir-2.296
20439-2.266
pees-2.243
Token appeared
Token ID4120
Feature activation+5.56e-02

Pos logit contributions
xual+1.717
 menstru+1.620
Bir+1.499
 ferment+1.476
20439+1.473
Neg logit contributions
rolet-1.589
orth-1.530
oppy-1.445
olls-1.368
 NTS-1.367
Token to
Token ID284
Feature activation+7.15e-02

Pos logit contributions
xual+0.119
 menstru+0.114
Bir+0.105
 ferment+0.104
pees+0.102
Neg logit contributions
rolet-0.110
orth-0.103
oppy-0.099
olls-0.093
 NTS-0.092
Token be
Token ID307
Feature activation-5.36e-01

Pos logit contributions
xual+0.144
 menstru+0.137
Bir+0.125
 ferment+0.123
pees+0.122
Neg logit contributions
rolet-0.151
orth-0.143
oppy-0.138
olls-0.129
 NTS-0.128
Token a
Token ID257
Feature activation-9.30e-02

Pos logit contributions
rolet+1.052
orth+1.017
oppy+0.961
 NTS+0.917
olls+0.912
Neg logit contributions
xual-1.134
 menstru-1.053
Bir-0.993
20439-0.983
pees-0.973
Token grease
Token ID35537
Feature activation+4.23e-02

Pos logit contributions
rolet+0.183
orth+0.176
oppy+0.165
 NTS+0.157
olls+0.157
Neg logit contributions
xual-0.199
 menstru-0.185
Bir-0.174
20439-0.172
pees-0.172
Token pencil
Token ID21613
Feature activation+2.60e+00

Pos logit contributions
xual+0.091
 menstru+0.085
Bir+0.080
20439+0.079
pees+0.078
Neg logit contributions
rolet-0.083
orth-0.079
oppy-0.075
 NTS-0.071
olls-0.070
Token."
Token ID526
Feature activation-5.43e-01

Pos logit contributions
xual+5.633
 menstru+5.427
 ferment+4.978
pees+4.859
Bir+4.850
Neg logit contributions
rolet-5.074
orth-4.624
oppy-4.442
olls-4.158
 NTS-4.125
Token
Token ID198
Feature activation+4.89e-02

Pos logit contributions
rolet+1.051
orth+1.001
oppy+0.947
olls+0.890
 NTS+0.886
Neg logit contributions
xual-1.188
 menstru-1.126
Bir-1.044
 ferment-1.025
pees-1.022
Token
Token ID198
Feature activation+8.45e-02

Pos logit contributions
xual+0.116
 menstru+0.108
pees+0.100
 ferment+0.100
Bir+0.100
Neg logit contributions
rolet-0.087
orth-0.084
oppy-0.078
 NTS-0.074
olls-0.073
Token"
Token ID1
Feature activation+3.75e-01

Pos logit contributions
xual+0.184
 menstru+0.169
 ferment+0.156
pees+0.153
20439+0.151
Neg logit contributions
rolet-0.169
orth-0.164
oppy-0.153
rays-0.146
 NTS-0.145
TokenAs
Token ID1722
Feature activation-1.93e-01

Pos logit contributions
xual+0.761
 menstru+0.709
 ferment+0.643
pees+0.637
Bir+0.631
Neg logit contributions
rolet-0.790
orth-0.765
oppy-0.721
 NTS-0.687
olls-0.683
Token News
Token ID3000
Feature activation-6.78e-01

Pos logit contributions
xual+0.320
 menstru+0.304
Bir+0.281
 ferment+0.277
pees+0.277
Neg logit contributions
rolet-0.278
orth-0.266
oppy-0.251
olls-0.237
 NTS-0.236
Token 24
Token ID1987
Feature activation+4.51e-01

Pos logit contributions
rolet+1.250
orth+1.206
oppy+1.127
 NTS+1.074
olls+1.070
Neg logit contributions
xual-1.525
 menstru-1.449
Bir-1.341
pees-1.327
 ferment-1.326
Token.
Token ID13
Feature activation+2.14e-01

Pos logit contributions
xual+1.016
 menstru+0.965
Bir+0.898
 ferment+0.882
pees+0.879
Neg logit contributions
rolet-0.841
orth-0.798
oppy-0.754
olls-0.706
 NTS-0.703
Token
Token ID198
Feature activation-1.26e-01

Pos logit contributions
xual+0.467
 menstru+0.442
Bir+0.408
 ferment+0.404
pees+0.401
Neg logit contributions
rolet-0.416
orth-0.397
oppy-0.375
olls-0.355
 NTS-0.353
Token
Token ID198
Feature activation+5.94e-03

Pos logit contributions
rolet+0.218
orth+0.212
oppy+0.194
 NTS+0.184
olls+0.184
Neg logit contributions
xual-0.307
 menstru-0.286
pees-0.266
 ferment-0.265
20439-0.262
TokenTopics
Token ID25902
Feature activation+2.58e+00

Pos logit contributions
xual+0.012
 menstru+0.011
 ferment+0.010
Bir+0.010
pees+0.010
Neg logit contributions
rolet-0.013
orth-0.012
oppy-0.012
olls-0.011
rays-0.011
Token:
Token ID25
Feature activation+8.64e-01

Pos logit contributions
xual+5.394
 menstru+5.179
Bir+4.774
 ferment+4.655
20439+4.578
Neg logit contributions
rolet-5.145
orth-4.793
oppy-4.659
olls-4.358
 NTS-4.277
Token beef
Token ID12023
Feature activation+4.95e-01

Pos logit contributions
xual+1.547
 menstru+1.454
Bir+1.317
 ferment+1.295
pees+1.282
Neg logit contributions
rolet-2.012
orth-1.928
oppy-1.845
olls-1.753
 NTS-1.746
Token-
Token ID12
Feature activation+5.90e-02

Pos logit contributions
xual+1.086
 menstru+1.027
Bir+0.956
 ferment+0.943
pees+0.932
Neg logit contributions
rolet-0.936
orth-0.879
oppy-0.851
 NTS-0.796
olls-0.795
Tokenc
Token ID66
Feature activation+2.47e-01

Pos logit contributions
xual+0.112
 menstru+0.105
Bir+0.096
 ferment+0.094
20439+0.094
Neg logit contributions
rolet-0.131
orth-0.128
oppy-0.120
olls-0.115
rays-0.114
Tokenattle
Token ID1999
Feature activation-6.19e-01

Pos logit contributions
xual+0.320
 menstru+0.294
Bir+0.256
 ferment+0.250
20439+0.247
Neg logit contributions
rolet-0.697
orth-0.679
oppy-0.653
olls-0.627
rays-0.621
Token Committee
Token ID4606
Feature activation-1.66e-01

Pos logit contributions
xual+2.522
 menstru+2.400
Bir+2.245
 ferment+2.228
pees+2.212
Neg logit contributions
rolet-1.454
orth-1.350
oppy-1.268
olls-1.163
 NTS-1.150
Token.
Token ID13
Feature activation-1.97e-01

Pos logit contributions
rolet+0.299
orth+0.284
oppy+0.267
olls+0.250
 NTS+0.249
Neg logit contributions
xual-0.385
 menstru-0.366
Bir-0.341
 ferment-0.335
pees-0.334
Token
Token ID198
Feature activation-1.58e-01

Pos logit contributions
rolet+0.373
orth+0.355
oppy+0.335
 NTS+0.316
olls+0.314
Neg logit contributions
xual-0.442
 menstru-0.418
Bir-0.386
 ferment-0.382
pees-0.381
Token
Token ID198
Feature activation-3.52e-02

Pos logit contributions
rolet+0.272
orth+0.264
oppy+0.243
 NTS+0.232
olls+0.228
Neg logit contributions
xual-0.384
 menstru-0.357
pees-0.332
 ferment-0.330
20439-0.328
TokenF
Token ID37
Feature activation-8.85e-01

Pos logit contributions
rolet+0.072
orth+0.069
oppy+0.065
olls+0.062
rays+0.061
Neg logit contributions
xual-0.074
 menstru-0.069
 ferment-0.063
Bir-0.062
pees-0.062
Tokenemin
Token ID14857
Feature activation+2.56e+00

Pos logit contributions
rolet+1.673
orth+1.645
oppy+1.528
olls+1.451
rays+1.416
Neg logit contributions
xual-1.977
 menstru-1.864
Bir-1.723
 ferment-1.696
20439-1.695
Tokenist
Token ID396
Feature activation-4.52e-01

Pos logit contributions
xual+5.654
 menstru+5.445
Bir+5.112
pees+5.005
 ferment+4.964
Neg logit contributions
rolet-4.694
orth-4.356
oppy-4.051
rays-3.898
 NTS-3.841
Token groups
Token ID2628
Feature activation-2.31e-01

Pos logit contributions
rolet+0.821
orth+0.785
oppy+0.741
olls+0.695
 NTS+0.695
Neg logit contributions
xual-1.038
 menstru-0.975
Bir-0.907
pees-0.899
20439-0.897
Token financed
Token ID29768
Feature activation+9.67e-02

Pos logit contributions
rolet+0.398
orth+0.378
oppy+0.353
 NTS+0.329
olls+0.329
Neg logit contributions
xual-0.554
 menstru-0.524
Bir-0.492
pees-0.483
20439-0.481
Token include
Token ID2291
Feature activation+7.29e-01

Pos logit contributions
xual+0.179
 menstru+0.167
Bir+0.153
pees+0.150
 ferment+0.150
Neg logit contributions
rolet-0.220
orth-0.211
oppy-0.201
olls-0.191
 NTS-0.190
Token the
Token ID262
Feature activation+2.39e-01

Pos logit contributions
xual+1.526
 menstru+1.442
Bir+1.332
 ferment+1.308
pees+1.304
Neg logit contributions
rolet-1.479
orth-1.412
oppy-1.339
olls-1.263
 NTS-1.259
Token,
Token ID11
Feature activation-1.82e-01

Pos logit contributions
xual+2.606
 menstru+2.496
Bir+2.349
 ferment+2.319
pees+2.299
Neg logit contributions
rolet-1.558
orth-1.456
oppy-1.361
olls-1.259
 NTS-1.231
Token Great
Token ID3878
Feature activation+1.22e-01

Pos logit contributions
rolet+0.334
orth+0.319
oppy+0.300
 NTS+0.284
olls+0.280
Neg logit contributions
xual-0.417
 menstru-0.394
Bir-0.367
pees-0.362
20439-0.361
Token Depression
Token ID22483
Feature activation-1.94e-01

Pos logit contributions
xual+0.260
 menstru+0.245
Bir+0.225
pees+0.222
 ferment+0.221
Neg logit contributions
rolet-0.244
orth-0.234
oppy-0.221
 NTS-0.209
olls-0.208
Token<|endoftext|>
Token ID50256
Feature activation+4.05e-02

Pos logit contributions
rolet+0.356
orth+0.339
oppy+0.319
 NTS+0.300
olls+0.299
Neg logit contributions
xual-0.444
 menstru-0.422
Bir-0.392
pees-0.386
 ferment-0.384
TokenW
Token ID54
Feature activation-1.53e-01

Pos logit contributions
xual+0.082
 menstru+0.076
 ferment+0.069
Bir+0.068
pees+0.068
Neg logit contributions
rolet-0.086
orth-0.083
oppy-0.078
rays-0.074
olls-0.074
TokenALTH
Token ID40818
Feature activation-2.93e+00

Pos logit contributions
rolet+0.291
orth+0.280
oppy+0.262
olls+0.245
 NTS+0.242
Neg logit contributions
xual-0.345
 menstru-0.326
Bir-0.301
 ferment-0.297
pees-0.297
TokenAM
Token ID2390
Feature activation-9.94e-01

Pos logit contributions
orth+4.732
rolet+4.632
oppy+4.253
 NTS+4.192
olls+4.101
Neg logit contributions
xual-7.248
 menstru-6.803
pees-6.303
20439-6.240
 ferment-6.180
Token,
Token ID11
Feature activation+1.23e-02

Pos logit contributions
rolet+1.667
orth+1.610
oppy+1.472
 NTS+1.412
olls+1.386
Neg logit contributions
xual-2.430
 menstru-2.298
pees-2.114
Bir-2.110
 ferment-2.107
Token Mass
Token ID5674
Feature activation-1.96e+00

Pos logit contributions
xual+0.037
 menstru+0.035
Bir+0.034
pees+0.033
20439+0.033
Neg logit contributions
rolet-0.014
orth-0.013
oppy-0.011
 NTS-0.010
olls-0.010
Token.
Token ID13
Feature activation+2.64e-01

Pos logit contributions
rolet+3.314
orth+3.112
oppy+2.905
 NTS+2.756
olls+2.723
Neg logit contributions
xual-4.777
 menstru-4.526
Bir-4.205
 ferment-4.157
20439-4.150
Token --
Token ID1377
Feature activation-9.25e-01

Pos logit contributions
xual+0.623
 menstru+0.593
Bir+0.554
 ferment+0.544
pees+0.542
Neg logit contributions
rolet-0.465
orth-0.441
oppy-0.415
olls-0.387
 NTS-0.384
Token do
Token ID466
Feature activation-5.45e-02

Pos logit contributions
rolet+0.137
orth+0.131
oppy+0.122
 NTS+0.116
olls+0.115
Neg logit contributions
xual-0.171
 menstru-0.159
Bir-0.151
20439-0.150
pees-0.148
Token is
Token ID318
Feature activation-6.29e-01

Pos logit contributions
rolet+0.099
orth+0.095
oppy+0.088
 NTS+0.083
olls+0.083
Neg logit contributions
xual-0.125
 menstru-0.119
Bir-0.111
pees-0.109
 ferment-0.108
Token to
Token ID284
Feature activation-1.77e-01

Pos logit contributions
rolet+1.147
orth+1.096
oppy+1.020
 NTS+0.980
olls+0.957
Neg logit contributions
xual-1.437
 menstru-1.350
Bir-1.279
pees-1.260
20439-1.252
Token determine
Token ID5004
Feature activation+4.08e-01

Pos logit contributions
rolet+0.335
orth+0.320
oppy+0.299
 NTS+0.288
olls+0.282
Neg logit contributions
xual-0.394
 menstru-0.367
Bir-0.350
20439-0.345
pees-0.342
Token how
Token ID703
Feature activation+4.91e-03

Pos logit contributions
xual+0.887
 menstru+0.839
Bir+0.779
pees+0.764
 ferment+0.763
Neg logit contributions
rolet-0.794
orth-0.758
oppy-0.716
 NTS-0.676
olls-0.674
Token much
Token ID881
Feature activation-2.87e+00

Pos logit contributions
xual+0.012
 menstru+0.011
Bir+0.010
20439+0.010
pees+0.010
Neg logit contributions
rolet-0.008
orth-0.008
oppy-0.008
 NTS-0.007
olls-0.007
Token R
Token ID371
Feature activation-8.71e-02

Pos logit contributions
orth+4.567
rolet+4.486
 NTS+4.312
oppy+4.171
rays+3.975
Neg logit contributions
xual-6.747
 menstru-6.230
20439-6.048
Bir-5.986
pees-5.960
TokenFI
Token ID11674
Feature activation-3.56e-01

Pos logit contributions
rolet+0.201
orth+0.191
oppy+0.183
olls+0.174
 NTS+0.173
Neg logit contributions
xual-0.158
 menstru-0.148
Bir-0.136
 ferment-0.133
pees-0.133
Token is
Token ID318
Feature activation-1.74e-01

Pos logit contributions
rolet+0.656
orth+0.634
oppy+0.596
 NTS+0.569
olls+0.559
Neg logit contributions
xual-0.803
 menstru-0.754
Bir-0.706
20439-0.694
pees-0.690
Token being
Token ID852
Feature activation-3.23e-02

Pos logit contributions
rolet+0.346
orth+0.334
oppy+0.314
 NTS+0.301
olls+0.299
Neg logit contributions
xual-0.371
 menstru-0.344
Bir-0.324
20439-0.317
pees-0.315
Token generated
Token ID7560
Feature activation+1.28e-01

Pos logit contributions
rolet+0.062
orth+0.060
oppy+0.056
 NTS+0.054
olls+0.054
Neg logit contributions
xual-0.071
 menstru-0.066
Bir-0.062
20439-0.061
pees-0.060
Token Stella
Token ID45856
Feature activation-4.92e-01

Pos logit contributions
rolet+0.071
orth+0.068
oppy+0.065
 NTS+0.061
olls+0.061
Neg logit contributions
xual-0.084
 menstru-0.079
Bir-0.074
pees-0.073
20439-0.072
Token didn
Token ID1422
Feature activation+4.68e-01

Pos logit contributions
rolet+0.916
orth+0.895
oppy+0.842
olls+0.789
 NTS+0.782
Neg logit contributions
xual-1.100
 menstru-1.006
Bir-0.959
20439-0.959
pees-0.943
Token't
Token ID470
Feature activation+4.85e-01

Pos logit contributions
xual+0.957
 menstru+0.892
Bir+0.814
 ferment+0.810
pees+0.808
Neg logit contributions
rolet-0.979
orth-0.949
oppy-0.893
 NTS-0.847
olls-0.845
Token know
Token ID760
Feature activation+6.34e-01

Pos logit contributions
xual+1.097
 menstru+1.020
Bir+0.973
20439+0.953
pees+0.948
Neg logit contributions
rolet-0.902
orth-0.864
oppy-0.813
olls-0.766
 NTS-0.759
Token how
Token ID703
Feature activation-6.53e-02

Pos logit contributions
xual+1.394
 menstru+1.315
Bir+1.225
pees+1.199
 ferment+1.199
Neg logit contributions
rolet-1.218
orth-1.166
oppy-1.099
olls-1.036
 NTS-1.033
Token much
Token ID881
Feature activation-2.80e+00

Pos logit contributions
rolet+0.114
orth+0.111
oppy+0.104
 NTS+0.098
olls+0.098
Neg logit contributions
xual-0.154
 menstru-0.143
Bir-0.135
20439-0.133
pees-0.133
Token it
Token ID340
Feature activation-3.53e-01

Pos logit contributions
orth+4.104
rolet+3.976
oppy+3.793
 NTS+3.659
rays+3.561
Neg logit contributions
xual-6.917
20439-6.203
pees-6.164
 menstru-6.101
Bir-6.079
Token had
Token ID550
Feature activation+1.62e-01

Pos logit contributions
rolet+0.636
orth+0.619
oppy+0.580
olls+0.545
rays+0.543
Neg logit contributions
xual-0.813
 menstru-0.741
Bir-0.712
20439-0.711
pees-0.703
Token worsened
Token ID44838
Feature activation-5.36e-02

Pos logit contributions
xual+0.356
 menstru+0.330
Bir+0.313
20439+0.309
pees+0.306
Neg logit contributions
rolet-0.312
orth-0.297
oppy-0.283
olls-0.266
 NTS-0.263
Token,
Token ID11
Feature activation-6.02e-02

Pos logit contributions
rolet+0.095
orth+0.091
oppy+0.085
olls+0.080
 NTS+0.080
Neg logit contributions
xual-0.125
 menstru-0.118
Bir-0.111
20439-0.110
pees-0.109
Token didn
Token ID1422
Feature activation-1.18e-01

Pos logit contributions
rolet+0.108
orth+0.103
oppy+0.097
olls+0.091
 NTS+0.090
Neg logit contributions
xual-0.140
 menstru-0.131
Bir-0.123
pees-0.122
20439-0.121
Token 2
Token ID362
Feature activation-9.27e-01

Pos logit contributions
xual+0.427
 menstru+0.406
Bir+0.376
pees+0.372
 ferment+0.371
Neg logit contributions
rolet-0.355
orth-0.340
oppy-0.318
 NTS-0.302
olls-0.301
Token-
Token ID12
Feature activation-3.70e-01

Pos logit contributions
rolet+1.617
orth+1.554
oppy+1.443
 NTS+1.366
olls+1.362
Neg logit contributions
xual-2.171
 menstru-2.072
pees-1.907
Bir-1.902
20439-1.894
Token3
Token ID18
Feature activation-8.40e-01

Pos logit contributions
rolet+0.805
orth+0.788
oppy+0.734
olls+0.708
rays+0.707
Neg logit contributions
xual-0.715
 menstru-0.674
 ferment-0.603
pees-0.598
Bir-0.597
Token).
Token ID737
Feature activation+9.83e-02

Pos logit contributions
rolet+1.258
orth+1.201
oppy+1.102
 NTS+1.036
olls+1.031
Neg logit contributions
xual-2.159
 menstru-2.071
Bir-1.937
pees-1.935
20439-1.918
Token The
Token ID383
Feature activation-6.76e-01

Pos logit contributions
xual+0.218
 menstru+0.205
pees+0.189
Bir+0.189
 ferment+0.187
Neg logit contributions
rolet-0.188
orth-0.181
oppy-0.169
 NTS-0.161
olls-0.160
Token general
Token ID2276
Feature activation-2.79e+00

Pos logit contributions
rolet+1.244
orth+1.214
oppy+1.129
 NTS+1.084
olls+1.071
Neg logit contributions
xual-1.534
 menstru-1.408
pees-1.331
Bir-1.322
20439-1.308
Token-
Token ID12
Feature activation+3.30e-02

Pos logit contributions
rolet+5.019
orth+5.017
oppy+4.571
 NTS+4.397
rays+4.322
Neg logit contributions
xual-6.074
 menstru-5.534
pees-5.344
20439-5.258
Bir-5.249
Tokencirc
Token ID21170
Feature activation-4.37e-01

Pos logit contributions
xual+0.070
 menstru+0.067
Bir+0.062
 ferment+0.061
pees+0.061
Neg logit contributions
rolet-0.066
orth-0.062
oppy-0.059
 NTS-0.055
olls-0.055
Tokenulation
Token ID1741
Feature activation+1.25e-01

Pos logit contributions
rolet+0.616
orth+0.580
oppy+0.533
rays+0.496
olls+0.495
Neg logit contributions
xual-1.178
 menstru-1.133
Bir-1.071
 ferment-1.052
20439-1.049
Token models
Token ID4981
Feature activation+4.05e-02

Pos logit contributions
xual+0.272
 menstru+0.256
Bir+0.237
pees+0.235
20439+0.232
Neg logit contributions
rolet-0.241
orth-0.232
oppy-0.218
 NTS-0.206
olls-0.206
Token,
Token ID11
Feature activation+2.30e-01

Pos logit contributions
xual+0.092
 menstru+0.086
Bir+0.081
pees+0.080
20439+0.079
Neg logit contributions
rolet-0.075
orth-0.072
oppy-0.067
 NTS-0.064
olls-0.063
Token
Token ID447
Feature activation-3.33e-01

Pos logit contributions
rolet+1.172
orth+1.124
oppy+1.046
olls+0.982
 NTS+0.969
Neg logit contributions
xual-1.573
 menstru-1.494
Bir-1.390
20439-1.369
 ferment-1.368
Token
Token ID247
Feature activation-3.78e-01

Pos logit contributions
rolet+0.539
orth+0.514
oppy+0.477
olls+0.444
 NTS+0.443
Neg logit contributions
xual-0.823
 menstru-0.792
Bir-0.736
 ferment-0.730
pees-0.726
Tokens
Token ID82
Feature activation-2.73e-01

Pos logit contributions
rolet+0.685
orth+0.656
oppy+0.613
olls+0.575
 NTS+0.572
Neg logit contributions
xual-0.870
 menstru-0.827
Bir-0.764
 ferment-0.756
pees-0.751
Token younger
Token ID7099
Feature activation+4.61e-01

Pos logit contributions
rolet+0.523
orth+0.499
oppy+0.473
olls+0.446
 NTS+0.443
Neg logit contributions
xual-0.604
 menstru-0.564
Bir-0.524
20439-0.520
pees-0.514
Token brother
Token ID3956
Feature activation-4.39e-01

Pos logit contributions
xual+0.888
 menstru+0.825
Bir+0.758
20439+0.749
pees+0.747
Neg logit contributions
rolet-1.018
orth-0.974
oppy-0.929
 NTS-0.884
olls-0.882
Token Vin
Token ID11820
Feature activation-2.78e+00

Pos logit contributions
rolet+0.799
orth+0.763
oppy+0.716
 NTS+0.674
olls+0.672
Neg logit contributions
xual-1.010
 menstru-0.956
Bir-0.887
 ferment-0.872
20439-0.870
Tokenod
Token ID375
Feature activation-9.76e-01

Pos logit contributions
rolet+4.145
orth+4.036
oppy+3.664
olls+3.448
rays+3.330
Neg logit contributions
xual-7.191
 menstru-6.857
Bir-6.386
20439-6.350
 ferment-6.323
Token,
Token ID11
Feature activation-7.76e-02

Pos logit contributions
rolet+1.747
orth+1.664
oppy+1.560
olls+1.465
 NTS+1.455
Neg logit contributions
xual-2.271
 menstru-2.153
Bir-2.003
 ferment-1.979
pees-1.966
Token brother
Token ID3956
Feature activation-8.62e-01

Pos logit contributions
rolet+0.142
orth+0.135
oppy+0.127
 NTS+0.120
olls+0.119
Neg logit contributions
xual-0.178
 menstru-0.168
Bir-0.156
pees-0.154
20439-0.153
Token-
Token ID12
Feature activation-2.25e-01

Pos logit contributions
rolet+1.359
orth+1.287
oppy+1.196
 NTS+1.112
olls+1.110
Neg logit contributions
xual-2.186
 menstru-2.081
Bir-1.944
 ferment-1.917
pees-1.914
Tokenin
Token ID259
Feature activation-2.96e-01

Pos logit contributions
rolet+0.491
orth+0.470
oppy+0.447
rays+0.423
olls+0.423
Neg logit contributions
xual-0.440
 menstru-0.408
Bir-0.370
20439-0.367
 ferment-0.366
Token,
Token ID11
Feature activation-8.21e-02

Pos logit contributions
xual+0.017
 menstru+0.016
Bir+0.015
pees+0.015
20439+0.014
Neg logit contributions
rolet-0.013
orth-0.012
oppy-0.012
 NTS-0.011
olls-0.011
Token but
Token ID475
Feature activation+5.62e-01

Pos logit contributions
rolet+0.148
orth+0.141
oppy+0.133
 NTS+0.125
olls+0.124
Neg logit contributions
xual-0.191
 menstru-0.178
Bir-0.168
pees-0.165
20439-0.165
Token there
Token ID612
Feature activation-4.58e-01

Pos logit contributions
xual+1.232
 menstru+1.156
Bir+1.080
pees+1.064
20439+1.061
Neg logit contributions
rolet-1.084
orth-1.036
oppy-0.978
 NTS-0.927
olls-0.923
Token is
Token ID318
Feature activation-3.14e-01

Pos logit contributions
rolet+0.841
orth+0.811
oppy+0.756
olls+0.718
 NTS+0.716
Neg logit contributions
xual-1.034
 menstru-0.978
Bir-0.907
pees-0.896
20439-0.896
Token not
Token ID407
Feature activation+2.28e-01

Pos logit contributions
rolet+0.612
orth+0.593
oppy+0.557
 NTS+0.534
olls+0.527
Neg logit contributions
xual-0.671
 menstru-0.627
Bir-0.589
pees-0.585
20439-0.582
Token much
Token ID881
Feature activation-2.76e+00

Pos logit contributions
xual+0.482
 menstru+0.455
Bir+0.421
 ferment+0.413
pees+0.413
Neg logit contributions
rolet-0.456
orth-0.436
oppy-0.412
olls-0.389
 NTS-0.388
Token I
Token ID314
Feature activation-2.20e-01

Pos logit contributions
orth+4.388
rolet+4.184
oppy+3.942
 NTS+3.922
olls+3.655
Neg logit contributions
xual-6.510
 menstru-5.974
pees-5.861
Bir-5.778
20439-5.722
Token can
Token ID460
Feature activation-3.71e-01

Pos logit contributions
rolet+0.410
orth+0.392
oppy+0.364
 NTS+0.347
olls+0.342
Neg logit contributions
xual-0.498
 menstru-0.464
Bir-0.438
pees-0.431
20439-0.430
Token do
Token ID466
Feature activation+7.78e-02

Pos logit contributions
rolet+0.681
orth+0.648
oppy+0.602
 NTS+0.573
olls+0.569
Neg logit contributions
xual-0.852
 menstru-0.793
Bir-0.754
20439-0.745
pees-0.739
Token.
Token ID13
Feature activation-5.12e-01

Pos logit contributions
xual+0.176
 menstru+0.167
Bir+0.156
pees+0.153
 ferment+0.152
Neg logit contributions
rolet-0.144
orth-0.138
oppy-0.129
 NTS-0.121
olls-0.121
Token As
Token ID1081
Feature activation-6.74e-01

Pos logit contributions
rolet+0.936
orth+0.893
oppy+0.832
 NTS+0.810
olls+0.782
Neg logit contributions
xual-1.181
 menstru-1.107
pees-1.020
 ferment-1.016
Bir-1.015
Token that
Token ID326
Feature activation-4.35e-01

Pos logit contributions
rolet+1.117
orth+1.072
oppy+1.000
 NTS+0.955
olls+0.949
Neg logit contributions
xual-1.409
 menstru-1.319
Bir-1.236
pees-1.231
20439-1.217
Token the
Token ID262
Feature activation-2.47e-01

Pos logit contributions
rolet+0.817
orth+0.794
oppy+0.748
 NTS+0.716
olls+0.709
Neg logit contributions
xual-0.958
 menstru-0.891
pees-0.839
Bir-0.835
20439-0.832
Token reference
Token ID4941
Feature activation-1.33e-01

Pos logit contributions
rolet+0.469
orth+0.453
oppy+0.427
 NTS+0.407
olls+0.403
Neg logit contributions
xual-0.545
 menstru-0.509
Bir-0.474
pees-0.472
20439-0.468
Token to
Token ID284
Feature activation-1.95e-01

Pos logit contributions
rolet+0.236
orth+0.226
oppy+0.212
 NTS+0.203
olls+0.200
Neg logit contributions
xual-0.309
 menstru-0.290
Bir-0.271
pees-0.268
20439-0.267
Token Sh
Token ID911
Feature activation-2.77e-01

Pos logit contributions
rolet+0.384
orth+0.370
oppy+0.350
 NTS+0.333
olls+0.332
Neg logit contributions
xual-0.418
 menstru-0.388
Bir-0.362
pees-0.361
20439-0.359
Tokenav
Token ID615
Feature activation-2.75e+00

Pos logit contributions
rolet+0.522
orth+0.507
oppy+0.475
olls+0.445
rays+0.438
Neg logit contributions
xual-0.622
 menstru-0.588
Bir-0.547
 ferment-0.537
pees-0.537
Tokeniv
Token ID452
Feature activation-1.21e+00

Pos logit contributions
rolet+5.831
orth+5.725
oppy+5.202
olls+5.078
igl+5.049
Neg logit contributions
xual-5.374
 menstru-5.040
20439-4.738
Bir-4.618
-4.536
Token (
Token ID357
Feature activation-2.77e-01

Pos logit contributions
rolet+2.314
orth+2.225
oppy+2.082
olls+1.967
rays+1.965
Neg logit contributions
xual-2.656
 menstru-2.484
Bir-2.289
20439-2.279
pees-2.279
Token2008
Token ID11528
Feature activation-3.17e-01

Pos logit contributions
rolet+0.598
orth+0.583
oppy+0.547
rays+0.520
 NTS+0.519
Neg logit contributions
xual-0.546
 menstru-0.508
 ferment-0.460
pees-0.455
Bir-0.454
Token)
Token ID8
Feature activation-2.02e-01

Pos logit contributions
rolet+0.515
orth+0.487
oppy+0.453
 NTS+0.422
olls+0.421
Neg logit contributions
xual-0.791
 menstru-0.752
Bir-0.703
pees-0.695
 ferment-0.694
Token should
Token ID815
Feature activation+1.77e-01

Pos logit contributions
rolet+0.369
orth+0.355
oppy+0.332
 NTS+0.314
olls+0.313
Neg logit contributions
xual-0.461
 menstru-0.436
Bir-0.407
pees-0.400
 ferment-0.399
Token 121
Token ID20416
Feature activation+9.69e-01

Pos logit contributions
rolet+0.503
orth+0.487
oppy+0.458
 NTS+0.442
olls+0.435
Neg logit contributions
xual-0.522
 menstru-0.484
Bir-0.449
20439-0.448
pees-0.447
Token months
Token ID1933
Feature activation+7.41e-02

Pos logit contributions
xual+1.780
 menstru+1.671
Bir+1.524
 ferment+1.493
pees+1.485
Neg logit contributions
rolet-2.212
orth-2.121
oppy-2.024
olls-1.925
 NTS-1.916
Token.
Token ID13
Feature activation+8.73e-02

Pos logit contributions
xual+0.170
 menstru+0.161
Bir+0.150
 ferment+0.147
pees+0.147
Neg logit contributions
rolet-0.136
orth-0.129
oppy-0.121
olls-0.114
 NTS-0.113
Token On
Token ID1550
Feature activation-1.26e+00

Pos logit contributions
xual+0.199
 menstru+0.189
 ferment+0.173
pees+0.173
Bir+0.172
Neg logit contributions
rolet-0.162
orth-0.155
oppy-0.145
 NTS-0.139
olls-0.137
Token the
Token ID262
Feature activation-4.67e-01

Pos logit contributions
rolet+2.405
orth+2.343
oppy+2.199
 NTS+2.088
olls+2.077
Neg logit contributions
xual-2.737
 menstru-2.573
Bir-2.376
pees-2.360
20439-2.352
Token flip
Token ID14283
Feature activation-2.75e+00

Pos logit contributions
rolet+0.914
orth+0.878
oppy+0.825
 NTS+0.788
olls+0.784
Neg logit contributions
xual-1.010
 menstru-0.951
Bir-0.881
pees-0.871
20439-0.864
Token side
Token ID1735
Feature activation-1.06e+00

Pos logit contributions
rolet+3.497
orth+3.408
oppy+3.019
olls+2.701
 NTS+2.669
Neg logit contributions
xual-7.677
 menstru-7.319
Bir-6.900
pees-6.857
20439-6.815
Token,
Token ID11
Feature activation-2.99e-02

Pos logit contributions
rolet+1.991
orth+1.887
oppy+1.788
olls+1.673
 NTS+1.663
Neg logit contributions
xual-2.401
 menstru-2.280
Bir-2.119
 ferment-2.085
pees-2.072
Token there
Token ID612
Feature activation-4.61e-01

Pos logit contributions
rolet+0.057
orth+0.055
oppy+0.052
 NTS+0.049
olls+0.049
Neg logit contributions
xual-0.065
 menstru-0.062
Bir-0.057
pees-0.057
 ferment-0.056
Token seems
Token ID2331
Feature activation-3.73e-01

Pos logit contributions
rolet+0.859
orth+0.824
oppy+0.769
olls+0.731
 NTS+0.727
Neg logit contributions
xual-1.037
 menstru-0.983
Bir-0.910
 ferment-0.898
20439-0.892
Token to
Token ID284
Feature activation-7.07e-02

Pos logit contributions
rolet+0.719
orth+0.682
oppy+0.649
olls+0.607
 NTS+0.604
Neg logit contributions
xual-0.818
 menstru-0.777
Bir-0.720
 ferment-0.710
pees-0.704
Token would
Token ID561
Feature activation-2.97e-01

Pos logit contributions
rolet+0.757
orth+0.743
oppy+0.693
olls+0.660
rays+0.650
Neg logit contributions
xual-0.958
 menstru-0.887
20439-0.859
Bir-0.846
pees-0.825
Token have
Token ID423
Feature activation-1.46e-01

Pos logit contributions
rolet+0.599
orth+0.575
oppy+0.544
olls+0.509
 NTS+0.505
Neg logit contributions
xual-0.617
 menstru-0.579
Bir-0.550
20439-0.547
pees-0.538
Token created
Token ID2727
Feature activation+5.66e-01

Pos logit contributions
rolet+0.274
orth+0.261
oppy+0.246
olls+0.232
 NTS+0.231
Neg logit contributions
xual-0.327
 menstru-0.307
Bir-0.290
20439-0.286
pees-0.284
Token just
Token ID655
Feature activation-4.22e-01

Pos logit contributions
xual+1.201
 menstru+1.134
Bir+1.052
pees+1.032
20439+1.030
Neg logit contributions
rolet-1.129
orth-1.081
oppy-1.024
olls-0.965
 NTS-0.965
Token too
Token ID1165
Feature activation-2.62e+00

Pos logit contributions
rolet+0.781
orth+0.756
oppy+0.709
 NTS+0.667
olls+0.666
Neg logit contributions
xual-0.951
 menstru-0.895
20439-0.839
Bir-0.838
pees-0.825
Token much
Token ID881
Feature activation-2.73e+00

Pos logit contributions
orth+3.660
rolet+3.638
oppy+3.444
 NTS+3.142
olls+3.099
Neg logit contributions
xual-6.571
 menstru-6.171
20439-6.073
Bir-5.939
pees-5.910
Token tension
Token ID12097
Feature activation+9.52e-02

Pos logit contributions
rolet+5.062
orth+5.028
oppy+4.793
 NTS+4.700
 Registry+4.446
Neg logit contributions
xual-5.548
20439-5.094
 menstru-5.011
pees-4.969
Bir-4.855
Token,
Token ID11
Feature activation-2.27e-01

Pos logit contributions
xual+0.223
 menstru+0.212
Bir+0.199
20439+0.195
pees+0.195
Neg logit contributions
rolet-0.168
orth-0.160
oppy-0.150
olls-0.141
 NTS-0.140
Token knowing
Token ID6970
Feature activation-3.40e-02

Pos logit contributions
rolet+0.407
orth+0.392
oppy+0.367
 NTS+0.350
olls+0.344
Neg logit contributions
xual-0.520
 menstru-0.486
20439-0.464
Bir-0.461
pees-0.456
Token you
Token ID345
Feature activation-7.51e-01

Pos logit contributions
rolet+0.062
orth+0.059
oppy+0.056
 NTS+0.053
olls+0.052
Neg logit contributions
xual-0.078
 menstru-0.073
Bir-0.069
20439-0.068
pees-0.068
Token were
Token ID547
Feature activation-2.27e-01

Pos logit contributions
rolet+1.400
orth+1.341
oppy+1.254
 NTS+1.189
olls+1.182
Neg logit contributions
xual-1.694
 menstru-1.536
20439-1.491
Bir-1.476
pees-1.464
Token on
Token ID319
Feature activation-3.42e-01

Pos logit contributions
rolet+0.323
orth+0.309
oppy+0.295
 NTS+0.276
olls+0.275
Neg logit contributions
xual-0.421
 menstru-0.397
Bir-0.374
pees-0.367
20439-0.365
Token just
Token ID655
Feature activation-5.22e-01

Pos logit contributions
rolet+0.619
orth+0.592
oppy+0.560
 NTS+0.529
olls+0.523
Neg logit contributions
xual-0.788
 menstru-0.745
Bir-0.697
pees-0.687
20439-0.683
Token to
Token ID284
Feature activation-2.13e-01

Pos logit contributions
rolet+0.921
orth+0.896
oppy+0.836
 NTS+0.801
olls+0.790
Neg logit contributions
xual-1.211
 menstru-1.141
Bir-1.072
20439-1.059
pees-1.052
Token see
Token ID766
Feature activation+1.50e-01

Pos logit contributions
rolet+0.415
orth+0.403
oppy+0.379
 NTS+0.361
olls+0.358
Neg logit contributions
xual-0.460
 menstru-0.428
Bir-0.405
20439-0.399
pees-0.394
Token how
Token ID703
Feature activation-3.24e-01

Pos logit contributions
xual+0.343
 menstru+0.324
Bir+0.303
pees+0.297
20439+0.296
Neg logit contributions
rolet-0.274
orth-0.263
oppy-0.248
 NTS-0.234
olls-0.232
Token much
Token ID881
Feature activation-2.73e+00

Pos logit contributions
rolet+0.543
orth+0.525
oppy+0.497
 NTS+0.469
rays+0.462
Neg logit contributions
xual-0.781
 menstru-0.736
Bir-0.693
20439-0.685
pees-0.682
Token R
Token ID371
Feature activation-1.16e-02

Pos logit contributions
orth+4.441
rolet+4.403
 NTS+4.166
oppy+4.140
rays+4.048
Neg logit contributions
xual-6.241
 menstru-5.778
20439-5.557
Bir-5.529
pees-5.482
TokenFI
Token ID11674
Feature activation-2.26e-01

Pos logit contributions
rolet+0.025
orth+0.024
oppy+0.023
olls+0.022
 NTS+0.022
Neg logit contributions
xual-0.023
 menstru-0.021
Bir-0.019
 ferment-0.019
20439-0.019
Token is
Token ID318
Feature activation-1.91e-01

Pos logit contributions
rolet+0.401
orth+0.385
oppy+0.362
 NTS+0.343
olls+0.341
Neg logit contributions
xual-0.527
 menstru-0.494
Bir-0.463
20439-0.455
pees-0.452
Token getting
Token ID1972
Feature activation+1.06e-01

Pos logit contributions
rolet+0.375
orth+0.360
oppy+0.338
 NTS+0.324
olls+0.323
Neg logit contributions
xual-0.409
 menstru-0.377
Bir-0.355
20439-0.347
pees-0.346
Token into
Token ID656
Feature activation-3.39e-01

Pos logit contributions
xual+0.227
 menstru+0.214
Bir+0.200
20439+0.196
pees+0.195
Neg logit contributions
rolet-0.206
orth-0.198
oppy-0.187
olls-0.178
 NTS-0.177
Token not
Token ID407
Feature activation+3.47e-01

Pos logit contributions
xual+0.901
 menstru+0.856
Bir+0.796
 ferment+0.781
pees+0.780
Neg logit contributions
rolet-0.739
orth-0.703
oppy-0.662
olls-0.621
 NTS-0.621
Token a
Token ID257
Feature activation-2.34e-01

Pos logit contributions
xual+0.747
 menstru+0.704
Bir+0.653
 ferment+0.640
pees+0.639
Neg logit contributions
rolet-0.685
orth-0.652
oppy-0.617
olls-0.582
 NTS-0.581
Token backup
Token ID11559
Feature activation-6.36e-01

Pos logit contributions
rolet+0.420
orth+0.398
oppy+0.375
 NTS+0.351
olls+0.350
Neg logit contributions
xual-0.545
 menstru-0.515
Bir-0.481
pees-0.472
 ferment-0.471
Token system
Token ID1080
Feature activation+1.16e-01

Pos logit contributions
rolet+1.177
orth+1.127
oppy+1.063
 NTS+1.004
olls+0.991
Neg logit contributions
xual-1.430
 menstru-1.350
Bir-1.250
pees-1.243
20439-1.238
Token.
Token ID764
Feature activation-4.44e-01

Pos logit contributions
xual+0.270
 menstru+0.256
Bir+0.239
 ferment+0.235
pees+0.235
Neg logit contributions
rolet-0.209
orth-0.198
oppy-0.186
olls-0.175
 NTS-0.174
Token Rest
Token ID8324
Feature activation-2.72e+00

Pos logit contributions
rolet+0.831
orth+0.788
oppy+0.746
 NTS+0.714
olls+0.698
Neg logit contributions
xual-1.007
 menstru-0.948
Bir-0.874
 ferment-0.864
pees-0.862
Tokenores
Token ID2850
Feature activation-9.85e-01

Pos logit contributions
rolet+2.921
orth+2.732
oppy+2.495
rays+2.169
olls+2.158
Neg logit contributions
xual-8.196
 menstru-7.827
Bir-7.447
20439-7.353
 ferment-7.295
Token are
Token ID389
Feature activation+9.33e-02

Pos logit contributions
rolet+1.873
orth+1.780
oppy+1.692
 NTS+1.605
rays+1.595
Neg logit contributions
xual-2.161
 menstru-2.032
Bir-1.907
20439-1.858
pees-1.848
Token a
Token ID257
Feature activation+3.20e-01

Pos logit contributions
xual+0.204
 menstru+0.192
Bir+0.179
20439+0.175
pees+0.174
Neg logit contributions
rolet-0.182
orth-0.173
oppy-0.163
 NTS-0.155
olls-0.154
Token non
Token ID1729
Feature activation-2.12e-01

Pos logit contributions
xual+0.717
 menstru+0.680
Bir+0.632
pees+0.620
 ferment+0.620
Neg logit contributions
rolet-0.602
orth-0.572
oppy-0.540
olls-0.506
 NTS-0.505
Token-
Token ID12
Feature activation-1.52e-02

Pos logit contributions
rolet+0.385
orth+0.365
oppy+0.345
olls+0.323
 NTS+0.321
Neg logit contributions
xual-0.488
 menstru-0.465
Bir-0.432
 ferment-0.426
pees-0.424
Token of
Token ID286
Feature activation+3.26e-02

Pos logit contributions
rolet+1.315
orth+1.256
oppy+1.169
olls+1.090
 NTS+1.088
Neg logit contributions
xual-2.017
 menstru-1.914
Bir-1.797
20439-1.772
pees-1.770
Token the
Token ID262
Feature activation-2.34e-01

Pos logit contributions
xual+0.066
 menstru+0.062
Bir+0.057
 ferment+0.056
pees+0.056
Neg logit contributions
rolet-0.068
orth-0.065
oppy-0.062
olls-0.059
 NTS-0.059
Token two
Token ID734
Feature activation-3.32e-01

Pos logit contributions
rolet+0.502
orth+0.482
oppy+0.460
 NTS+0.438
olls+0.434
Neg logit contributions
xual-0.461
 menstru-0.428
Bir-0.394
20439-0.392
pees-0.387
Token.
Token ID13
Feature activation-2.93e-02

Pos logit contributions
rolet+0.738
orth+0.719
oppy+0.684
olls+0.653
 NTS+0.651
Neg logit contributions
xual-0.623
 menstru-0.573
Bir-0.525
20439-0.524
pees-0.517
Token Not
Token ID1892
Feature activation+4.70e-01

Pos logit contributions
rolet+0.056
orth+0.054
oppy+0.051
 NTS+0.049
olls+0.048
Neg logit contributions
xual-0.064
 menstru-0.061
 ferment-0.056
pees-0.055
Bir-0.055
Token much
Token ID881
Feature activation-2.71e+00

Pos logit contributions
xual+1.002
 menstru+0.935
Bir+0.870
20439+0.858
pees+0.855
Neg logit contributions
rolet-0.933
orth-0.902
oppy-0.846
 NTS-0.804
olls-0.800
Token fun
Token ID1257
Feature activation-7.47e-01

Pos logit contributions
orth+4.472
rolet+4.309
oppy+4.075
 NTS+4.026
rays+3.862
Neg logit contributions
xual-6.091
 menstru-5.587
20439-5.501
pees-5.408
Bir-5.391
Token to
Token ID284
Feature activation+1.82e-01

Pos logit contributions
rolet+1.322
orth+1.276
oppy+1.179
olls+1.117
 NTS+1.114
Neg logit contributions
xual-1.726
 menstru-1.620
Bir-1.519
20439-1.510
pees-1.499
Token go
Token ID467
Feature activation-1.90e-01

Pos logit contributions
xual+0.403
 menstru+0.374
Bir+0.351
20439+0.350
pees+0.346
Neg logit contributions
rolet-0.344
orth-0.330
oppy-0.313
olls-0.296
 NTS-0.292
Token to
Token ID284
Feature activation-1.42e-01

Pos logit contributions
rolet+0.333
orth+0.320
oppy+0.301
olls+0.282
 NTS+0.279
Neg logit contributions
xual-0.446
 menstru-0.420
Bir-0.394
20439-0.392
pees-0.387
Token the
Token ID262
Feature activation-2.55e-01

Pos logit contributions
rolet+0.264
orth+0.252
oppy+0.238
olls+0.223
 NTS+0.223
Neg logit contributions
xual-0.321
 menstru-0.300
Bir-0.278
20439-0.276
pees-0.275
Token don
Token ID836
Feature activation+1.03e-01

Pos logit contributions
xual+0.336
 menstru+0.313
Bir+0.295
20439+0.292
pees+0.291
Neg logit contributions
rolet-0.289
orth-0.277
oppy-0.262
olls-0.246
 NTS-0.245
Token't
Token ID470
Feature activation+3.01e-01

Pos logit contributions
xual+0.216
 menstru+0.201
 ferment+0.183
pees+0.183
Bir+0.183
Neg logit contributions
rolet-0.212
orth-0.206
oppy-0.193
rays-0.182
 NTS-0.182
Token ever
Token ID1683
Feature activation-1.10e+00

Pos logit contributions
xual+0.682
 menstru+0.643
Bir+0.607
20439+0.596
pees+0.595
Neg logit contributions
rolet-0.558
orth-0.532
oppy-0.502
olls-0.471
 NTS-0.470
Token really
Token ID1107
Feature activation-3.25e-01

Pos logit contributions
rolet+1.973
orth+1.874
oppy+1.774
 NTS+1.665
olls+1.659
Neg logit contributions
xual-2.507
 menstru-2.295
Bir-2.254
20439-2.248
pees-2.202
Token see
Token ID766
Feature activation-1.02e-02

Pos logit contributions
rolet+0.598
orth+0.573
oppy+0.538
olls+0.507
 NTS+0.506
Neg logit contributions
xual-0.736
 menstru-0.683
Bir-0.658
20439-0.651
pees-0.642
Token much
Token ID881
Feature activation-2.70e+00

Pos logit contributions
rolet+0.020
orth+0.019
oppy+0.018
olls+0.017
 NTS+0.017
Neg logit contributions
xual-0.022
 menstru-0.020
Bir-0.019
pees-0.019
20439-0.019
Token about
Token ID546
Feature activation-3.67e-01

Pos logit contributions
orth+3.761
rolet+3.738
oppy+3.511
 NTS+3.316
rays+3.207
Neg logit contributions
xual-6.719
 menstru-6.355
Bir-6.195
pees-6.152
20439-6.128
Token the
Token ID262
Feature activation-4.69e-01

Pos logit contributions
rolet+0.730
orth+0.701
oppy+0.666
olls+0.631
 NTS+0.630
Neg logit contributions
xual-0.770
 menstru-0.726
Bir-0.680
20439-0.664
pees-0.664
Token past
Token ID1613
Feature activation-4.74e-02

Pos logit contributions
rolet+0.914
orth+0.878
oppy+0.840
 NTS+0.791
olls+0.789
Neg logit contributions
xual-1.006
 menstru-0.946
Bir-0.890
20439-0.873
pees-0.868
Token there
Token ID612
Feature activation-7.01e-01

Pos logit contributions
rolet+0.085
orth+0.081
oppy+0.076
olls+0.071
 NTS+0.071
Neg logit contributions
xual-0.110
 menstru-0.105
Bir-0.098
pees-0.096
 ferment-0.096
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
rolet+1.218
orth+1.161
oppy+1.085
olls+1.015
 NTS+1.009
Neg logit contributions
xual-1.661
 menstru-1.583
Bir-1.480
pees-1.455
20439-1.450
Token manually
Token ID14500
Feature activation+2.55e-01

Pos logit contributions
rolet+0.818
orth+0.782
oppy+0.735
 NTS+0.698
olls+0.692
Neg logit contributions
xual-0.984
 menstru-0.907
20439-0.884
Bir-0.875
pees-0.850
Token keep
Token ID1394
Feature activation-1.34e-01

Pos logit contributions
xual+0.563
 menstru+0.523
Bir+0.498
20439+0.491
pees+0.484
Neg logit contributions
rolet-0.488
orth-0.469
oppy-0.439
 NTS-0.418
olls-0.412
Token track
Token ID2610
Feature activation+5.63e-01

Pos logit contributions
rolet+0.258
orth+0.253
oppy+0.238
 NTS+0.228
olls+0.227
Neg logit contributions
xual-0.288
 menstru-0.267
Bir-0.254
20439-0.246
pees-0.244
Token of
Token ID286
Feature activation-2.85e-01

Pos logit contributions
xual+1.365
 menstru+1.310
Bir+1.210
 ferment+1.202
pees+1.192
Neg logit contributions
rolet-0.961
orth-0.892
oppy-0.839
olls-0.783
 NTS-0.776
Token how
Token ID703
Feature activation+1.70e-01

Pos logit contributions
rolet+0.530
orth+0.521
oppy+0.492
 NTS+0.469
olls+0.466
Neg logit contributions
xual-0.629
 menstru-0.581
Bir-0.557
20439-0.541
pees-0.539
Token much
Token ID881
Feature activation-2.69e+00

Pos logit contributions
xual+0.373
 menstru+0.349
Bir+0.326
20439+0.319
pees+0.318
Neg logit contributions
rolet-0.323
orth-0.317
oppy-0.300
olls-0.284
 NTS-0.283
Token text
Token ID2420
Feature activation-1.73e-01

Pos logit contributions
orth+4.390
rolet+4.180
oppy+4.068
 NTS+3.990
olls+3.880
Neg logit contributions
xual-6.220
 menstru-5.637
Bir-5.477
20439-5.471
pees-5.391
Token can
Token ID460
Feature activation-1.02e-01

Pos logit contributions
rolet+0.324
orth+0.320
oppy+0.302
olls+0.287
 NTS+0.285
Neg logit contributions
xual-0.382
 menstru-0.355
Bir-0.333
20439-0.328
pees-0.322
Token go
Token ID467
Feature activation-1.14e-01

Pos logit contributions
rolet+0.191
orth+0.189
oppy+0.175
olls+0.167
igl+0.164
Neg logit contributions
xual-0.227
 menstru-0.210
Bir-0.201
20439-0.199
pees-0.193
Token in
Token ID287
Feature activation-2.39e-01

Pos logit contributions
rolet+0.198
orth+0.193
oppy+0.179
olls+0.170
 NTS+0.168
Neg logit contributions
xual-0.269
 menstru-0.253
Bir-0.241
20439-0.236
pees-0.233
Token each
Token ID1123
Feature activation+1.04e+00

Pos logit contributions
rolet+0.454
orth+0.444
oppy+0.419
 NTS+0.395
olls+0.394
Neg logit contributions
xual-0.522
 menstru-0.489
Bir-0.460
pees-0.448
20439-0.446
Token said
Token ID531
Feature activation-5.47e-01

Pos logit contributions
rolet+0.764
orth+0.720
oppy+0.669
 NTS+0.622
olls+0.617
Neg logit contributions
xual-1.383
 menstru-1.318
Bir-1.232
pees-1.221
20439-1.217
Token Drew
Token ID18624
Feature activation-4.66e-01

Pos logit contributions
rolet+0.922
orth+0.880
oppy+0.827
 NTS+0.783
olls+0.774
Neg logit contributions
xual-1.327
 menstru-1.251
Bir-1.170
pees-1.160
20439-1.154
Token T
Token ID309
Feature activation+3.80e-01

Pos logit contributions
rolet+0.857
orth+0.819
oppy+0.770
olls+0.722
 NTS+0.720
Neg logit contributions
xual-1.068
 menstru-1.013
Bir-0.937
 ferment-0.924
20439-0.921
Token.
Token ID13
Feature activation+3.01e-01

Pos logit contributions
xual+0.844
 menstru+0.800
Bir+0.744
 ferment+0.731
pees+0.730
Neg logit contributions
rolet-0.720
orth-0.683
oppy-0.646
 NTS-0.607
olls-0.605
Token Sh
Token ID911
Feature activation-3.49e-01

Pos logit contributions
xual+0.688
 menstru+0.655
Bir+0.611
 ferment+0.599
pees+0.597
Neg logit contributions
rolet-0.551
orth-0.522
oppy-0.493
olls-0.461
 NTS-0.458
Tokenind
Token ID521
Feature activation-2.68e+00

Pos logit contributions
rolet+0.684
orth+0.664
oppy+0.624
olls+0.590
rays+0.579
Neg logit contributions
xual-0.755
 menstru-0.719
Bir-0.664
 ferment-0.653
20439-0.652
Tokenell
Token ID695
Feature activation-9.31e-01

Pos logit contributions
orth+5.931
rolet+5.917
oppy+5.521
olls+5.353
igl+5.250
Neg logit contributions
xual-4.791
 menstru-4.622
Bir-4.235
20439-4.138
-4.098
Token,
Token ID11
Feature activation+2.46e-01

Pos logit contributions
rolet+1.681
orth+1.602
oppy+1.506
olls+1.409
 NTS+1.405
Neg logit contributions
xual-2.151
 menstru-2.044
Bir-1.899
 ferment-1.868
pees-1.868
Token professor
Token ID6240
Feature activation-1.20e+00

Pos logit contributions
xual+0.531
 menstru+0.502
Bir+0.465
pees+0.456
 ferment+0.456
Neg logit contributions
rolet-0.482
orth-0.461
oppy-0.436
olls-0.410
 NTS-0.410
Token of
Token ID286
Feature activation-3.53e-01

Pos logit contributions
rolet+1.764
orth+1.699
oppy+1.556
 NTS+1.454
olls+1.441
Neg logit contributions
xual-3.133
 menstru-2.964
Bir-2.791
pees-2.772
20439-2.754
Token climate
Token ID4258
Feature activation+4.45e-01

Pos logit contributions
rolet+0.664
orth+0.639
oppy+0.599
 NTS+0.567
olls+0.565
Neg logit contributions
xual-0.790
 menstru-0.736
Bir-0.690
20439-0.685
pees-0.680
Token
Token ID247
Feature activation-1.12e-01

Pos logit contributions
rolet+0.976
orth+0.940
oppy+0.900
rays+0.863
olls+0.862
Neg logit contributions
xual-0.600
 menstru-0.557
Bir-0.505
 ferment-0.490
20439-0.487
Tokens
Token ID82
Feature activation+7.20e-02

Pos logit contributions
rolet+0.217
orth+0.212
oppy+0.197
rays+0.187
 NTS+0.187
Neg logit contributions
xual-0.241
 menstru-0.230
Bir-0.213
 ferment-0.210
20439-0.209
Token silly
Token ID14397
Feature activation+2.02e-02

Pos logit contributions
xual+0.150
 menstru+0.141
Bir+0.130
pees+0.128
20439+0.128
Neg logit contributions
rolet-0.146
orth-0.141
oppy-0.132
 NTS-0.127
rays-0.125
Token.
Token ID13
Feature activation+4.71e-02

Pos logit contributions
xual+0.047
 menstru+0.044
Bir+0.041
 ferment+0.041
pees+0.041
Neg logit contributions
rolet-0.036
orth-0.035
oppy-0.032
 NTS-0.030
olls-0.030
Token Not
Token ID1892
Feature activation+5.16e-01

Pos logit contributions
xual+0.104
 menstru+0.098
Bir+0.091
20439+0.090
 ferment+0.090
Neg logit contributions
rolet-0.090
orth-0.087
oppy-0.081
 NTS-0.078
olls-0.076
Token much
Token ID881
Feature activation-2.67e+00

Pos logit contributions
xual+1.130
 menstru+1.062
Bir+0.985
pees+0.970
 ferment+0.969
Neg logit contributions
rolet-0.996
orth-0.958
oppy-0.900
 NTS-0.854
olls-0.845
Token to
Token ID284
Feature activation-2.25e-01

Pos logit contributions
orth+4.412
rolet+4.284
oppy+3.991
 NTS+3.984
rays+3.712
Neg logit contributions
xual-6.112
 menstru-5.656
20439-5.372
pees-5.358
Bir-5.325
Token grasp
Token ID13180
Feature activation-7.76e-01

Pos logit contributions
rolet+0.427
orth+0.409
oppy+0.384
 NTS+0.367
olls+0.361
Neg logit contributions
xual-0.501
 menstru-0.468
Bir-0.436
20439-0.431
pees-0.429
Token at
Token ID379
Feature activation-6.18e-01

Pos logit contributions
rolet+1.354
orth+1.305
oppy+1.202
 NTS+1.158
rays+1.125
Neg logit contributions
xual-1.826
 menstru-1.716
Bir-1.614
20439-1.596
pees-1.596
Token here
Token ID994
Feature activation-2.20e-01

Pos logit contributions
rolet+1.280
orth+1.235
oppy+1.165
olls+1.109
 NTS+1.108
Neg logit contributions
xual-1.265
 menstru-1.173
Bir-1.082
20439-1.072
 ferment-1.066
Token
Token ID784
Feature activation-3.86e-01

Pos logit contributions
rolet+0.382
orth+0.363
oppy+0.339
 NTS+0.319
olls+0.316
Neg logit contributions
xual-0.525
 menstru-0.497
Bir-0.463
pees-0.458
 ferment-0.457
Token transparent
Token ID13245
Feature activation-4.16e-01

Pos logit contributions
xual+0.784
 menstru+0.741
Bir+0.693
pees+0.680
 ferment+0.675
Neg logit contributions
rolet-0.651
orth-0.623
oppy-0.585
 NTS-0.553
olls-0.550
Tokenly
Token ID306
Feature activation+5.36e-01

Pos logit contributions
rolet+0.715
orth+0.690
oppy+0.640
 NTS+0.604
rays+0.600
Neg logit contributions
xual-0.987
 menstru-0.938
Bir-0.882
pees-0.864
 ferment-0.862
Token to
Token ID284
Feature activation+1.70e-01

Pos logit contributions
xual+1.241
 menstru+1.178
Bir+1.103
pees+1.080
 ferment+1.079
Neg logit contributions
rolet-0.965
orth-0.922
oppy-0.865
 NTS-0.810
olls-0.809
Token you
Token ID345
Feature activation-2.58e-01

Pos logit contributions
xual+0.347
 menstru+0.325
Bir+0.304
pees+0.296
20439+0.295
Neg logit contributions
rolet-0.349
orth-0.340
oppy-0.322
 NTS-0.307
olls-0.305
Token.
Token ID13
Feature activation-1.01e-01

Pos logit contributions
rolet+0.458
orth+0.439
oppy+0.408
 NTS+0.386
olls+0.384
Neg logit contributions
xual-0.602
 menstru-0.570
Bir-0.535
pees-0.527
20439-0.523
Token Rest
Token ID8324
Feature activation-2.66e+00

Pos logit contributions
rolet+0.189
orth+0.182
oppy+0.170
 NTS+0.164
olls+0.161
Neg logit contributions
xual-0.227
 menstru-0.215
Bir-0.198
 ferment-0.197
pees-0.197
Token assured
Token ID13933
Feature activation+3.97e-01

Pos logit contributions
rolet+2.979
orth+2.932
oppy+2.569
 NTS+2.419
rays+2.351
Neg logit contributions
xual-7.763
 menstru-7.394
Bir-7.056
-6.936
pees-6.925
Token,
Token ID11
Feature activation+9.51e-02

Pos logit contributions
xual+0.890
 menstru+0.844
Bir+0.785
 ferment+0.770
pees+0.770
Neg logit contributions
rolet-0.746
orth-0.711
oppy-0.671
olls-0.630
 NTS-0.630
Token the
Token ID262
Feature activation+4.15e-03

Pos logit contributions
xual+0.199
 menstru+0.187
Bir+0.175
pees+0.171
20439+0.170
Neg logit contributions
rolet-0.191
orth-0.184
oppy-0.174
 NTS-0.166
olls-0.165
Token techn
Token ID1579
Feature activation-1.11e+00

Pos logit contributions
xual+0.009
 menstru+0.008
Bir+0.008
pees+0.007
20439+0.007
Neg logit contributions
rolet-0.008
orth-0.008
oppy-0.008
 NTS-0.007
olls-0.007
Tokenologists
Token ID9251
Feature activation-9.48e-01

Pos logit contributions
rolet+2.492
orth+2.447
oppy+2.325
olls+2.224
igl+2.180
Neg logit contributions
xual-2.028
 menstru-1.904
Bir-1.725
pees-1.692
20439-1.691
Token It
Token ID632
Feature activation-4.22e-01

Pos logit contributions
rolet+0.366
orth+0.349
oppy+0.324
 NTS+0.319
olls+0.304
Neg logit contributions
xual-0.493
 menstru-0.464
pees-0.427
 ferment-0.425
Bir-0.424
Token would
Token ID561
Feature activation-2.97e-01

Pos logit contributions
rolet+0.757
orth+0.743
oppy+0.693
olls+0.660
rays+0.650
Neg logit contributions
xual-0.958
 menstru-0.887
20439-0.859
Bir-0.846
pees-0.825
Token have
Token ID423
Feature activation-1.46e-01

Pos logit contributions
rolet+0.599
orth+0.575
oppy+0.544
olls+0.509
 NTS+0.505
Neg logit contributions
xual-0.617
 menstru-0.579
Bir-0.550
20439-0.547
pees-0.538
Token created
Token ID2727
Feature activation+5.66e-01

Pos logit contributions
rolet+0.274
orth+0.261
oppy+0.246
olls+0.232
 NTS+0.231
Neg logit contributions
xual-0.327
 menstru-0.307
Bir-0.290
20439-0.286
pees-0.284
Token just
Token ID655
Feature activation-4.22e-01

Pos logit contributions
xual+1.201
 menstru+1.134
Bir+1.052
pees+1.032
20439+1.030
Neg logit contributions
rolet-1.129
orth-1.081
oppy-1.024
olls-0.965
 NTS-0.965
Token too
Token ID1165
Feature activation-2.62e+00

Pos logit contributions
rolet+0.781
orth+0.756
oppy+0.709
 NTS+0.667
olls+0.666
Neg logit contributions
xual-0.951
 menstru-0.895
20439-0.839
Bir-0.838
pees-0.825
Token much
Token ID881
Feature activation-2.73e+00

Pos logit contributions
orth+3.660
rolet+3.638
oppy+3.444
 NTS+3.142
olls+3.099
Neg logit contributions
xual-6.571
 menstru-6.171
20439-6.073
Bir-5.939
pees-5.910
Token tension
Token ID12097
Feature activation+9.52e-02

Pos logit contributions
rolet+5.062
orth+5.028
oppy+4.793
 NTS+4.700
 Registry+4.446
Neg logit contributions
xual-5.548
20439-5.094
 menstru-5.011
pees-4.969
Bir-4.855
Token,
Token ID11
Feature activation-2.27e-01

Pos logit contributions
xual+0.223
 menstru+0.212
Bir+0.199
20439+0.195
pees+0.195
Neg logit contributions
rolet-0.168
orth-0.160
oppy-0.150
olls-0.141
 NTS-0.140
Token knowing
Token ID6970
Feature activation-3.40e-02

Pos logit contributions
rolet+0.407
orth+0.392
oppy+0.367
 NTS+0.350
olls+0.344
Neg logit contributions
xual-0.520
 menstru-0.486
20439-0.464
Bir-0.461
pees-0.456
Token you
Token ID345
Feature activation-7.51e-01

Pos logit contributions
rolet+0.062
orth+0.059
oppy+0.056
 NTS+0.053
olls+0.052
Neg logit contributions
xual-0.078
 menstru-0.073
Bir-0.069
20439-0.068
pees-0.068
Token them
Token ID606
Feature activation-1.96e-01

Pos logit contributions
rolet+0.593
orth+0.570
oppy+0.543
olls+0.515
 NTS+0.515
Neg logit contributions
xual-0.643
 menstru-0.600
Bir-0.558
20439-0.554
pees-0.545
Token the
Token ID262
Feature activation-2.25e-01

Pos logit contributions
rolet+0.358
orth+0.342
oppy+0.325
olls+0.304
 NTS+0.303
Neg logit contributions
xual-0.447
 menstru-0.420
Bir-0.394
20439-0.389
pees-0.386
Token size
Token ID2546
Feature activation+1.06e+00

Pos logit contributions
rolet+0.441
orth+0.421
oppy+0.400
 NTS+0.378
olls+0.376
Neg logit contributions
xual-0.486
 menstru-0.460
Bir-0.425
pees-0.418
20439-0.418
Token of
Token ID286
Feature activation-2.63e-01

Pos logit contributions
xual+2.486
 menstru+2.389
Bir+2.228
 ferment+2.197
pees+2.168
Neg logit contributions
rolet-1.846
orth-1.739
oppy-1.628
olls-1.506
 NTS-1.490
Token my
Token ID616
Feature activation-5.03e-02

Pos logit contributions
rolet+0.549
orth+0.524
oppy+0.505
olls+0.479
 NTS+0.477
Neg logit contributions
xual-0.537
 menstru-0.494
Bir-0.460
20439-0.457
pees-0.449
Token thumb
Token ID15683
Feature activation-2.60e+00

Pos logit contributions
rolet+0.097
orth+0.092
oppy+0.088
 NTS+0.083
olls+0.082
Neg logit contributions
xual-0.111
 menstru-0.103
Bir-0.096
20439-0.095
pees-0.095
Token).
Token ID737
Feature activation-2.37e-01

Pos logit contributions
rolet+3.947
orth+3.938
oppy+3.617
olls+3.450
rays+3.378
Neg logit contributions
xual-6.346
 menstru-6.020
Bir-5.722
20439-5.721
pees-5.450
Token Now
Token ID2735
Feature activation-1.21e+00

Pos logit contributions
rolet+0.434
orth+0.413
oppy+0.387
 NTS+0.371
olls+0.364
Neg logit contributions
xual-0.549
 menstru-0.519
20439-0.475
Bir-0.475
pees-0.475
Token throw
Token ID3714
Feature activation+6.89e-01

Pos logit contributions
rolet+2.216
orth+2.126
oppy+1.987
 NTS+1.887
olls+1.858
Neg logit contributions
xual-2.706
 menstru-2.498
20439-2.410
Bir-2.398
pees-2.356
Token it
Token ID340
Feature activation-1.02e-02

Pos logit contributions
xual+1.394
 menstru+1.316
Bir+1.212
 ferment+1.189
pees+1.184
Neg logit contributions
rolet-1.444
orth-1.381
oppy-1.312
olls-1.240
 NTS-1.236
Token on
Token ID319
Feature activation-2.77e-01

Pos logit contributions
rolet+0.020
orth+0.019
oppy+0.018
 NTS+0.017
olls+0.017
Neg logit contributions
xual-0.022
 menstru-0.021
Bir-0.019
20439-0.019
pees-0.019
Token the
Token ID262
Feature activation-1.04e-01

Pos logit contributions
rolet+0.347
orth+0.333
oppy+0.317
 NTS+0.301
olls+0.299
Neg logit contributions
xual-0.374
 menstru-0.348
Bir-0.324
20439-0.321
pees-0.320
Token fans
Token ID3296
Feature activation+7.73e-01

Pos logit contributions
rolet+0.198
orth+0.189
oppy+0.179
 NTS+0.171
olls+0.170
Neg logit contributions
xual-0.233
 menstru-0.216
Bir-0.203
20439-0.202
pees-0.200
Token were
Token ID547
Feature activation+1.21e-01

Pos logit contributions
xual+1.690
 menstru+1.587
Bir+1.479
pees+1.450
20439+1.445
Neg logit contributions
rolet-1.503
orth-1.435
oppy-1.354
olls-1.277
 NTS-1.270
Token not
Token ID407
Feature activation+4.96e-01

Pos logit contributions
xual+0.256
 menstru+0.236
Bir+0.222
20439+0.217
pees+0.217
Neg logit contributions
rolet-0.244
orth-0.234
oppy-0.221
olls-0.211
 NTS-0.209
Token missing
Token ID4814
Feature activation-5.30e-01

Pos logit contributions
xual+1.031
 menstru+0.961
Bir+0.894
pees+0.875
20439+0.872
Neg logit contributions
rolet-1.018
orth-0.974
oppy-0.923
olls-0.877
 NTS-0.869
Token much
Token ID881
Feature activation-2.59e+00

Pos logit contributions
rolet+0.895
orth+0.870
oppy+0.810
olls+0.765
rays+0.759
Neg logit contributions
xual-1.271
 menstru-1.185
Bir-1.115
20439-1.104
pees-1.101
Token action
Token ID2223
Feature activation+2.39e-01

Pos logit contributions
orth+3.824
rolet+3.796
oppy+3.557
 NTS+3.406
olls+3.335
Neg logit contributions
xual-6.346
 menstru-5.795
pees-5.651
20439-5.642
Bir-5.559
Token,
Token ID11
Feature activation-3.82e-01

Pos logit contributions
xual+0.559
 menstru+0.530
Bir+0.495
pees+0.486
 ferment+0.486
Neg logit contributions
rolet-0.427
orth-0.406
oppy-0.382
olls-0.357
 NTS-0.356
Token with
Token ID351
Feature activation+4.06e-01

Pos logit contributions
rolet+0.674
orth+0.646
oppy+0.609
 NTS+0.570
olls+0.567
Neg logit contributions
xual-0.901
 menstru-0.838
Bir-0.787
pees-0.779
20439-0.778
Token the
Token ID262
Feature activation-2.02e-02

Pos logit contributions
xual+0.859
 menstru+0.804
Bir+0.747
pees+0.734
20439+0.732
Neg logit contributions
rolet-0.815
orth-0.780
oppy-0.741
olls-0.701
 NTS-0.700
Token conditions
Token ID3403
Feature activation-1.79e-02

Pos logit contributions
rolet+0.038
orth+0.036
oppy+0.034
 NTS+0.033
olls+0.032
Neg logit contributions
xual-0.045
 menstru-0.042
Bir-0.039
20439-0.039
pees-0.039
Token federal
Token ID2717
Feature activation+4.81e-01

Pos logit contributions
xual+0.282
 menstru+0.266
Bir+0.247
20439+0.243
pees+0.243
Neg logit contributions
rolet-0.224
orth-0.213
oppy-0.201
 NTS-0.190
olls-0.189
Token government
Token ID1230
Feature activation-3.51e-02

Pos logit contributions
xual+0.907
 menstru+0.853
Bir+0.779
 ferment+0.762
pees+0.761
Neg logit contributions
rolet-1.074
orth-1.032
oppy-0.983
 NTS-0.937
olls-0.934
Token.
Token ID13
Feature activation+9.10e-02

Pos logit contributions
rolet+0.062
orth+0.058
oppy+0.055
olls+0.051
 NTS+0.051
Neg logit contributions
xual-0.083
 menstru-0.079
Bir-0.074
 ferment-0.072
pees-0.072
Token
Token ID198
Feature activation-2.26e-01

Pos logit contributions
xual+0.195
 menstru+0.185
Bir+0.174
 ferment+0.168
pees+0.168
Neg logit contributions
rolet-0.179
orth-0.170
oppy-0.162
olls-0.152
rays-0.150
Token
Token ID198
Feature activation-1.82e-01

Pos logit contributions
rolet+0.390
orth+0.375
oppy+0.347
 NTS+0.332
olls+0.326
Neg logit contributions
xual-0.552
 menstru-0.515
pees-0.476
 ferment-0.475
 skelet-0.471
TokenEr
Token ID9139
Feature activation+2.44e+00

Pos logit contributions
rolet+0.363
orth+0.348
oppy+0.329
 NTS+0.310
olls+0.309
Neg logit contributions
xual-0.389
 menstru-0.365
 ferment-0.331
Bir-0.329
pees-0.328
Tokenn
Token ID77
Feature activation+5.22e-03

Pos logit contributions
xual+4.637
 menstru+4.439
Bir+4.087
pees+4.058
tur+4.015
Neg logit contributions
rolet-5.092
orth-4.858
oppy-4.652
 NTS-4.438
olls-4.376
Tokenest
Token ID395
Feature activation+2.09e-02

Pos logit contributions
xual+0.011
 menstru+0.011
Bir+0.010
 ferment+0.010
pees+0.010
Neg logit contributions
rolet-0.010
orth-0.010
oppy-0.009
olls-0.009
 NTS-0.008
Tokeno
Token ID78
Feature activation-1.91e-01

Pos logit contributions
xual+0.052
 menstru+0.050
Bir+0.047
 ferment+0.046
pees+0.046
Neg logit contributions
rolet-0.034
orth-0.032
oppy-0.030
olls-0.028
 NTS-0.028
Token Gal
Token ID5027
Feature activation-7.49e-01

Pos logit contributions
rolet+0.336
orth+0.320
oppy+0.301
 NTS+0.282
olls+0.281
Neg logit contributions
xual-0.451
 menstru-0.428
Bir-0.397
 ferment-0.392
pees-0.392
Tokenar
Token ID283
Feature activation+4.74e-01

Pos logit contributions
rolet+1.542
orth+1.500
oppy+1.412
igl+1.326
rays+1.323
Neg logit contributions
xual-1.536
 menstru-1.447
Bir-1.336
20439-1.325
 ferment-1.312
Token Sciences
Token ID13473
Feature activation+2.83e-01

Pos logit contributions
xual+1.419
 menstru+1.349
Bir+1.243
 ferment+1.225
pees+1.205
Neg logit contributions
rolet-1.478
orth-1.374
oppy-1.320
olls-1.244
 NTS-1.237
Token in
Token ID287
Feature activation+2.67e-01

Pos logit contributions
xual+0.645
 menstru+0.611
Bir+0.567
pees+0.560
 ferment+0.560
Neg logit contributions
rolet-0.521
orth-0.499
oppy-0.466
 NTS-0.439
olls-0.437
Token Memory
Token ID14059
Feature activation+7.45e-02

Pos logit contributions
xual+0.598
 menstru+0.570
Bir+0.530
 ferment+0.521
pees+0.517
Neg logit contributions
rolet-0.501
orth-0.473
oppy-0.448
olls-0.420
 NTS-0.416
Token of
Token ID286
Feature activation+2.94e-01

Pos logit contributions
xual+0.183
 menstru+0.175
Bir+0.164
 ferment+0.161
20439+0.159
Neg logit contributions
rolet-0.124
orth-0.116
oppy-0.111
olls-0.103
rays-0.101
Token Alfred
Token ID22044
Feature activation+1.84e-01

Pos logit contributions
xual+0.523
 menstru+0.490
Bir+0.445
 ferment+0.435
pees+0.434
Neg logit contributions
rolet-0.690
orth-0.663
oppy-0.633
olls-0.603
 NTS-0.601
Token Nobel
Token ID20715
Feature activation+2.19e+00

Pos logit contributions
xual+0.349
 menstru+0.320
Bir+0.291
pees+0.289
20439+0.289
Neg logit contributions
rolet-0.412
orth-0.402
oppy-0.380
 NTS-0.366
olls-0.360
Token,
Token ID11
Feature activation+2.89e-02

Pos logit contributions
xual+4.609
 menstru+4.388
Bir+4.078
 ferment+3.993
pees+3.937
Neg logit contributions
rolet-4.299
orth-4.034
oppy-3.943
olls-3.671
rays-3.647
Token founder
Token ID9119
Feature activation-6.04e-01

Pos logit contributions
xual+0.064
 menstru+0.061
Bir+0.056
pees+0.055
 ferment+0.055
Neg logit contributions
rolet-0.055
orth-0.053
oppy-0.049
 NTS-0.047
olls-0.046
Token of
Token ID286
Feature activation-3.65e-01

Pos logit contributions
rolet+0.968
orth+0.912
oppy+0.851
olls+0.789
 NTS+0.785
Neg logit contributions
xual-1.521
 menstru-1.452
Bir-1.361
 ferment-1.341
pees-1.337
Token the
Token ID262
Feature activation-2.55e-01

Pos logit contributions
rolet+0.742
orth+0.715
oppy+0.671
 NTS+0.637
olls+0.635
Neg logit contributions
xual-0.764
 menstru-0.713
Bir-0.658
pees-0.652
20439-0.649
Token Nobel
Token ID20715
Feature activation+1.55e+00

Pos logit contributions
rolet+0.495
orth+0.474
oppy+0.446
 NTS+0.424
olls+0.421
Neg logit contributions
xual-0.559
 menstru-0.523
Bir-0.484
pees-0.480
20439-0.480
Token,
Token ID11
Feature activation+6.34e-02

Pos logit contributions
rolet+0.821
orth+0.782
oppy+0.727
olls+0.690
 NTS+0.677
Neg logit contributions
xual-1.038
 menstru-0.972
Bir-0.907
pees-0.894
20439-0.892
Token who
Token ID508
Feature activation-8.77e-01

Pos logit contributions
xual+0.140
 menstru+0.131
Bir+0.122
pees+0.121
20439+0.120
Neg logit contributions
rolet-0.121
orth-0.117
oppy-0.110
 NTS-0.103
olls-0.103
Token had
Token ID550
Feature activation+1.09e-01

Pos logit contributions
rolet+1.618
orth+1.580
oppy+1.461
olls+1.401
 NTS+1.369
Neg logit contributions
xual-1.988
 menstru-1.817
20439-1.720
Bir-1.717
pees-1.703
Token scored
Token ID7781
Feature activation+1.32e+00

Pos logit contributions
xual+0.236
 menstru+0.220
Bir+0.206
20439+0.203
pees+0.203
Neg logit contributions
rolet-0.212
orth-0.204
oppy-0.192
olls-0.182
 NTS-0.182
Token a
Token ID257
Feature activation+9.80e-03

Pos logit contributions
xual+2.731
 menstru+2.572
Bir+2.374
pees+2.325
 ferment+2.323
Neg logit contributions
rolet-2.725
orth-2.609
oppy-2.475
olls-2.341
 NTS-2.336
Token hat
Token ID6877
Feature activation+2.65e+00

Pos logit contributions
xual+0.022
 menstru+0.021
Bir+0.019
pees+0.019
20439+0.019
Neg logit contributions
rolet-0.018
orth-0.018
oppy-0.017
olls-0.016
 NTS-0.016
Token-
Token ID12
Feature activation-2.95e-01

Pos logit contributions
xual+5.875
 menstru+5.588
Bir+5.250
 ferment+5.163
pees+5.121
Neg logit contributions
rolet-4.868
orth-4.564
oppy-4.367
olls-4.126
 NTS-4.117
Tokentr
Token ID2213
Feature activation-3.05e-02

Pos logit contributions
rolet+0.649
orth+0.629
oppy+0.592
olls+0.560
rays+0.559
Neg logit contributions
xual-0.573
 menstru-0.538
Bir-0.485
 ferment-0.483
20439-0.481
Tokenick
Token ID624
Feature activation-2.65e-01

Pos logit contributions
rolet+0.035
orth+0.033
oppy+0.031
olls+0.027
rays+0.025
Neg logit contributions
xual-0.091
 menstru-0.087
Bir-0.082
20439-0.082
 ferment-0.081
Token,
Token ID11
Feature activation-1.34e-01

Pos logit contributions
rolet+0.446
orth+0.427
oppy+0.398
olls+0.369
 NTS+0.367
Neg logit contributions
xual-0.646
 menstru-0.612
Bir-0.571
pees-0.569
20439-0.566
Token and
Token ID290
Feature activation+1.14e-01

Pos logit contributions
rolet+0.244
orth+0.235
oppy+0.222
 NTS+0.207
olls+0.206
Neg logit contributions
xual-0.307
 menstru-0.287
Bir-0.267
pees-0.264
20439-0.263
Token,
Token ID11
Feature activation+1.03e-01

Pos logit contributions
xual+3.039
 menstru+2.889
Bir+2.678
 ferment+2.649
pees+2.616
Neg logit contributions
rolet-2.592
orth-2.447
oppy-2.323
olls-2.184
 NTS-2.160
Token the
Token ID262
Feature activation+9.18e-02

Pos logit contributions
xual+0.221
 menstru+0.207
Bir+0.192
20439+0.189
pees+0.188
Neg logit contributions
rolet-0.204
orth-0.196
oppy-0.185
 NTS-0.175
olls-0.175
Token intersection
Token ID16246
Feature activation+4.97e-01

Pos logit contributions
xual+0.201
 menstru+0.188
Bir+0.174
20439+0.172
pees+0.171
Neg logit contributions
rolet-0.179
orth-0.171
oppy-0.162
 NTS-0.154
olls-0.153
Token of
Token ID286
Feature activation-1.29e-01

Pos logit contributions
xual+1.160
 menstru+1.104
Bir+1.028
 ferment+1.012
pees+1.008
Neg logit contributions
rolet-0.888
orth-0.841
oppy-0.792
olls-0.740
 NTS-0.736
Token Y
Token ID575
Feature activation+1.55e+00

Pos logit contributions
rolet+0.246
orth+0.236
oppy+0.222
 NTS+0.210
olls+0.210
Neg logit contributions
xual-0.286
 menstru-0.268
Bir-0.248
20439-0.245
pees-0.244
Tokenonge
Token ID14220
Feature activation+2.21e+00

Pos logit contributions
xual+2.598
 menstru+2.423
Bir+2.209
 ferment+2.153
pees+2.146
Neg logit contributions
rolet-3.781
orth-3.600
oppy-3.459
olls-3.297
 NTS-3.297
Token and
Token ID290
Feature activation+3.79e-01

Pos logit contributions
xual+4.704
 menstru+4.508
Bir+4.219
 ferment+4.159
pees+4.120
Neg logit contributions
rolet-4.306
orth-4.036
oppy-3.827
olls-3.599
 NTS-3.574
Token E
Token ID412
Feature activation+8.97e-01

Pos logit contributions
xual+0.800
 menstru+0.748
Bir+0.690
20439+0.679
pees+0.677
Neg logit contributions
rolet-0.765
orth-0.739
oppy-0.698
olls-0.663
 NTS-0.660
Tokengl
Token ID4743
Feature activation-6.74e-01

Pos logit contributions
xual+2.670
 menstru+2.566
Bir+2.430
 ferment+2.400
pees+2.394
Neg logit contributions
rolet-1.026
orth-0.945
oppy-0.854
olls-0.762
 NTS-0.755
Tokeninton
Token ID2371
Feature activation+3.08e-01

Pos logit contributions
rolet+1.057
orth+1.047
oppy+0.954
olls+0.882
oise+0.880
Neg logit contributions
xual-1.716
 menstru-1.640
20439-1.555
Bir-1.525
 ferment-1.490
Token will
Token ID481
Feature activation-1.80e-01

Pos logit contributions
xual+0.704
 menstru+0.665
Bir+0.617
20439+0.608
 ferment+0.605
Neg logit contributions
rolet-0.569
orth-0.547
oppy-0.513
olls-0.485
 NTS-0.482
Token red
Token ID2266
Feature activation-1.35e-01

Pos logit contributions
xual+1.588
 menstru+1.494
Bir+1.374
 ferment+1.346
pees+1.344
Neg logit contributions
rolet-1.678
orth-1.606
oppy-1.527
olls-1.446
 NTS-1.441
Token and
Token ID290
Feature activation+4.22e-01

Pos logit contributions
rolet+0.320
orth+0.311
oppy+0.297
olls+0.283
rays+0.281
Neg logit contributions
xual-0.237
 menstru-0.218
Bir-0.198
20439-0.195
pees-0.192
Token yellow
Token ID7872
Feature activation+2.23e-01

Pos logit contributions
xual+0.901
 menstru+0.847
Bir+0.785
pees+0.772
20439+0.768
Neg logit contributions
rolet-0.842
orth-0.806
oppy-0.765
olls-0.719
 NTS-0.718
Token peppers
Token ID31804
Feature activation-3.20e-01

Pos logit contributions
xual+0.415
 menstru+0.386
Bir+0.354
20439+0.345
pees+0.344
Neg logit contributions
rolet-0.505
orth-0.486
oppy-0.464
olls-0.441
 NTS-0.439
Token,
Token ID11
Feature activation+3.10e-01

Pos logit contributions
rolet+0.565
orth+0.537
oppy+0.506
olls+0.474
 NTS+0.467
Neg logit contributions
xual-0.752
 menstru-0.712
Bir-0.668
20439-0.655
pees-0.652
Token cour
Token ID1093
Feature activation+2.19e+00

Pos logit contributions
xual+0.597
 menstru+0.556
Bir+0.510
pees+0.499
20439+0.499
Neg logit contributions
rolet-0.684
orth-0.658
oppy-0.627
olls-0.595
 NTS-0.593
Tokenget
Token ID1136
Feature activation+3.82e-01

Pos logit contributions
xual+2.869
 menstru+2.596
Bir+2.259
pees+2.238
 ferment+2.194
Neg logit contributions
rolet-6.090
orth-5.819
oppy-5.664
 NTS-5.460
olls-5.387
Tokentes
Token ID4879
Feature activation+1.26e+00

Pos logit contributions
xual+0.655
 menstru+0.611
Bir+0.552
 ferment+0.541
pees+0.538
Neg logit contributions
rolet-0.918
orth-0.881
oppy-0.844
olls-0.804
 NTS-0.803
Token,
Token ID11
Feature activation+2.62e-01

Pos logit contributions
xual+2.765
 menstru+2.624
Bir+2.415
 ferment+2.407
pees+2.385
Neg logit contributions
rolet-2.413
orth-2.282
oppy-2.158
olls-2.021
 NTS-2.015
Token basil
Token ID37792
Feature activation-4.01e-01

Pos logit contributions
xual+0.512
 menstru+0.479
Bir+0.440
pees+0.431
20439+0.429
Neg logit contributions
rolet-0.568
orth-0.545
oppy-0.519
olls-0.491
 NTS-0.490
Token and
Token ID290
Feature activation+6.09e-01

Pos logit contributions
rolet+0.716
orth+0.686
oppy+0.647
olls+0.605
 NTS+0.597
Neg logit contributions
xual-0.940
 menstru-0.885
Bir-0.826
20439-0.810
pees-0.809
Token).[
Token ID42669
Feature activation+6.07e-01

Pos logit contributions
rolet+1.088
orth+1.039
oppy+0.960
olls+0.906
 NTS+0.903
Neg logit contributions
xual-1.602
 menstru-1.516
Bir-1.427
20439-1.399
pees-1.399
Token188
Token ID20356
Feature activation+6.42e-01

Pos logit contributions
xual+1.028
 menstru+0.956
Bir+0.870
 ferment+0.843
pees+0.839
Neg logit contributions
rolet-1.476
orth-1.413
oppy-1.360
olls-1.296
 NTS-1.293
Token]
Token ID60
Feature activation+9.69e-02

Pos logit contributions
xual+1.392
 menstru+1.319
Bir+1.231
 ferment+1.203
20439+1.185
Neg logit contributions
rolet-1.247
orth-1.170
oppy-1.120
olls-1.050
rays-1.048
Token The
Token ID383
Feature activation-3.82e-01

Pos logit contributions
xual+0.214
 menstru+0.201
Bir+0.185
pees+0.184
 ferment+0.184
Neg logit contributions
rolet-0.187
orth-0.179
oppy-0.168
 NTS-0.161
olls-0.160
Token party
Token ID2151
Feature activation+3.31e-01

Pos logit contributions
rolet+0.716
orth+0.686
oppy+0.647
olls+0.619
 NTS+0.618
Neg logit contributions
xual-0.855
 menstru-0.801
Bir-0.750
pees-0.739
20439-0.737
Token with
Token ID351
Feature activation+6.37e-01

Pos logit contributions
xual+0.742
 menstru+0.701
Bir+0.652
pees+0.641
 ferment+0.639
Neg logit contributions
rolet-0.620
orth-0.593
oppy-0.557
olls-0.526
 NTS-0.523
Token majority
Token ID3741
Feature activation+6.78e-01

Pos logit contributions
xual+1.290
 menstru+1.214
Bir+1.119
 ferment+1.096
pees+1.094
Neg logit contributions
rolet-1.338
orth-1.281
oppy-1.215
olls-1.153
 NTS-1.147
Token support
Token ID1104
Feature activation+3.92e-01

Pos logit contributions
xual+1.515
 menstru+1.436
Bir+1.335
 ferment+1.310
pees+1.309
Neg logit contributions
rolet-1.278
orth-1.217
oppy-1.147
olls-1.080
 NTS-1.077
Token in
Token ID287
Feature activation+4.65e-01

Pos logit contributions
xual+0.879
 menstru+0.832
Bir+0.776
 ferment+0.759
pees+0.759
Neg logit contributions
rolet-0.736
orth-0.701
oppy-0.659
olls-0.623
 NTS-0.618
Token the
Token ID262
Feature activation+2.91e-02

Pos logit contributions
xual+0.947
 menstru+0.880
Bir+0.821
20439+0.806
pees+0.804
Neg logit contributions
rolet-0.966
orth-0.931
oppy-0.881
olls-0.848
 NTS-0.840
Token House
Token ID2097
Feature activation+6.91e-01

Pos logit contributions
xual+0.063
 menstru+0.059
Bir+0.055
20439+0.055
pees+0.054
Neg logit contributions
rolet-0.057
orth-0.054
oppy-0.051
olls-0.049
 NTS-0.049
Token the
Token ID262
Feature activation+6.45e-02

Pos logit contributions
xual+0.841
 menstru+0.792
Bir+0.730
 ferment+0.714
pees+0.714
Neg logit contributions
rolet-0.928
orth-0.892
oppy-0.847
olls-0.806
 NTS-0.805
Token earth
Token ID4534
Feature activation+6.14e-01

Pos logit contributions
xual+0.146
 menstru+0.138
Bir+0.130
pees+0.128
20439+0.128
Neg logit contributions
rolet-0.118
orth-0.113
oppy-0.106
 NTS-0.101
olls-0.100
Token
Token ID960
Feature activation+1.26e-01

Pos logit contributions
xual+1.400
 menstru+1.332
Bir+1.237
 ferment+1.218
pees+1.213
Neg logit contributions
rolet-1.130
orth-1.073
oppy-1.012
olls-0.947
 NTS-0.943
Tokenfrom
Token ID6738
Feature activation+3.48e-01

Pos logit contributions
xual+0.271
 menstru+0.256
Bir+0.234
 ferment+0.234
20439+0.232
Neg logit contributions
rolet-0.247
orth-0.239
oppy-0.224
olls-0.212
 NTS-0.211
Token Armenia
Token ID32369
Feature activation-2.53e-01

Pos logit contributions
xual+0.703
 menstru+0.658
Bir+0.609
20439+0.599
pees+0.597
Neg logit contributions
rolet-0.726
orth-0.697
oppy-0.662
olls-0.631
 NTS-0.631
Token,
Token ID11
Feature activation+5.15e-01

Pos logit contributions
rolet+0.473
orth+0.451
oppy+0.422
 NTS+0.398
olls+0.398
Neg logit contributions
xual-0.570
 menstru-0.541
Bir-0.502
 ferment-0.494
pees-0.493
Token Arts
Token ID11536
Feature activation+9.06e-01

Pos logit contributions
xual+0.839
 menstru+0.776
Bir+0.696
pees+0.684
20439+0.683
Neg logit contributions
rolet-1.278
orth-1.234
oppy-1.180
 NTS-1.133
olls-1.132
Tokenakh
Token ID11322
Feature activation+5.46e-02

Pos logit contributions
xual+1.341
 menstru+1.241
Bir+1.098
20439+1.071
 ferment+1.068
Neg logit contributions
rolet-2.391
orth-2.326
oppy-2.225
olls-2.133
 NTS-2.125
Token,
Token ID11
Feature activation+2.58e-01

Pos logit contributions
xual+0.124
 menstru+0.117
Bir+0.109
 ferment+0.107
pees+0.107
Neg logit contributions
rolet-0.102
orth-0.096
oppy-0.091
olls-0.085
 NTS-0.085
Token and
Token ID290
Feature activation+1.50e-01

Pos logit contributions
xual+0.467
 menstru+0.434
Bir+0.392
20439+0.391
pees+0.389
Neg logit contributions
rolet-0.592
orth-0.574
oppy-0.546
 NTS-0.525
olls-0.525
Token Jav
Token ID49247
Feature activation-7.83e-01

Pos logit contributions
xual+0.274
 menstru+0.257
Bir+0.233
20439+0.232
pees+0.232
Neg logit contributions
rolet-0.339
orth-0.328
oppy-0.311
olls-0.300
 NTS-0.300
Tokens
Token ID82
Feature activation+9.34e-02

Pos logit contributions
xual+0.171
 menstru+0.162
Bir+0.148
 ferment+0.146
pees+0.146
Neg logit contributions
rolet-0.166
orth-0.162
oppy-0.152
 NTS-0.144
rays-0.143
Token micro
Token ID4580
Feature activation-2.08e-01

Pos logit contributions
xual+0.203
 menstru+0.190
Bir+0.178
pees+0.174
20439+0.174
Neg logit contributions
rolet-0.182
orth-0.174
oppy-0.165
 NTS-0.158
olls-0.157
Token circuitry
Token ID42344
Feature activation-1.04e+00

Pos logit contributions
rolet+0.418
orth+0.397
oppy+0.375
 NTS+0.354
olls+0.353
Neg logit contributions
xual-0.447
 menstru-0.419
Bir-0.388
pees-0.379
 ferment-0.378
Token it
Token ID340
Feature activation+4.07e-01

Pos logit contributions
rolet+1.940
orth+1.886
oppy+1.777
 NTS+1.738
rays+1.683
Neg logit contributions
xual-2.294
 menstru-2.136
Bir-2.020
pees-1.987
20439-1.973
Token is
Token ID318
Feature activation+1.38e-01

Pos logit contributions
xual+0.901
 menstru+0.852
Bir+0.791
pees+0.777
 ferment+0.777
Neg logit contributions
rolet-0.776
orth-0.745
oppy-0.699
olls-0.662
 NTS-0.659
Token not
Token ID407
Feature activation+4.83e-01

Pos logit contributions
xual+0.275
 menstru+0.255
Bir+0.236
pees+0.232
20439+0.231
Neg logit contributions
rolet-0.293
orth-0.284
oppy-0.267
 NTS-0.257
olls-0.254
Token impossible
Token ID5340
Feature activation-1.25e+00

Pos logit contributions
xual+0.988
 menstru+0.926
Bir+0.854
pees+0.839
20439+0.836
Neg logit contributions
rolet-1.003
orth-0.966
oppy-0.911
 NTS-0.866
olls-0.864
Token.
Token ID13
Feature activation-2.23e-01

Pos logit contributions
rolet+2.120
orth+2.014
oppy+1.858
 NTS+1.793
rays+1.741
Neg logit contributions
xual-2.996
 menstru-2.825
Bir-2.627
pees-2.624
20439-2.603
Token It
Token ID632
Feature activation-4.96e-01

Pos logit contributions
rolet+0.413
orth+0.396
oppy+0.369
 NTS+0.361
olls+0.348
Neg logit contributions
xual-0.510
 menstru-0.481
pees-0.440
 ferment-0.440
Bir-0.438
Token is
Token ID318
Feature activation+7.23e-02

Pos logit contributions
rolet+0.915
orth+0.888
oppy+0.825
olls+0.792
rays+0.781
Neg logit contributions
xual-1.116
 menstru-1.051
Bir-0.975
20439-0.967
pees-0.960
Token also
Token ID635
Feature activation+2.10e-01

Pos logit contributions
xual+0.150
 menstru+0.140
Bir+0.130
pees+0.128
20439+0.128
Neg logit contributions
rolet-0.148
orth-0.143
oppy-0.134
 NTS-0.129
olls-0.128
Token unsupported
Token ID24222
Feature activation-3.77e-01

Pos logit contributions
xual+1.121
 menstru+1.044
Bir+0.987
pees+0.968
20439+0.964
Neg logit contributions
rolet-0.868
orth-0.832
oppy-0.777
 NTS-0.748
rays-0.723
Token on
Token ID319
Feature activation-2.90e-01

Pos logit contributions
rolet+0.529
orth+0.507
oppy+0.452
 NTS+0.438
rays+0.418
Neg logit contributions
xual-1.027
 menstru-0.972
Bir-0.910
 ferment-0.903
pees-0.901
Token your
Token ID534
Feature activation+9.57e-03

Pos logit contributions
rolet+0.497
orth+0.481
oppy+0.453
 NTS+0.441
olls+0.425
Neg logit contributions
xual-0.690
 menstru-0.638
Bir-0.604
pees-0.594
 ferment-0.592
Token device
Token ID3335
Feature activation+7.77e-01

Pos logit contributions
xual+0.023
 menstru+0.021
Bir+0.020
+0.020
pees+0.020
Neg logit contributions
rolet-0.016
orth-0.016
oppy-0.015
 NTS-0.014
olls-0.014
Token Media
Token ID6343
Feature activation+1.20e-01

Pos logit contributions
xual+1.616
 menstru+1.520
Bir+1.395
 ferment+1.380
pees+1.374
Neg logit contributions
rolet-1.595
orth-1.525
oppy-1.452
 NTS-1.381
olls-1.365
Token caption
Token ID8305
Feature activation+4.50e-01

Pos logit contributions
xual+0.204
 menstru+0.188
Bir+0.170
pees+0.168
20439+0.167
Neg logit contributions
rolet-0.289
orth-0.281
oppy-0.266
 NTS-0.256
rays-0.254
Token Prof
Token ID4415
Feature activation-1.21e+00

Pos logit contributions
xual+1.019
 menstru+0.966
Bir+0.897
 ferment+0.883
pees+0.881
Neg logit contributions
rolet-0.836
orth-0.796
oppy-0.749
 NTS-0.705
olls-0.703
Token Re
Token ID797
Feature activation-3.34e-01

Pos logit contributions
rolet+2.151
orth+2.081
oppy+1.928
olls+1.831
 NTS+1.829
Neg logit contributions
xual-2.782
 menstru-2.661
Bir-2.440
20439-2.439
 ferment-2.414
Tokeniner
Token ID7274
Feature activation+1.53e-03

Pos logit contributions
rolet+0.709
orth+0.686
oppy+0.651
igl+0.609
olls+0.608
Neg logit contributions
xual-0.671
 menstru-0.633
Bir-0.577
20439-0.573
 ferment-0.569
Token R
Token ID371
Feature activation+6.20e-01

Pos logit contributions
xual+0.004
 menstru+0.003
Bir+0.003
 ferment+0.003
pees+0.003
Neg logit contributions
rolet-0.003
orth-0.003
oppy-0.002
olls-0.002
 NTS-0.002
Tokenumm
Token ID13929
Feature activation-3.32e-01

Pos logit contributions
xual+1.318
 menstru+1.247
Bir+1.154
 ferment+1.133
pees+1.129
Neg logit contributions
rolet-1.235
orth-1.176
oppy-1.115
olls-1.050
 NTS-1.047
Token he
Token ID339
Feature activation+6.08e-01

Pos logit contributions
xual+0.594
 menstru+0.561
Bir+0.522
 ferment+0.515
pees+0.515
Neg logit contributions
rolet-0.489
orth-0.467
oppy-0.439
olls-0.412
 NTS-0.411
Token said
Token ID531
Feature activation+2.02e-01

Pos logit contributions
xual+1.561
 menstru+1.489
Bir+1.398
 ferment+1.378
pees+1.373
Neg logit contributions
rolet-0.945
orth-0.890
oppy-0.828
olls-0.765
 NTS-0.760
Token.
Token ID13
Feature activation+1.36e-01

Pos logit contributions
xual+0.464
 menstru+0.442
Bir+0.410
 ferment+0.404
pees+0.402
Neg logit contributions
rolet-0.370
orth-0.350
oppy-0.331
olls-0.309
 NTS-0.308
Token
Token ID564
Feature activation-2.50e-01

Pos logit contributions
xual+0.296
 menstru+0.279
Bir+0.256
 ferment+0.255
pees+0.254
Neg logit contributions
rolet-0.268
orth-0.256
oppy-0.241
 NTS-0.228
olls-0.227
Token
Token ID250
Feature activation-4.04e-01

Pos logit contributions
rolet+0.563
orth+0.540
oppy+0.515
olls+0.489
 NTS+0.488
Neg logit contributions
xual-0.468
 menstru-0.440
Bir-0.402
 ferment-0.393
pees-0.392
TokenSomething
Token ID22210
Feature activation+1.97e+00

Pos logit contributions
rolet+0.848
orth+0.824
oppy+0.771
olls+0.737
rays+0.736
Neg logit contributions
xual-0.818
 menstru-0.761
 ferment-0.696
20439-0.685
pees-0.678
Token
Token ID447
Feature activation+2.05e-01

Pos logit contributions
xual+4.187
 menstru+3.985
Bir+3.673
 ferment+3.611
pees+3.586
Neg logit contributions
rolet-3.929
orth-3.715
oppy-3.533
olls-3.313
 NTS-3.289
Token
Token ID247
Feature activation+1.75e-01

Pos logit contributions
xual+0.363
 menstru+0.339
Bir+0.308
 ferment+0.301
pees+0.300
Neg logit contributions
rolet-0.481
orth-0.462
oppy-0.442
olls-0.421
rays-0.420
Tokens
Token ID82
Feature activation+9.17e-02

Pos logit contributions
xual+0.369
 menstru+0.350
Bir+0.324
 ferment+0.318
pees+0.316
Neg logit contributions
rolet-0.348
orth-0.338
oppy-0.317
olls-0.301
rays-0.299
Token going
Token ID1016
Feature activation+9.17e-01

Pos logit contributions
xual+0.201
 menstru+0.189
Bir+0.176
20439+0.173
pees+0.172
Neg logit contributions
rolet-0.177
orth-0.171
oppy-0.160
olls-0.152
 NTS-0.150
Token to
Token ID284
Feature activation+3.52e-01

Pos logit contributions
xual+2.037
 menstru+1.960
Bir+1.813
 ferment+1.803
pees+1.771
Neg logit contributions
rolet-1.709
orth-1.616
oppy-1.531
olls-1.416
 NTS-1.408
Token when
Token ID618
Feature activation+2.09e-01

Pos logit contributions
rolet+0.036
orth+0.034
oppy+0.032
 NTS+0.030
olls+0.030
Neg logit contributions
xual-0.050
 menstru-0.047
Bir-0.045
pees-0.044
20439-0.044
Token D
Token ID360
Feature activation+2.15e-01

Pos logit contributions
xual+0.428
 menstru+0.394
Bir+0.372
20439+0.367
pees+0.366
Neg logit contributions
rolet-0.423
orth-0.413
oppy-0.389
olls-0.372
 NTS-0.372
TokenNR
Token ID24723
Feature activation+7.93e-01

Pos logit contributions
xual+0.466
 menstru+0.439
Bir+0.405
 ferment+0.400
20439+0.396
Neg logit contributions
rolet-0.424
orth-0.406
oppy-0.382
olls-0.360
 NTS-0.356
Token biologists
Token ID43149
Feature activation-5.45e-01

Pos logit contributions
xual+1.725
 menstru+1.629
Bir+1.512
 ferment+1.490
20439+1.485
Neg logit contributions
rolet-1.542
orth-1.480
oppy-1.384
olls-1.320
 NTS-1.314
Token take
Token ID1011
Feature activation-9.91e-01

Pos logit contributions
rolet+1.011
orth+0.973
oppy+0.912
olls+0.868
 NTS+0.866
Neg logit contributions
xual-1.220
 menstru-1.121
Bir-1.076
20439-1.062
pees-1.056
Token groups
Token ID2628
Feature activation+8.37e-03

Pos logit contributions
rolet+1.844
orth+1.789
oppy+1.670
olls+1.617
 NTS+1.605
Neg logit contributions
xual-2.152
 menstru-2.008
Bir-1.905
20439-1.898
pees-1.870
Token of
Token ID286
Feature activation+2.19e-01

Pos logit contributions
xual+0.021
 menstru+0.020
Bir+0.019
pees+0.018
 ferment+0.018
Neg logit contributions
rolet-0.014
orth-0.013
oppy-0.012
 NTS-0.011
olls-0.011
Token people
Token ID661
Feature activation-1.29e-01

Pos logit contributions
xual+0.406
 menstru+0.374
Bir+0.349
20439+0.341
pees+0.339
Neg logit contributions
rolet-0.488
orth-0.474
oppy-0.447
 NTS-0.432
olls-0.432
Token to
Token ID284
Feature activation+1.23e-01

Pos logit contributions
rolet+0.221
orth+0.211
oppy+0.197
 NTS+0.186
olls+0.186
Neg logit contributions
xual-0.310
 menstru-0.289
Bir-0.274
pees-0.270
20439-0.270
Token dens
Token ID29509
Feature activation+9.20e-01

Pos logit contributions
xual+0.260
 menstru+0.241
Bir+0.224
20439+0.222
pees+0.219
Neg logit contributions
rolet-0.248
orth-0.237
oppy-0.225
olls-0.214
 NTS-0.213
Token during
Token ID1141
Feature activation+2.23e-01

Pos logit contributions
xual+2.096
 menstru+1.992
Bir+1.853
 ferment+1.822
pees+1.816
Neg logit contributions
rolet-1.695
orth-1.610
oppy-1.518
olls-1.422
 NTS-1.416
Token Government
Token ID5070
Feature activation-6.36e-01

Pos logit contributions
rolet+0.540
orth+0.516
oppy+0.489
 NTS+0.466
olls+0.461
Neg logit contributions
xual-0.575
 menstru-0.538
Bir-0.501
 ferment-0.490
pees-0.490
Token should
Token ID815
Feature activation-3.37e-01

Pos logit contributions
rolet+1.236
orth+1.181
oppy+1.108
 NTS+1.055
rays+1.044
Neg logit contributions
xual-1.385
 menstru-1.289
Bir-1.217
20439-1.184
pees-1.183
Token immediately
Token ID3393
Feature activation-1.71e-03

Pos logit contributions
rolet+0.675
orth+0.639
oppy+0.600
 NTS+0.573
olls+0.566
Neg logit contributions
xual-0.720
 menstru-0.665
Bir-0.638
20439-0.622
pees-0.620
Token bring
Token ID2222
Feature activation+2.45e-01

Pos logit contributions
rolet+0.003
orth+0.003
oppy+0.003
 NTS+0.003
olls+0.003
Neg logit contributions
xual-0.004
 menstru-0.003
Bir-0.003
20439-0.003
pees-0.003
Token amendments
Token ID17835
Feature activation-2.59e-02

Pos logit contributions
xual+0.599
 menstru+0.569
Bir+0.535
pees+0.524
 ferment+0.523
Neg logit contributions
rolet-0.410
orth-0.388
oppy-0.362
 NTS-0.339
olls-0.337
Token to
Token ID284
Feature activation-2.51e-01

Pos logit contributions
rolet+0.047
orth+0.045
oppy+0.042
 NTS+0.040
olls+0.040
Neg logit contributions
xual-0.059
 menstru-0.056
Bir-0.053
 ferment-0.052
pees-0.052
Token the
Token ID262
Feature activation-2.90e-01

Pos logit contributions
rolet+0.515
orth+0.492
oppy+0.466
 NTS+0.441
olls+0.440
Neg logit contributions
xual-0.521
 menstru-0.490
Bir-0.454
 ferment-0.444
pees-0.443
Token present
Token ID1944
Feature activation-2.90e-01

Pos logit contributions
rolet+0.521
orth+0.495
oppy+0.465
 NTS+0.440
olls+0.437
Neg logit contributions
xual-0.676
 menstru-0.637
Bir-0.597
pees-0.586
 ferment-0.584
Token Motor
Token ID12533
Feature activation-4.77e-01

Pos logit contributions
rolet+0.499
orth+0.474
oppy+0.441
 NTS+0.419
olls+0.415
Neg logit contributions
xual-0.698
 menstru-0.659
Bir-0.618
pees-0.610
 ferment-0.605
Token Vehicle
Token ID21501
Feature activation-3.89e-01

Pos logit contributions
rolet+0.800
orth+0.755
oppy+0.709
olls+0.659
rays+0.654
Neg logit contributions
xual-1.150
 menstru-1.103
Bir-1.035
 ferment-1.014
pees-1.008
Token Act
Token ID2191
Feature activation-1.49e+00

Pos logit contributions
rolet+0.708
orth+0.670
oppy+0.633
olls+0.593
rays+0.587
Neg logit contributions
xual-0.894
 menstru-0.852
Bir-0.793
 ferment-0.780
pees-0.774
Token users
Token ID2985
Feature activation+3.24e-01

Pos logit contributions
rolet+0.082
orth+0.079
oppy+0.076
 NTS+0.072
olls+0.071
Neg logit contributions
xual-0.074
 menstru-0.069
Bir-0.063
pees-0.062
20439-0.062
Token to
Token ID284
Feature activation+2.96e-01

Pos logit contributions
xual+0.737
 menstru+0.700
Bir+0.651
 ferment+0.640
pees+0.638
Neg logit contributions
rolet-0.599
orth-0.568
oppy-0.536
olls-0.503
 NTS-0.500
Token install
Token ID2721
Feature activation-5.92e-02

Pos logit contributions
xual+0.643
 menstru+0.602
Bir+0.568
20439+0.558
pees+0.555
Neg logit contributions
rolet-0.580
orth-0.553
oppy-0.521
 NTS-0.496
olls-0.488
Token and
Token ID290
Feature activation-1.83e-01

Pos logit contributions
rolet+0.111
orth+0.106
oppy+0.101
 NTS+0.095
olls+0.094
Neg logit contributions
xual-0.133
 menstru-0.125
Bir-0.117
pees-0.115
20439-0.114
Token remove
Token ID4781
Feature activation+1.42e-01

Pos logit contributions
rolet+0.360
orth+0.344
oppy+0.323
 NTS+0.309
olls+0.304
Neg logit contributions
xual-0.396
 menstru-0.370
Bir-0.348
20439-0.341
pees-0.340
Token.
Token ID13
Feature activation+2.16e-02

Pos logit contributions
xual+0.300
 menstru+0.282
Bir+0.261
pees+0.256
20439+0.256
Neg logit contributions
rolet-0.285
orth-0.274
oppy-0.260
 NTS-0.246
olls-0.244
TokenMS
Token ID5653
Feature activation-2.84e-01

Pos logit contributions
xual+0.048
 menstru+0.046
 ferment+0.042
Bir+0.042
pees+0.042
Neg logit contributions
rolet-0.041
orth-0.039
oppy-0.037
 NTS-0.035
olls-0.035
TokenI
Token ID40
Feature activation-3.95e-01

Pos logit contributions
rolet+0.620
orth+0.605
oppy+0.567
igl+0.537
olls+0.535
Neg logit contributions
xual-0.543
 menstru-0.508
 ferment-0.466
pees-0.465
20439-0.463
Token exclusive
Token ID8568
Feature activation+3.97e-01

Pos logit contributions
rolet+0.749
orth+0.720
oppy+0.668
 NTS+0.639
olls+0.628
Neg logit contributions
xual-0.875
 menstru-0.828
Bir-0.768
20439-0.763
pees-0.760
Token Un
Token ID791
Feature activation-1.35e-01

Pos logit contributions
xual+0.890
 menstru+0.839
Bir+0.779
pees+0.769
 ferment+0.766
Neg logit contributions
rolet-0.751
orth-0.718
oppy-0.675
 NTS-0.639
olls-0.632
Tokenlocked
Token ID24162
Feature activation-6.02e-01

Pos logit contributions
rolet+0.249
orth+0.237
oppy+0.224
olls+0.209
 NTS+0.208
Neg logit contributions
xual-0.306
 menstru-0.291
Bir-0.270
 ferment-0.266
pees-0.265
Token,
Token ID11
Feature activation+2.45e-01

Pos logit contributions
xual+0.063
 menstru+0.060
Bir+0.055
pees+0.054
 ferment+0.054
Neg logit contributions
rolet-0.055
orth-0.053
oppy-0.050
olls-0.047
 NTS-0.047
Token
Token ID447
Feature activation-3.67e-02

Pos logit contributions
xual+0.524
 menstru+0.495
Bir+0.459
pees+0.450
 ferment+0.450
Neg logit contributions
rolet-0.485
orth-0.462
oppy-0.437
olls-0.412
 NTS-0.411
Token
Token ID251
Feature activation+4.28e-01

Pos logit contributions
rolet+0.094
orth+0.090
oppy+0.087
rays+0.082
olls+0.082
Neg logit contributions
xual-0.058
 menstru-0.053
Bir-0.048
 ferment-0.046
20439-0.046
Token the
Token ID262
Feature activation+2.08e-01

Pos logit contributions
xual+0.883
 menstru+0.837
Bir+0.778
pees+0.762
20439+0.760
Neg logit contributions
rolet-0.870
orth-0.840
oppy-0.788
olls-0.747
 NTS-0.746
Token powerful
Token ID3665
Feature activation+6.17e-01

Pos logit contributions
xual+0.450
 menstru+0.427
Bir+0.401
20439+0.392
pees+0.392
Neg logit contributions
rolet-0.402
orth-0.387
oppy-0.361
 NTS-0.344
olls-0.339
Token
Token ID564
Feature activation+4.28e-01

Pos logit contributions
xual+1.322
 menstru+1.245
Bir+1.167
pees+1.144
20439+1.141
Neg logit contributions
rolet-1.217
orth-1.165
oppy-1.088
 NTS-1.031
rays-1.024
Token
Token ID250
Feature activation-2.76e-01

Pos logit contributions
xual+0.845
 menstru+0.797
Bir+0.732
 ferment+0.717
pees+0.714
Neg logit contributions
rolet-0.921
orth-0.881
oppy-0.838
olls-0.794
 NTS-0.790
Tokenset
Token ID2617
Feature activation+3.59e-02

Pos logit contributions
rolet+0.565
orth+0.551
oppy+0.508
rays+0.489
olls+0.485
Neg logit contributions
xual-0.566
 menstru-0.538
Bir-0.491
 ferment-0.489
20439-0.483
Token their
Token ID511
Feature activation+4.45e-01

Pos logit contributions
xual+0.080
 menstru+0.076
Bir+0.071
pees+0.070
20439+0.070
Neg logit contributions
rolet-0.067
orth-0.064
oppy-0.060
olls-0.057
rays-0.057
Token seal
Token ID13810
Feature activation+4.41e-01

Pos logit contributions
xual+0.939
 menstru+0.885
Bir+0.824
20439+0.811
pees+0.803
Neg logit contributions
rolet-0.892
orth-0.860
oppy-0.805
olls-0.762
 NTS-0.762
Token on
Token ID319
Feature activation+2.85e-02

Pos logit contributions
xual+1.091
 menstru+1.040
Bir+0.974
 ferment+0.959
pees+0.956
Neg logit contributions
rolet-0.726
orth-0.686
oppy-0.640
olls-0.596
 NTS-0.593
Token Morning
Token ID14410
Feature activation+7.18e-02

Pos logit contributions
rolet+0.386
orth+0.368
oppy+0.322
 NTS+0.291
olls+0.287
Neg logit contributions
xual-1.135
 menstru-1.087
 ferment-1.031
Bir-1.023
20439-1.021
Token.
Token ID13
Feature activation+1.98e-01

Pos logit contributions
xual+0.166
 menstru+0.158
Bir+0.147
 ferment+0.145
pees+0.144
Neg logit contributions
rolet-0.129
orth-0.123
oppy-0.115
 NTS-0.108
olls-0.108
Token 16
Token ID1467
Feature activation-3.49e-01

Pos logit contributions
xual+0.446
 menstru+0.425
Bir+0.393
 ferment+0.391
pees+0.385
Neg logit contributions
rolet-0.369
orth-0.354
oppy-0.331
olls-0.312
 NTS-0.311
Token W
Token ID370
Feature activation-4.17e-01

Pos logit contributions
rolet+0.678
orth+0.661
oppy+0.619
 NTS+0.589
rays+0.583
Neg logit contributions
xual-0.751
 menstru-0.708
Bir-0.649
 ferment-0.645
pees-0.641
Token.
Token ID13
Feature activation-2.30e-02

Pos logit contributions
rolet+0.798
orth+0.771
oppy+0.726
olls+0.684
 NTS+0.676
Neg logit contributions
xual-0.926
 menstru-0.873
Bir-0.803
 ferment-0.791
20439-0.788
Token Madison
Token ID14909
Feature activation+2.28e-02

Pos logit contributions
rolet+0.044
orth+0.042
oppy+0.040
 NTS+0.038
olls+0.038
Neg logit contributions
xual-0.051
 menstru-0.048
Bir-0.044
 ferment-0.044
pees-0.044
Token St
Token ID520
Feature activation-1.11e+00

Pos logit contributions
xual+0.052
 menstru+0.049
Bir+0.046
 ferment+0.045
20439+0.045
Neg logit contributions
rolet-0.042
orth-0.040
oppy-0.038
 NTS-0.036
olls-0.035
Token.
Token ID13
Feature activation-1.12e-01

Pos logit contributions
rolet+2.014
orth+1.945
oppy+1.821
 NTS+1.717
olls+1.712
Neg logit contributions
xual-2.550
 menstru-2.414
 ferment-2.205
Bir-2.203
20439-2.198
Token Baltimore
Token ID10346
Feature activation-1.25e+00

Pos logit contributions
rolet+0.201
orth+0.192
oppy+0.180
 NTS+0.170
olls+0.169
Neg logit contributions
xual-0.260
 menstru-0.247
Bir-0.226
 ferment-0.226
pees-0.224
Token,
Token ID11
Feature activation-5.38e-01

Pos logit contributions
rolet+2.026
orth+1.953
oppy+1.793
 NTS+1.717
rays+1.698
Neg logit contributions
xual-3.092
 menstru-2.913
pees-2.695
Bir-2.683
 ferment-2.678
Token MD
Token ID10670
Feature activation-1.05e+00

Pos logit contributions
rolet+0.696
orth+0.652
oppy+0.590
 NTS+0.545
rays+0.539
Neg logit contributions
xual-1.528
 menstru-1.453
Bir-1.360
 ferment-1.360
pees-1.359
Token
Token ID447
Feature activation-2.70e-01

Pos logit contributions
rolet+0.110
orth+0.105
oppy+0.099
 NTS+0.094
olls+0.093
Neg logit contributions
xual-0.122
 menstru-0.115
Bir-0.106
 ferment-0.105
pees-0.105
Token
Token ID251
Feature activation-2.56e-01

Pos logit contributions
rolet+0.610
orth+0.585
oppy+0.559
olls+0.530
 NTS+0.529
Neg logit contributions
xual-0.501
 menstru-0.470
Bir-0.429
 ferment-0.420
pees-0.419
Token In
Token ID554
Feature activation-2.15e-01

Pos logit contributions
rolet+0.492
orth+0.471
oppy+0.444
 NTS+0.423
olls+0.418
Neg logit contributions
xual-0.565
 menstru-0.531
 ferment-0.486
Bir-0.486
pees-0.485
Token reality
Token ID3950
Feature activation-3.19e-01

Pos logit contributions
rolet+0.420
orth+0.406
oppy+0.383
 NTS+0.363
olls+0.360
Neg logit contributions
xual-0.461
 menstru-0.434
Bir-0.401
pees-0.396
 ferment-0.396
Token the
Token ID262
Feature activation+2.89e-01

Pos logit contributions
rolet+0.611
orth+0.580
oppy+0.549
olls+0.515
 NTS+0.511
Neg logit contributions
xual-0.701
 menstru-0.669
Bir-0.621
 ferment-0.608
pees-0.604
Token photo
Token ID4590
Feature activation-1.44e+00

Pos logit contributions
xual+0.738
 menstru+0.700
Bir+0.659
pees+0.650
20439+0.650
Neg logit contributions
rolet-0.452
orth-0.428
oppy-0.400
 NTS-0.373
olls-0.370
Token was
Token ID373
Feature activation-4.08e-02

Pos logit contributions
rolet+2.446
orth+2.359
oppy+2.190
 NTS+2.136
olls+2.113
Neg logit contributions
xual-3.375
 menstru-3.177
20439-3.015
Bir-2.983
pees-2.944
Token taken
Token ID2077
Feature activation-1.58e+00

Pos logit contributions
rolet+0.076
orth+0.072
oppy+0.068
 NTS+0.064
olls+0.064
Neg logit contributions
xual-0.092
 menstru-0.087
Bir-0.081
pees-0.080
20439-0.079
Token by
Token ID416
Feature activation-3.99e-01

Pos logit contributions
rolet+2.622
orth+2.483
oppy+2.320
 NTS+2.229
olls+2.193
Neg logit contributions
xual-3.828
 menstru-3.570
20439-3.407
Bir-3.395
pees-3.376
Token Reuters
Token ID8428
Feature activation-2.75e-01

Pos logit contributions
rolet+0.767
orth+0.733
oppy+0.693
 NTS+0.661
olls+0.655
Neg logit contributions
xual-0.877
 menstru-0.822
Bir-0.764
pees-0.755
20439-0.752
Token in
Token ID287
Feature activation+2.37e-01

Pos logit contributions
rolet+0.446
orth+0.426
oppy+0.394
 NTS+0.368
olls+0.366
Neg logit contributions
xual-0.683
 menstru-0.652
Bir-0.610
pees-0.603
 ferment-0.602
TokenIt
Token ID1026
Feature activation+2.14e-01

Pos logit contributions
rolet+0.811
orth+0.786
oppy+0.738
olls+0.701
 NTS+0.693
Neg logit contributions
xual-0.845
 menstru-0.783
 ferment-0.718
pees-0.703
20439-0.696
Token also
Token ID635
Feature activation+1.74e-01

Pos logit contributions
xual+0.485
 menstru+0.457
Bir+0.428
20439+0.420
pees+0.419
Neg logit contributions
rolet-0.397
orth-0.380
oppy-0.357
olls-0.337
 NTS-0.334
Token means
Token ID1724
Feature activation+3.14e-01

Pos logit contributions
xual+0.389
 menstru+0.365
Bir+0.343
20439+0.337
pees+0.335
Neg logit contributions
rolet-0.325
orth-0.313
oppy-0.294
olls-0.278
rays-0.276
Token that
Token ID326
Feature activation+4.01e-01

Pos logit contributions
xual+0.701
 menstru+0.660
Bir+0.612
pees+0.605
20439+0.602
Neg logit contributions
rolet-0.595
orth-0.569
oppy-0.534
 NTS-0.507
olls-0.505
Token all
Token ID477
Feature activation+6.96e-01

Pos logit contributions
xual+0.883
 menstru+0.829
Bir+0.768
20439+0.762
pees+0.760
Neg logit contributions
rolet-0.769
orth-0.739
oppy-0.699
 NTS-0.663
olls-0.658
Token law
Token ID1099
Feature activation-1.54e+00

Pos logit contributions
xual+1.642
 menstru+1.556
Bir+1.450
pees+1.426
 ferment+1.425
Neg logit contributions
rolet-1.229
orth-1.169
oppy-1.099
 NTS-1.030
olls-1.027
Token students
Token ID2444
Feature activation+3.56e-01

Pos logit contributions
rolet+2.356
orth+2.345
oppy+2.126
 NTS+2.010
rays+1.973
Neg logit contributions
xual-3.859
 menstru-3.611
20439-3.385
Bir-3.381
pees-3.370
Token,
Token ID11
Feature activation+3.58e-01

Pos logit contributions
xual+0.837
 menstru+0.789
Bir+0.740
pees+0.727
 ferment+0.725
Neg logit contributions
rolet-0.629
orth-0.601
oppy-0.560
 NTS-0.527
olls-0.525
Token regardless
Token ID7692
Feature activation-1.77e-01

Pos logit contributions
xual+0.805
 menstru+0.762
Bir+0.708
 ferment+0.698
pees+0.696
Neg logit contributions
rolet-0.672
orth-0.638
oppy-0.601
olls-0.565
 NTS-0.565
Token of
Token ID286
Feature activation-3.55e-01

Pos logit contributions
rolet+0.254
orth+0.242
oppy+0.222
 NTS+0.208
olls+0.204
Neg logit contributions
xual-0.468
 menstru-0.445
Bir-0.420
pees-0.416
 ferment-0.415
Token their
Token ID511
Feature activation+1.20e-01

Pos logit contributions
rolet+0.713
orth+0.686
oppy+0.650
 NTS+0.624
olls+0.614
Neg logit contributions
xual-0.740
 menstru-0.688
Bir-0.643
20439-0.636
pees-0.636
Token support
Token ID1104
Feature activation+4.17e-01

Pos logit contributions
xual+2.028
 menstru+1.927
Bir+1.802
 ferment+1.771
pees+1.769
Neg logit contributions
rolet-1.493
orth-1.415
oppy-1.328
olls-1.241
 NTS-1.236
Token Clinton
Token ID2605
Feature activation+4.09e-01

Pos logit contributions
xual+0.991
 menstru+0.941
Bir+0.880
 ferment+0.866
pees+0.864
Neg logit contributions
rolet-0.728
orth-0.691
oppy-0.648
olls-0.607
 NTS-0.605
Token.
Token ID13
Feature activation+1.32e-02

Pos logit contributions
xual+0.923
 menstru+0.876
Bir+0.814
 ferment+0.801
pees+0.798
Neg logit contributions
rolet-0.764
orth-0.727
oppy-0.685
olls-0.643
 NTS-0.640
Token
Token ID198
Feature activation+2.94e-03

Pos logit contributions
xual+0.030
 menstru+0.028
 ferment+0.026
Bir+0.026
pees+0.026
Neg logit contributions
rolet-0.025
orth-0.024
oppy-0.022
 NTS-0.021
olls-0.021
Token
Token ID198
Feature activation+3.58e-02

Pos logit contributions
xual+0.007
 menstru+0.007
pees+0.006
 ferment+0.006
Bir+0.006
Neg logit contributions
rolet-0.005
orth-0.005
oppy-0.005
 NTS-0.004
olls-0.004
TokenBack
Token ID7282
Feature activation-1.54e+00

Pos logit contributions
xual+0.077
 menstru+0.072
 ferment+0.066
pees+0.065
Bir+0.064
Neg logit contributions
rolet-0.071
orth-0.069
oppy-0.065
olls-0.061
rays-0.061
Token during
Token ID1141
Feature activation-5.38e-01

Pos logit contributions
rolet+2.678
orth+2.506
oppy+2.338
 NTS+2.242
olls+2.220
Neg logit contributions
xual-3.555
 menstru-3.342
Bir-3.128
pees-3.096
 ferment-3.082
Token the
Token ID262
Feature activation-4.59e-02

Pos logit contributions
rolet+1.068
orth+1.018
oppy+0.969
olls+0.923
 NTS+0.922
Neg logit contributions
xual-1.145
 menstru-1.057
Bir-0.994
pees-0.983
20439-0.973
Token early
Token ID1903
Feature activation+9.78e-02

Pos logit contributions
rolet+0.079
orth+0.075
oppy+0.071
 NTS+0.067
olls+0.067
Neg logit contributions
xual-0.110
 menstru-0.103
Bir-0.097
pees-0.096
20439-0.095
Token parts
Token ID3354
Feature activation-3.45e-01

Pos logit contributions
xual+0.208
 menstru+0.195
Bir+0.181
pees+0.177
20439+0.176
Neg logit contributions
rolet-0.195
orth-0.187
oppy-0.177
 NTS-0.167
olls-0.167
Token of
Token ID286
Feature activation+1.95e-01

Pos logit contributions
rolet+0.477
orth+0.458
oppy+0.416
 NTS+0.392
olls+0.381
Neg logit contributions
xual-0.932
 menstru-0.887
Bir-0.838
pees-0.834
 ferment-0.828
Token
Token ID12466
Feature activation-7.97e-01

Pos logit contributions
rolet+1.558
orth+1.487
oppy+1.387
 NTS+1.307
olls+1.299
Neg logit contributions
xual-1.787
 menstru-1.687
Bir-1.564
pees-1.542
 ferment-1.535
Token
Token ID111
Feature activation-6.89e-01

Pos logit contributions
rolet+1.813
orth+1.744
oppy+1.648
olls+1.587
 NTS+1.567
Neg logit contributions
xual-1.455
 menstru-1.360
Bir-1.246
pees-1.216
 ferment-1.212
Tokenо
Token ID15166
Feature activation-6.77e-01

Pos logit contributions
rolet+1.220
orth+1.154
oppy+1.078
olls+1.006
 NTS+1.001
Neg logit contributions
xual-1.620
 menstru-1.544
Bir-1.436
 ferment-1.420
pees-1.409
Tokenр
Token ID21169
Feature activation-8.27e-01

Pos logit contributions
rolet+1.236
orth+1.182
oppy+1.096
 NTS+1.028
olls+1.027
Neg logit contributions
xual-1.548
 menstru-1.471
Bir-1.364
pees-1.357
 ferment-1.343
Tokenя
Token ID40623
Feature activation-9.74e-01

Pos logit contributions
rolet+1.529
orth+1.464
oppy+1.364
 NTS+1.269
rays+1.269
Neg logit contributions
xual-1.862
 menstru-1.781
Bir-1.636
pees-1.632
 ferment-1.620
Token
Token ID141
Feature activation-1.25e+00

Pos logit contributions
rolet+2.102
orth+2.018
oppy+1.880
 NTS+1.804
olls+1.789
Neg logit contributions
xual-1.915
 menstru-1.792
Bir-1.641
pees-1.625
 ferment-1.611
Token
Token ID229
Feature activation-6.05e-01

Pos logit contributions
rolet+2.559
orth+2.444
oppy+2.311
olls+2.193
rays+2.182
Neg logit contributions
xual-2.557
 menstru-2.395
Bir-2.236
pees-2.211
20439-2.190
Tokenи
Token ID18849
Feature activation-8.61e-01

Pos logit contributions
rolet+1.168
orth+1.126
oppy+1.060
 NTS+0.997
olls+0.994
Neg logit contributions
xual-1.308
 menstru-1.236
Bir-1.148
pees-1.127
20439-1.127
Token
Token ID141
Feature activation-1.42e+00

Pos logit contributions
rolet+1.778
orth+1.717
oppy+1.611
 NTS+1.524
olls+1.517
Neg logit contributions
xual-1.762
 menstru-1.650
Bir-1.530
20439-1.490
 ferment-1.484
Token
Token ID227
Feature activation-2.82e-01

Pos logit contributions
rolet+2.881
orth+2.762
oppy+2.609
 NTS+2.478
rays+2.469
Neg logit contributions
xual-2.914
 menstru-2.736
Bir-2.553
20439-2.509
pees-2.505
Token
Token ID220
Feature activation-3.99e-01

Pos logit contributions
rolet+0.507
orth+0.482
oppy+0.450
 NTS+0.425
olls+0.422
Neg logit contributions
xual-0.656
 menstru-0.621
Bir-0.578
pees-0.571
 ferment-0.567
TokenFI
Token ID11674
Feature activation-2.26e-01

Pos logit contributions
rolet+0.025
orth+0.024
oppy+0.023
olls+0.022
 NTS+0.022
Neg logit contributions
xual-0.023
 menstru-0.021
Bir-0.019
 ferment-0.019
20439-0.019
Token is
Token ID318
Feature activation-1.91e-01

Pos logit contributions
rolet+0.401
orth+0.385
oppy+0.362
 NTS+0.343
olls+0.341
Neg logit contributions
xual-0.527
 menstru-0.494
Bir-0.463
20439-0.455
pees-0.452
Token getting
Token ID1972
Feature activation+1.06e-01

Pos logit contributions
rolet+0.375
orth+0.360
oppy+0.338
 NTS+0.324
olls+0.323
Neg logit contributions
xual-0.409
 menstru-0.377
Bir-0.355
20439-0.347
pees-0.346
Token into
Token ID656
Feature activation-3.39e-01

Pos logit contributions
xual+0.227
 menstru+0.214
Bir+0.200
20439+0.196
pees+0.195
Neg logit contributions
rolet-0.206
orth-0.198
oppy-0.187
olls-0.178
 NTS-0.177
Token the
Token ID262
Feature activation-3.66e-01

Pos logit contributions
rolet+0.686
orth+0.660
oppy+0.628
 NTS+0.596
olls+0.590
Neg logit contributions
xual-0.704
 menstru-0.664
Bir-0.616
pees-0.602
20439-0.602
Token radio
Token ID5243
Feature activation-1.42e+00

Pos logit contributions
rolet+0.662
orth+0.638
oppy+0.602
 NTS+0.576
rays+0.564
Neg logit contributions
xual-0.845
 menstru-0.794
Bir-0.743
20439-0.737
pees-0.730
Token.
Token ID13
Feature activation-2.07e-01

Pos logit contributions
rolet+2.425
orth+2.366
oppy+2.221
 NTS+2.106
rays+2.074
Neg logit contributions
xual-3.357
 menstru-3.154
Bir-2.964
20439-2.954
-2.873
Token The
Token ID383
Feature activation-6.87e-01

Pos logit contributions
rolet+0.391
orth+0.376
oppy+0.352
 NTS+0.340
olls+0.331
Neg logit contributions
xual-0.464
 menstru-0.438
Bir-0.401
 ferment-0.398
pees-0.398
Token following
Token ID1708
Feature activation-9.00e-01

Pos logit contributions
rolet+1.206
orth+1.170
oppy+1.097
 NTS+1.049
olls+1.019
Neg logit contributions
xual-1.611
 menstru-1.518
Bir-1.421
20439-1.406
pees-1.397
Token is
Token ID318
Feature activation-3.96e-01

Pos logit contributions
rolet+1.604
orth+1.553
oppy+1.441
 NTS+1.416
rays+1.368
Neg logit contributions
xual-2.087
 menstru-1.938
Bir-1.825
pees-1.792
20439-1.788
Token a
Token ID257
Feature activation+3.26e-01

Pos logit contributions
rolet+0.764
orth+0.737
oppy+0.691
 NTS+0.661
olls+0.650
Neg logit contributions
xual-0.863
 menstru-0.813
Bir-0.759
pees-0.743
 ferment-0.738