TOP ACTIVATIONS
MAX = 4.248

and former CEO of USA Track & Field who now works
Rock by Conservative candidate Dianne Watts , is being called absurd
/ new - age music tracks and many photos of m
following pioneering authors such as Hansen ( 1984 ), assume that
; ten confident , cinematic tracks for young st on ers
country . To help you track down a copy of your
: The Formula One race track in Mon za , Italy
stadt 04 , Ed son Budd le s current
yesterday to the latest race track scream ers , each with
Land au , including sound tracks for seasons 9 through 27
to be hurt by accidentally bump ing the shif ter into
Rye House k art ing track in Hert ford shire .
een , run by Indian Rail ways , operates from Room
. With the new forecast track shifting the cone of concern
equipment regulations borrowed from modern track pursuit bikes . UC I
philosopher - k ings , Watts Up With That is now
Barack Obama gets fast - track approval for TP PA
On the reverse side , Watts is pictured below a line
The renovations include bump ing the capacity from 1
saw it listed for the coax connection . Disable the Wireless

MIN ACTIVATIONS
MIN = -4.916

Ex amine all the vit rified test chamber doors (
is on the edge of vit icultural viability , the math
arsenal of the Ban u Qur ay za which consisted of
been revealed . Gil ad Perry , D ror
last year . Gil bert is known as a
the men of Ban u Qur ay za , the ensl
/ AP ) Gil bert and the ACLU have
Mohammad School teaching " a Qur ' an - guided journey
No woman of Ban u Qur ay za was killed except
, Survivor South Pacific ), voic em ails with Mike Bloom
for the Black berry or Palm Pre ? We
felt in Syria and Mes opot amia . As with so
The imminent merger between Time Warner Cable and Comcast herald s
living on the streets of Gotham . You know how Alfred
the venue s voic email at the time .
Vu itton , Gil more Girls ,
San Diego , Dallas , Palm Beach , Florida , Moreno
, Mass . -- Boston Celtics swing man Jae Crow der
" Show Spe lling and Gram mar " from the Spe
, P ious , Sanct imon ious Why 1939

INTERVAL 1.957 - 4.248
CONTAINS 0.473%

ists , the more successful fellow worship ers of the Lenin
with a football treatment !) HA IRD RI ER
day , said Brenda s oldest daughter
2 - ethyl - N -( t et rah yd ro
icycle keeps our dreams of speed er bikes alive -- if

INTERVAL -0.334 - 1.957
CONTAINS 74.964%

14 dates in the range of 22 , 000 to 39
two leads . Hun nam joins a list of actors being
have to be a practicing Lac anian psych oan alyst to
way to kick start a child s play and
need to be studied further , my advice for policy makers

INTERVAL -2.625 - -0.334
CONTAINS 24.493%

another drawing or poem shortly after finishing the first .
ov , now 88 , Philadelphia s accents are
s sake , American Horror Story : Murder House
That is not even the worst of it .
our legs open . I found it painful . When he

INTERVAL -4.916 - -2.625
CONTAINS 0.069%

d recounted in the New York Times recently , edible tet
That being said , Vil ma and the NFL PA
by the majority of feminist philosophers . I do not see
slider after shifting to the pen last year , am assing
( t ) exp ( -( t - t
Token and
Token ID290
Feature activation-4.54e-01

Pos logit contributions
orem+0.681
ril+0.669
 nerv+0.646
riors+0.626
 wills+0.623
Neg logit contributions
hatt-0.625
Beer-0.603
coat-0.541
andr-0.540
ness-0.535
Token former
Token ID1966
Feature activation-5.41e-01

Pos logit contributions
orem+0.731
ril+0.714
 nerv+0.690
riors+0.667
 wills+0.667
Neg logit contributions
hatt-0.670
Beer-0.644
andr-0.579
coat-0.578
ness-0.573
Token CEO
Token ID6123
Feature activation-4.47e-01

Pos logit contributions
orem+0.850
ril+0.828
 nerv+0.802
 wills+0.774
riors+0.772
Neg logit contributions
hatt-0.818
Beer-0.786
andr-0.710
coat-0.709
ness-0.698
Token of
Token ID286
Feature activation-1.84e-01

Pos logit contributions
orem+0.625
ril+0.610
 nerv+0.582
riors+0.564
 wills+0.561
Neg logit contributions
hatt-0.754
Beer-0.727
coat-0.664
andr-0.664
ness-0.659
Token USA
Token ID4916
Feature activation-1.23e+00

Pos logit contributions
orem+0.286
ril+0.280
 nerv+0.269
 wills+0.261
riors+0.260
Neg logit contributions
hatt-0.282
Beer-0.270
andr-0.244
coat-0.244
ness-0.242
Token Track
Token ID17762
Feature activation+4.25e+00

Pos logit contributions
orem+2.297
ril+2.268
 nerv+2.200
rior+2.133
riors+2.128
Neg logit contributions
hatt-1.466
Beer-1.378
andr-1.224
coat-1.196
ness-1.194
Token &
Token ID1222
Feature activation-7.21e-01

Pos logit contributions
hatt+5.794
Beer+5.526
coat+5.078
ness+5.027
andr+4.955
Neg logit contributions
orem-7.000
ril-6.816
 nerv-6.549
 wills-6.433
riors-6.334
Token Field
Token ID7663
Feature activation+1.99e-01

Pos logit contributions
orem+1.089
ril+1.065
 nerv+1.017
riors+0.983
 wills+0.982
Neg logit contributions
hatt-1.137
Beer-1.090
andr-0.992
coat-0.986
ness-0.982
Token who
Token ID508
Feature activation-4.26e-01

Pos logit contributions
hatt+0.291
Beer+0.279
andr+0.251
coat+0.250
ness+0.248
Neg logit contributions
orem-0.323
ril-0.316
 nerv-0.303
riors-0.296
 wills-0.294
Token now
Token ID783
Feature activation-6.04e-01

Pos logit contributions
orem+0.638
ril+0.625
 nerv+0.599
 wills+0.582
riors+0.581
Neg logit contributions
hatt-0.676
Beer-0.651
andr-0.590
coat-0.589
ness-0.583
Token works
Token ID2499
Feature activation-3.76e-01

Pos logit contributions
orem+0.827
ril+0.809
 nerv+0.771
 wills+0.747
riors+0.745
Neg logit contributions
hatt-1.033
Beer-0.997
andr-0.915
coat-0.910
ness-0.902
Token Rock
Token ID4631
Feature activation+3.19e-02

Pos logit contributions
orem+0.233
ril+0.228
 nerv+0.219
riors+0.214
 wills+0.213
Neg logit contributions
hatt-0.190
Beer-0.182
andr-0.163
coat-0.163
ness-0.161
Token by
Token ID416
Feature activation+6.56e-01

Pos logit contributions
hatt+0.046
Beer+0.044
andr+0.040
coat+0.040
ness+0.039
Neg logit contributions
orem-0.052
ril-0.051
 nerv-0.049
riors-0.048
 wills-0.048
Token Conservative
Token ID11132
Feature activation+4.91e-01

Pos logit contributions
hatt+0.996
Beer+0.959
andr+0.866
coat+0.861
ness+0.856
Neg logit contributions
orem-1.026
ril-1.004
 nerv-0.960
riors-0.936
 wills-0.934
Token candidate
Token ID4540
Feature activation+8.55e-01

Pos logit contributions
hatt+0.758
Beer+0.729
andr+0.660
coat+0.657
ness+0.647
Neg logit contributions
orem-0.757
ril-0.742
 nerv-0.710
riors-0.693
 wills-0.689
Token Dianne
Token ID49197
Feature activation+1.18e+00

Pos logit contributions
hatt+1.203
Beer+1.152
coat+1.033
andr+1.032
ness+1.025
Neg logit contributions
orem-1.434
ril-1.405
 nerv-1.349
riors-1.316
 wills-1.311
Token Watts
Token ID27555
Feature activation+4.11e+00

Pos logit contributions
hatt+1.788
Beer+1.719
coat+1.562
ness+1.555
andr+1.551
Neg logit contributions
orem-1.839
ril-1.800
 nerv-1.725
riors-1.679
 wills-1.673
Token,
Token ID11
Feature activation+2.15e-01

Pos logit contributions
hatt+6.019
Beer+5.699
ness+5.307
coat+5.244
andr+5.155
Neg logit contributions
orem-6.448
ril-6.287
 nerv-5.915
riors-5.855
igation-5.740
Token is
Token ID318
Feature activation+4.62e-01

Pos logit contributions
hatt+0.327
Beer+0.314
andr+0.284
coat+0.283
ness+0.281
Neg logit contributions
orem-0.336
ril-0.329
 nerv-0.315
riors-0.307
 wills-0.306
Token being
Token ID852
Feature activation-1.20e-01

Pos logit contributions
hatt+0.682
Beer+0.655
andr+0.590
coat+0.590
ness+0.586
Neg logit contributions
orem-0.742
ril-0.726
 nerv-0.696
riors-0.678
 wills-0.675
Token called
Token ID1444
Feature activation-5.52e-01

Pos logit contributions
orem+0.177
ril+0.173
 nerv+0.166
riors+0.160
 wills+0.160
Neg logit contributions
hatt-0.194
Beer-0.188
andr-0.171
coat-0.170
ness-0.169
Token absurd
Token ID12986
Feature activation+1.77e-01

Pos logit contributions
orem+0.881
ril+0.868
 nerv+0.834
riors+0.809
 wills+0.807
Neg logit contributions
hatt-0.815
Beer-0.781
andr-0.706
coat-0.702
ness-0.693
Token/
Token ID14
Feature activation+9.64e-01

Pos logit contributions
hatt+3.074
Beer+2.939
ness+2.710
coat+2.697
andr+2.670
Neg logit contributions
orem-3.163
ril-3.081
 nerv-2.953
riors-2.900
igation-2.861
Tokennew
Token ID3605
Feature activation+1.04e+00

Pos logit contributions
hatt+1.364
Beer+1.306
coat+1.172
andr+1.171
ness+1.164
Neg logit contributions
orem-1.612
ril-1.577
 nerv-1.516
riors-1.478
 wills-1.473
Token-
Token ID12
Feature activation+2.63e-01

Pos logit contributions
hatt+1.471
Beer+1.411
coat+1.279
ness+1.277
andr+1.269
Neg logit contributions
orem-1.746
ril-1.695
 nerv-1.636
riors-1.593
 wills-1.587
Tokenage
Token ID496
Feature activation+7.25e-01

Pos logit contributions
hatt+0.296
Beer+0.287
andr+0.247
coat+0.241
ness+0.233
Neg logit contributions
ril-0.506
orem-0.505
riors-0.475
 nerv-0.474
 wills-0.468
Token music
Token ID2647
Feature activation+1.63e+00

Pos logit contributions
hatt+1.098
Beer+1.055
andr+0.953
coat+0.953
ness+0.946
Neg logit contributions
orem-1.140
ril-1.116
 nerv-1.069
riors-1.040
 wills-1.036
Token tracks
Token ID8339
Feature activation+4.06e+00

Pos logit contributions
hatt+2.465
Beer+2.355
ness+2.154
coat+2.149
andr+2.143
Neg logit contributions
orem-2.553
ril-2.479
 nerv-2.376
riors-2.320
 wills-2.296
Token and
Token ID290
Feature activation+1.59e-01

Pos logit contributions
hatt+5.930
Beer+5.627
ness+5.291
coat+5.210
andr+5.113
Neg logit contributions
orem-6.366
ril-6.118
 nerv-5.798
riors-5.763
rior-5.670
Token many
Token ID867
Feature activation-9.71e-01

Pos logit contributions
hatt+0.250
Beer+0.240
coat+0.218
andr+0.218
ness+0.217
Neg logit contributions
orem-0.241
ril-0.235
 nerv-0.225
riors-0.219
 wills-0.218
Token photos
Token ID5205
Feature activation+7.03e-01

Pos logit contributions
orem+1.517
ril+1.482
 nerv+1.433
 wills+1.391
riors+1.381
Neg logit contributions
hatt-1.471
Beer-1.422
andr-1.285
coat-1.271
ness-1.252
Token of
Token ID286
Feature activation+1.43e-02

Pos logit contributions
hatt+1.054
Beer+1.008
coat+0.913
andr+0.912
ness+0.910
Neg logit contributions
orem-1.119
ril-1.090
 nerv-1.043
riors-1.019
 wills-1.014
Token m
Token ID285
Feature activation+4.62e-01

Pos logit contributions
hatt+0.022
Beer+0.021
andr+0.019
coat+0.019
ness+0.019
Neg logit contributions
orem-0.022
ril-0.021
 nerv-0.021
 wills-0.020
riors-0.020
Token following
Token ID1708
Feature activation+9.17e-01

Pos logit contributions
hatt+0.542
Beer+0.521
coat+0.471
andr+0.470
ness+0.468
Neg logit contributions
orem-0.576
ril-0.565
 nerv-0.538
riors-0.527
 wills-0.523
Token pioneering
Token ID36304
Feature activation+1.01e+00

Pos logit contributions
hatt+1.403
Beer+1.346
andr+1.221
coat+1.221
ness+1.221
Neg logit contributions
orem-1.416
ril-1.388
 nerv-1.328
riors-1.297
 wills-1.286
Token authors
Token ID7035
Feature activation+4.77e-01

Pos logit contributions
hatt+1.574
Beer+1.514
coat+1.374
andr+1.373
ness+1.372
Neg logit contributions
orem-1.537
ril-1.504
 nerv-1.435
riors-1.401
 wills-1.389
Token such
Token ID884
Feature activation+9.74e-01

Pos logit contributions
hatt+0.705
Beer+0.677
coat+0.610
andr+0.610
ness+0.606
Neg logit contributions
orem-0.765
ril-0.749
 nerv-0.718
riors-0.699
 wills-0.696
Token as
Token ID355
Feature activation+3.88e-01

Pos logit contributions
hatt+1.637
Beer+1.580
andr+1.442
coat+1.442
ness+1.427
Neg logit contributions
orem-1.368
ril-1.336
 nerv-1.275
riors-1.235
 wills-1.230
Token Hansen
Token ID27667
Feature activation+4.04e+00

Pos logit contributions
hatt+0.583
Beer+0.560
coat+0.505
andr+0.505
ness+0.502
Neg logit contributions
orem-0.615
ril-0.602
 nerv-0.576
riors-0.561
 wills-0.559
Token (
Token ID357
Feature activation+1.52e+00

Pos logit contributions
hatt+5.089
Beer+4.697
ness+4.342
coat+4.277
andr+4.203
Neg logit contributions
orem-7.098
ril-6.920
riors-6.621
 nerv-6.581
 wills-6.528
Token1984
Token ID28296
Feature activation+1.09e+00

Pos logit contributions
hatt+2.090
Beer+2.002
coat+1.789
andr+1.786
ness+1.776
Neg logit contributions
orem-2.592
ril-2.537
 nerv-2.444
riors-2.383
 wills-2.376
Token),
Token ID828
Feature activation-4.23e-01

Pos logit contributions
hatt+1.487
Beer+1.417
coat+1.272
andr+1.271
ness+1.267
Neg logit contributions
orem-1.857
ril-1.812
 nerv-1.738
riors-1.706
 wills-1.699
Token assume
Token ID7048
Feature activation-5.25e-02

Pos logit contributions
orem+0.659
ril+0.643
 nerv+0.618
riors+0.598
 wills+0.597
Neg logit contributions
hatt-0.646
Beer-0.622
andr-0.562
coat-0.562
ness-0.557
Token that
Token ID326
Feature activation+3.10e-01

Pos logit contributions
orem+0.083
ril+0.081
 nerv+0.077
riors+0.075
 wills+0.075
Neg logit contributions
hatt-0.079
Beer-0.076
coat-0.069
andr-0.069
ness-0.068
Token;
Token ID26
Feature activation-5.38e-01

Pos logit contributions
hatt+1.092
Beer+1.049
coat+0.947
andr+0.946
ness+0.940
Neg logit contributions
orem-1.164
ril-1.140
 nerv-1.093
riors-1.064
 wills-1.058
Token ten
Token ID3478
Feature activation-4.06e-01

Pos logit contributions
orem+0.836
ril+0.822
 nerv+0.790
riors+0.765
 wills+0.762
Neg logit contributions
hatt-0.819
Beer-0.788
andr-0.713
coat-0.712
ness-0.704
Token confident
Token ID6563
Feature activation+4.36e-01

Pos logit contributions
orem+0.616
ril+0.604
 nerv+0.574
riors+0.558
 wills+0.556
Neg logit contributions
hatt-0.638
Beer-0.615
andr-0.559
coat-0.557
ness-0.550
Token,
Token ID11
Feature activation-7.84e-02

Pos logit contributions
hatt+0.635
Beer+0.609
coat+0.548
andr+0.548
ness+0.544
Neg logit contributions
orem-0.709
ril-0.694
 nerv-0.665
riors-0.648
 wills-0.646
Token cinematic
Token ID29932
Feature activation-1.01e+00

Pos logit contributions
orem+0.133
ril+0.130
 nerv+0.125
riors+0.122
 wills+0.122
Neg logit contributions
hatt-0.109
Beer-0.105
andr-0.094
coat-0.094
ness-0.093
Token tracks
Token ID8339
Feature activation+4.01e+00

Pos logit contributions
orem+1.609
ril+1.585
 nerv+1.530
 wills+1.483
riors+1.483
Neg logit contributions
hatt-1.484
Beer-1.433
andr-1.292
coat-1.290
ness-1.254
Token for
Token ID329
Feature activation+1.27e-02

Pos logit contributions
hatt+5.705
Beer+5.370
ness+5.076
coat+5.017
andr+4.876
Neg logit contributions
orem-6.491
ril-6.212
riors-5.777
 nerv-5.773
 wills-5.716
Token young
Token ID1862
Feature activation+5.89e-01

Pos logit contributions
hatt+0.019
Beer+0.019
andr+0.017
coat+0.017
ness+0.017
Neg logit contributions
orem-0.020
ril-0.019
 nerv-0.019
riors-0.018
 wills-0.018
Token st
Token ID336
Feature activation+1.08e+00

Pos logit contributions
hatt+0.848
Beer+0.813
andr+0.731
coat+0.730
ness+0.718
Neg logit contributions
orem-0.971
ril-0.952
 nerv-0.918
riors-0.891
 wills-0.888
Tokenon
Token ID261
Feature activation-1.23e-01

Pos logit contributions
hatt+1.581
Beer+1.509
andr+1.365
coat+1.361
ness+1.360
Neg logit contributions
orem-1.735
ril-1.695
 nerv-1.639
 wills-1.597
riors-1.589
Tokeners
Token ID364
Feature activation-1.54e-01

Pos logit contributions
orem+0.242
ril+0.238
 nerv+0.229
riors+0.225
 wills+0.223
Neg logit contributions
hatt-0.137
Beer-0.130
andr-0.113
coat-0.113
ness-0.111
Token country
Token ID1499
Feature activation+1.19e+00

Pos logit contributions
hatt+0.145
Beer+0.139
coat+0.126
andr+0.126
ness+0.126
Neg logit contributions
orem-0.147
ril-0.144
 nerv-0.137
riors-0.134
 wills-0.133
Token.
Token ID13
Feature activation+2.21e-01

Pos logit contributions
hatt+1.729
Beer+1.652
coat+1.496
ness+1.489
andr+1.482
Neg logit contributions
orem-1.940
ril-1.886
 nerv-1.806
riors-1.765
 wills-1.761
Token To
Token ID1675
Feature activation+8.40e-01

Pos logit contributions
hatt+0.331
Beer+0.319
coat+0.287
andr+0.287
ness+0.286
Neg logit contributions
orem-0.351
ril-0.342
 nerv-0.329
riors-0.320
 wills-0.319
Token help
Token ID1037
Feature activation+2.04e-02

Pos logit contributions
hatt+1.308
Beer+1.257
coat+1.142
andr+1.140
ness+1.136
Neg logit contributions
orem-1.281
ril-1.251
 nerv-1.197
riors-1.165
 wills-1.161
Token you
Token ID345
Feature activation+1.10e+00

Pos logit contributions
hatt+0.032
Beer+0.030
coat+0.028
andr+0.028
ness+0.027
Neg logit contributions
orem-0.031
ril-0.031
 nerv-0.029
riors-0.028
 wills-0.028
Token track
Token ID2610
Feature activation+3.91e+00

Pos logit contributions
hatt+1.629
Beer+1.557
ness+1.410
coat+1.410
andr+1.408
Neg logit contributions
orem-1.770
ril-1.730
 nerv-1.657
riors-1.615
 wills-1.612
Token down
Token ID866
Feature activation+1.22e-01

Pos logit contributions
hatt+5.272
Beer+4.931
ness+4.556
coat+4.528
andr+4.434
Neg logit contributions
orem-6.550
ril-6.392
 nerv-6.086
riors-5.983
igation-5.869
Token a
Token ID257
Feature activation+2.31e-01

Pos logit contributions
hatt+0.190
Beer+0.183
coat+0.165
andr+0.165
ness+0.164
Neg logit contributions
orem-0.186
ril-0.181
 nerv-0.173
riors-0.169
 wills-0.168
Token copy
Token ID4866
Feature activation+5.48e-01

Pos logit contributions
hatt+0.384
Beer+0.370
coat+0.338
andr+0.337
ness+0.336
Neg logit contributions
orem-0.330
ril-0.322
 nerv-0.307
riors-0.298
 wills-0.296
Token of
Token ID286
Feature activation+3.48e-01

Pos logit contributions
hatt+0.839
Beer+0.803
coat+0.732
ness+0.731
andr+0.730
Neg logit contributions
orem-0.851
ril-0.831
 nerv-0.794
riors-0.773
 wills-0.772
Token your
Token ID534
Feature activation+8.53e-01

Pos logit contributions
hatt+0.516
Beer+0.495
coat+0.447
andr+0.446
ness+0.444
Neg logit contributions
orem-0.556
ril-0.545
 nerv-0.522
riors-0.509
 wills-0.506
Token:
Token ID25
Feature activation-6.40e-01

Pos logit contributions
orem+0.383
ril+0.377
 nerv+0.359
riors+0.351
 wills+0.348
Neg logit contributions
hatt-0.349
Beer-0.332
andr-0.302
coat-0.300
ness-0.296
Token The
Token ID383
Feature activation-8.06e-02

Pos logit contributions
orem+0.969
ril+0.950
 nerv+0.908
riors+0.880
 wills+0.877
Neg logit contributions
hatt-1.002
Beer-0.961
coat-0.874
andr-0.873
ness-0.866
Token Formula
Token ID19639
Feature activation+6.47e-02

Pos logit contributions
orem+0.124
ril+0.121
 nerv+0.116
riors+0.113
 wills+0.112
Neg logit contributions
hatt-0.125
Beer-0.120
coat-0.109
andr-0.109
ness-0.107
Token One
Token ID1881
Feature activation+1.24e+00

Pos logit contributions
hatt+0.104
Beer+0.100
coat+0.091
andr+0.091
ness+0.090
Neg logit contributions
orem-0.095
ril-0.093
 nerv-0.089
riors-0.087
 wills-0.086
Token race
Token ID3234
Feature activation+2.71e+00

Pos logit contributions
hatt+1.899
Beer+1.825
coat+1.652
andr+1.650
ness+1.644
Neg logit contributions
orem-1.936
ril-1.894
 nerv-1.813
riors-1.765
 wills-1.758
Token track
Token ID2610
Feature activation+3.88e+00

Pos logit contributions
hatt+3.554
Beer+3.391
coat+3.059
ness+3.031
andr+3.021
Neg logit contributions
orem-4.763
ril-4.598
 nerv-4.433
riors-4.333
 wills-4.319
Token in
Token ID287
Feature activation+2.31e-01

Pos logit contributions
hatt+5.294
Beer+5.021
ness+4.658
coat+4.575
andr+4.530
Neg logit contributions
orem-6.375
ril-6.182
 nerv-5.946
riors-5.772
 wills-5.744
Token Mon
Token ID2892
Feature activation-4.37e-01

Pos logit contributions
hatt+0.362
Beer+0.348
coat+0.316
andr+0.316
ness+0.314
Neg logit contributions
orem-0.352
ril-0.344
 nerv-0.329
riors-0.319
 wills-0.319
Tokenza
Token ID4496
Feature activation+1.16e+00

Pos logit contributions
orem+0.772
ril+0.759
 nerv+0.716
riors+0.705
igation+0.699
Neg logit contributions
hatt-0.570
Beer-0.554
andr-0.492
coat-0.490
ness-0.482
Token,
Token ID11
Feature activation+1.76e-01

Pos logit contributions
hatt+1.531
Beer+1.455
coat+1.300
andr+1.293
ness+1.290
Neg logit contributions
orem-2.045
ril-2.002
 nerv-1.928
riors-1.889
 wills-1.877
Token Italy
Token ID8031
Feature activation+1.63e-01

Pos logit contributions
hatt+0.295
Beer+0.285
andr+0.261
coat+0.260
ness+0.258
Neg logit contributions
orem-0.247
ril-0.241
 nerv-0.230
 wills-0.223
riors-0.223
Tokenstadt
Token ID38863
Feature activation+1.61e+00

Pos logit contributions
orem+1.639
ril+1.593
 nerv+1.499
riors+1.456
 wills+1.450
Neg logit contributions
hatt-2.101
Beer-2.050
coat-1.857
andr-1.848
ness-1.837
Token 04
Token ID8702
Feature activation+5.92e-01

Pos logit contributions
hatt+2.235
Beer+2.136
andr+1.923
coat+1.918
ness+1.915
Neg logit contributions
orem-2.719
ril-2.655
 nerv-2.538
 wills-2.491
riors-2.487
Token,
Token ID11
Feature activation+6.95e-02

Pos logit contributions
hatt+0.848
Beer+0.813
coat+0.731
andr+0.729
ness+0.722
Neg logit contributions
orem-0.977
ril-0.959
 nerv-0.923
riors-0.897
 wills-0.891
Token Ed
Token ID1717
Feature activation+5.11e-01

Pos logit contributions
hatt+0.106
Beer+0.102
coat+0.092
andr+0.092
ness+0.091
Neg logit contributions
orem-0.108
ril-0.106
 nerv-0.102
riors-0.099
 wills-0.098
Tokenson
Token ID1559
Feature activation+3.13e-01

Pos logit contributions
hatt+0.731
Beer+0.699
andr+0.629
coat+0.628
ness+0.625
Neg logit contributions
orem-0.847
ril-0.827
 nerv-0.796
riors-0.776
 wills-0.774
Token Budd
Token ID8578
Feature activation+3.86e+00

Pos logit contributions
hatt+0.456
Beer+0.440
coat+0.396
andr+0.391
ness+0.389
Neg logit contributions
orem-0.508
ril-0.499
 nerv-0.477
riors-0.465
 wills-0.462
Tokenle
Token ID293
Feature activation+3.76e-01

Pos logit contributions
hatt+4.689
Beer+4.361
ness+4.028
andr+3.915
coat+3.911
Neg logit contributions
orem-7.082
ril-6.855
 nerv-6.498
 wills-6.483
riors-6.477
Token
Token ID447
Feature activation-1.95e-01

Pos logit contributions
hatt+0.543
Beer+0.521
coat+0.468
andr+0.468
ness+0.465
Neg logit contributions
orem-0.617
ril-0.604
 nerv-0.580
riors-0.565
 wills-0.563
Token
Token ID247
Feature activation+1.64e-01

Pos logit contributions
orem+0.271
ril+0.265
 nerv+0.252
riors+0.245
 wills+0.242
Neg logit contributions
hatt-0.331
Beer-0.319
coat-0.292
andr-0.292
ness-0.290
Tokens
Token ID82
Feature activation-4.85e-01

Pos logit contributions
hatt+0.178
Beer+0.168
coat+0.145
andr+0.144
ness+0.142
Neg logit contributions
orem-0.328
ril-0.323
 nerv-0.311
riors-0.306
 wills-0.303
Token current
Token ID1459
Feature activation+8.31e-02

Pos logit contributions
orem+0.783
ril+0.763
 nerv+0.739
riors+0.718
 wills+0.707
Neg logit contributions
hatt-0.713
Beer-0.687
coat-0.616
andr-0.610
ness-0.603
Token yesterday
Token ID7415
Feature activation+3.01e-01

Pos logit contributions
hatt+0.464
Beer+0.446
andr+0.403
coat+0.403
ness+0.400
Neg logit contributions
orem-0.468
ril-0.458
 nerv-0.439
riors-0.426
 wills-0.426
Token to
Token ID284
Feature activation+3.04e-01

Pos logit contributions
hatt+0.434
Beer+0.417
andr+0.375
coat+0.374
ness+0.371
Neg logit contributions
orem-0.495
ril-0.485
 nerv-0.465
riors-0.453
 wills-0.452
Token the
Token ID262
Feature activation+1.40e-01

Pos logit contributions
hatt+0.446
Beer+0.428
coat+0.385
andr+0.385
ness+0.383
Neg logit contributions
orem-0.493
ril-0.482
 nerv-0.462
riors-0.451
 wills-0.449
Token latest
Token ID3452
Feature activation+1.22e+00

Pos logit contributions
hatt+0.195
Beer+0.187
coat+0.168
andr+0.168
ness+0.166
Neg logit contributions
orem-0.235
ril-0.230
 nerv-0.222
riors-0.216
 wills-0.215
Token race
Token ID3234
Feature activation+2.56e+00

Pos logit contributions
hatt+1.798
Beer+1.723
ness+1.561
coat+1.558
andr+1.557
Neg logit contributions
orem-1.959
ril-1.916
 nerv-1.828
riors-1.784
 wills-1.772
Token track
Token ID2610
Feature activation+3.81e+00

Pos logit contributions
hatt+3.559
Beer+3.364
coat+3.063
andr+3.031
ness+3.022
Neg logit contributions
orem-4.345
ril-4.190
 nerv-4.016
igation-3.911
 wills-3.907
Token scream
Token ID8196
Feature activation-1.06e-01

Pos logit contributions
hatt+5.688
Beer+5.340
ness+5.056
coat+5.034
andr+4.903
Neg logit contributions
orem-5.826
ril-5.639
 nerv-5.307
igation-5.200
 wills-5.152
Tokeners
Token ID364
Feature activation+1.83e-01

Pos logit contributions
orem+0.169
ril+0.166
 nerv+0.159
riors+0.155
 wills+0.155
Neg logit contributions
hatt-0.159
Beer-0.153
coat-0.137
andr-0.137
ness-0.136
Token,
Token ID11
Feature activation+2.04e-01

Pos logit contributions
hatt+0.266
Beer+0.256
andr+0.230
coat+0.230
ness+0.228
Neg logit contributions
orem-0.297
ril-0.291
 nerv-0.279
riors-0.272
 wills-0.271
Token each
Token ID1123
Feature activation+1.31e-01

Pos logit contributions
hatt+0.291
Beer+0.279
coat+0.251
andr+0.251
ness+0.249
Neg logit contributions
orem-0.338
ril-0.331
 nerv-0.318
riors-0.310
 wills-0.309
Token with
Token ID351
Feature activation+4.71e-01

Pos logit contributions
hatt+0.174
Beer+0.167
coat+0.148
andr+0.148
ness+0.146
Neg logit contributions
orem-0.228
ril-0.224
 nerv-0.216
 wills-0.210
riors-0.210
Token Land
Token ID6379
Feature activation+6.91e-01

Pos logit contributions
hatt+2.651
Beer+2.540
andr+2.318
coat+2.301
ness+2.300
Neg logit contributions
orem-2.666
ril-2.595
 nerv-2.503
riors-2.433
 wills-2.423
Tokenau
Token ID559
Feature activation+5.99e-01

Pos logit contributions
hatt+1.009
Beer+0.963
coat+0.875
ness+0.872
andr+0.870
Neg logit contributions
orem-1.121
ril-1.092
 nerv-1.062
riors-1.028
 wills-1.026
Token,
Token ID11
Feature activation+4.62e-01

Pos logit contributions
hatt+0.855
Beer+0.817
coat+0.735
andr+0.735
ness+0.731
Neg logit contributions
orem-0.995
ril-0.971
 nerv-0.933
riors-0.911
 wills-0.908
Token including
Token ID1390
Feature activation+4.88e-01

Pos logit contributions
hatt+0.686
Beer+0.659
coat+0.595
andr+0.595
ness+0.592
Neg logit contributions
orem-0.739
ril-0.722
 nerv-0.691
riors-0.675
 wills-0.670
Token sound
Token ID2128
Feature activation+4.49e-01

Pos logit contributions
hatt+0.709
Beer+0.680
coat+0.612
andr+0.612
ness+0.609
Neg logit contributions
orem-0.798
ril-0.780
 nerv-0.748
riors-0.730
 wills-0.726
Tokentracks
Token ID46074
Feature activation+3.79e+00

Pos logit contributions
hatt+0.343
Beer+0.316
coat+0.254
andr+0.253
ness+0.250
Neg logit contributions
orem-1.041
ril-1.025
 nerv-0.996
riors-0.979
 wills-0.976
Token for
Token ID329
Feature activation+3.71e-01

Pos logit contributions
hatt+5.319
Beer+5.127
ness+4.731
coat+4.699
andr+4.623
Neg logit contributions
orem-6.133
ril-5.853
 nerv-5.595
riors-5.510
 wills-5.504
Token seasons
Token ID7028
Feature activation+4.61e-01

Pos logit contributions
hatt+0.564
Beer+0.542
coat+0.491
andr+0.490
ness+0.488
Neg logit contributions
orem-0.580
ril-0.566
 nerv-0.542
riors-0.529
 wills-0.525
Token 9
Token ID860
Feature activation+1.42e-02

Pos logit contributions
hatt+0.744
Beer+0.716
coat+0.652
andr+0.651
ness+0.648
Neg logit contributions
orem-0.679
ril-0.663
 nerv-0.632
riors-0.615
 wills-0.612
Token through
Token ID832
Feature activation+2.76e-01

Pos logit contributions
hatt+0.020
Beer+0.019
coat+0.017
andr+0.017
ness+0.017
Neg logit contributions
orem-0.024
ril-0.024
 nerv-0.023
riors-0.022
 wills-0.022
Token 27
Token ID2681
Feature activation-6.74e-01

Pos logit contributions
hatt+0.446
Beer+0.430
coat+0.391
andr+0.391
ness+0.389
Neg logit contributions
orem-0.405
ril-0.395
 nerv-0.377
riors-0.366
 wills-0.365
Token to
Token ID284
Feature activation-2.23e-01

Pos logit contributions
hatt+0.156
Beer+0.151
coat+0.136
andr+0.136
ness+0.134
Neg logit contributions
orem-0.158
ril-0.155
 nerv-0.149
 wills-0.143
riors-0.143
Token be
Token ID307
Feature activation+3.96e-01

Pos logit contributions
orem+0.335
ril+0.328
 nerv+0.315
 wills+0.304
riors+0.303
Neg logit contributions
hatt-0.353
Beer-0.342
andr-0.309
coat-0.308
ness-0.305
Token hurt
Token ID5938
Feature activation-1.63e-01

Pos logit contributions
hatt+0.555
Beer+0.532
andr+0.476
coat+0.476
ness+0.472
Neg logit contributions
orem-0.666
ril-0.652
 nerv-0.627
riors-0.611
 wills-0.609
Token by
Token ID416
Feature activation+4.76e-01

Pos logit contributions
orem+0.260
ril+0.254
 nerv+0.244
riors+0.237
 wills+0.236
Neg logit contributions
hatt-0.243
Beer-0.233
andr-0.210
coat-0.210
ness-0.207
Token accidentally
Token ID14716
Feature activation+2.45e+00

Pos logit contributions
hatt+0.664
Beer+0.636
coat+0.570
andr+0.569
ness+0.566
Neg logit contributions
orem-0.803
ril-0.787
 nerv-0.756
riors-0.737
 wills-0.734
Token bump
Token ID13852
Feature activation+3.79e+00

Pos logit contributions
hatt+3.410
Beer+3.235
ness+2.944
coat+2.913
andr+2.900
Neg logit contributions
orem-4.114
ril-4.015
 nerv-3.811
riors-3.789
 wills-3.713
Tokening
Token ID278
Feature activation-2.06e-02

Pos logit contributions
hatt+2.506
Beer+2.229
ness+1.770
coat+1.752
andr+1.738
Neg logit contributions
orem-9.142
ril-8.926
 nerv-8.669
riors-8.570
 wills-8.480
Token the
Token ID262
Feature activation+1.42e-01

Pos logit contributions
orem+0.030
ril+0.030
 nerv+0.028
 wills+0.028
riors+0.027
Neg logit contributions
hatt-0.033
Beer-0.032
coat-0.029
andr-0.029
ness-0.029
Token shif
Token ID7143
Feature activation+6.63e-01

Pos logit contributions
hatt+0.206
Beer+0.198
andr+0.178
coat+0.178
ness+0.175
Neg logit contributions
orem-0.230
ril-0.225
 nerv-0.217
 wills-0.211
riors-0.210
Tokenter
Token ID353
Feature activation-4.67e-01

Pos logit contributions
hatt+0.903
Beer+0.865
coat+0.771
andr+0.770
ness+0.765
Neg logit contributions
orem-1.142
ril-1.120
 nerv-1.075
riors-1.050
 wills-1.045
Token into
Token ID656
Feature activation+1.96e-01

Pos logit contributions
orem+0.728
ril+0.715
 nerv+0.690
 wills+0.668
riors+0.667
Neg logit contributions
hatt-0.704
Beer-0.681
andr-0.608
coat-0.607
ness-0.597
Token Rye
Token ID45014
Feature activation-3.51e-01

Pos logit contributions
hatt+0.180
Beer+0.173
coat+0.157
andr+0.157
ness+0.155
Neg logit contributions
orem-0.177
ril-0.173
 nerv-0.166
riors-0.161
 wills-0.160
Token House
Token ID2097
Feature activation+7.34e-01

Pos logit contributions
orem+0.558
ril+0.545
 nerv+0.521
riors+0.508
 wills+0.505
Neg logit contributions
hatt-0.525
Beer-0.504
andr-0.455
coat-0.454
ness-0.451
Token k
Token ID479
Feature activation-8.35e-01

Pos logit contributions
hatt+1.009
Beer+0.965
andr+0.863
coat+0.861
ness+0.854
Neg logit contributions
orem-1.256
ril-1.228
 nerv-1.182
riors-1.154
 wills-1.148
Tokenart
Token ID433
Feature activation-5.36e-01

Pos logit contributions
orem+0.976
ril+0.949
 nerv+0.858
riors+0.849
rior+0.839
Neg logit contributions
hatt-1.596
Beer-1.562
coat-1.442
andr-1.435
ness-1.434
Tokening
Token ID278
Feature activation-1.93e-01

Pos logit contributions
orem+1.206
ril+1.187
 nerv+1.144
riors+1.132
igation+1.121
Neg logit contributions
hatt-0.450
Beer-0.416
andr-0.347
coat-0.335
ness-0.325
Token track
Token ID2610
Feature activation+3.73e+00

Pos logit contributions
orem+0.314
ril+0.306
 nerv+0.295
riors+0.289
 wills+0.286
Neg logit contributions
hatt-0.282
Beer-0.270
andr-0.245
coat-0.241
ness-0.240
Token in
Token ID287
Feature activation+1.75e-01

Pos logit contributions
hatt+5.053
Beer+4.821
coat+4.402
ness+4.337
andr+4.323
Neg logit contributions
orem-6.219
ril-6.138
 nerv-5.861
 wills-5.736
riors-5.683
Token Hert
Token ID40030
Feature activation+4.50e-01

Pos logit contributions
hatt+0.277
Beer+0.266
andr+0.242
coat+0.242
ness+0.240
Neg logit contributions
orem-0.261
ril-0.255
 nerv-0.245
 wills-0.237
riors-0.237
Tokenford
Token ID3841
Feature activation-1.94e-01

Pos logit contributions
hatt+0.642
Beer+0.614
coat+0.555
ness+0.553
andr+0.552
Neg logit contributions
orem-0.745
ril-0.725
 nerv-0.702
riors-0.682
 wills-0.681
Tokenshire
Token ID10932
Feature activation+3.50e-02

Pos logit contributions
orem+0.270
ril+0.265
 nerv+0.251
riors+0.244
 wills+0.243
Neg logit contributions
hatt-0.328
Beer-0.317
andr-0.290
coat-0.289
ness-0.287
Token.
Token ID13
Feature activation+3.70e-01

Pos logit contributions
hatt+0.052
Beer+0.050
andr+0.045
coat+0.045
ness+0.044
Neg logit contributions
orem-0.056
ril-0.055
 nerv-0.053
riors-0.051
 wills-0.051
Tokeneen
Token ID6429
Feature activation+3.13e-01

Pos logit contributions
hatt+0.680
Beer+0.658
coat+0.603
andr+0.602
ness+0.598
Neg logit contributions
orem-0.531
ril-0.519
 nerv-0.489
riors-0.476
 wills-0.473
Token,
Token ID11
Feature activation-4.52e-02

Pos logit contributions
hatt+0.500
Beer+0.481
coat+0.438
andr+0.437
ness+0.435
Neg logit contributions
orem-0.464
ril-0.454
 nerv-0.433
riors-0.421
 wills-0.419
Token run
Token ID1057
Feature activation+5.26e-01

Pos logit contributions
orem+0.074
ril+0.072
 nerv+0.070
riors+0.068
 wills+0.068
Neg logit contributions
hatt-0.065
Beer-0.063
andr-0.056
coat-0.056
ness-0.056
Token by
Token ID416
Feature activation+8.49e-01

Pos logit contributions
hatt+0.788
Beer+0.758
coat+0.684
andr+0.683
ness+0.681
Neg logit contributions
orem-0.836
ril-0.816
 nerv-0.782
riors-0.762
 wills-0.760
Token Indian
Token ID3942
Feature activation+3.23e-01

Pos logit contributions
hatt+1.292
Beer+1.240
coat+1.123
andr+1.122
ness+1.117
Neg logit contributions
orem-1.325
ril-1.297
 nerv-1.241
riors-1.209
 wills-1.200
Token Rail
Token ID12950
Feature activation+3.70e+00

Pos logit contributions
hatt+0.506
Beer+0.487
coat+0.442
andr+0.442
ness+0.440
Neg logit contributions
orem-0.489
ril-0.478
 nerv-0.457
riors-0.444
 wills-0.442
Tokenways
Token ID1322
Feature activation+1.39e+00

Pos logit contributions
hatt+2.240
Beer+2.020
andr+1.571
coat+1.551
ness+1.551
Neg logit contributions
orem-9.024
ril-8.936
 nerv-8.731
 wills-8.558
riors-8.486
Token,
Token ID11
Feature activation+3.03e-01

Pos logit contributions
hatt+2.032
Beer+1.953
coat+1.761
andr+1.759
ness+1.756
Neg logit contributions
orem-2.240
ril-2.193
 nerv-2.104
riors-2.052
 wills-2.037
Token operates
Token ID14051
Feature activation+8.33e-02

Pos logit contributions
hatt+0.491
Beer+0.473
coat+0.430
andr+0.430
ness+0.428
Neg logit contributions
orem-0.445
ril-0.435
 nerv-0.415
riors-0.403
 wills-0.401
Token from
Token ID422
Feature activation+3.01e-01

Pos logit contributions
hatt+0.125
Beer+0.120
andr+0.109
coat+0.109
ness+0.108
Neg logit contributions
orem-0.131
ril-0.128
 nerv-0.123
riors-0.120
 wills-0.120
Token Room
Token ID10096
Feature activation+5.94e-01

Pos logit contributions
hatt+0.465
Beer+0.448
coat+0.405
andr+0.405
ness+0.403
Neg logit contributions
orem-0.463
ril-0.452
 nerv-0.433
riors-0.421
 wills-0.419
Token.
Token ID13
Feature activation-4.64e-02

Pos logit contributions
hatt+0.518
Beer+0.497
coat+0.447
andr+0.447
ness+0.444
Neg logit contributions
orem-0.584
ril-0.571
 nerv-0.548
riors-0.534
 wills-0.532
Token With
Token ID2080
Feature activation+3.38e-01

Pos logit contributions
orem+0.073
ril+0.072
 nerv+0.069
riors+0.067
 wills+0.067
Neg logit contributions
hatt-0.070
Beer-0.067
coat-0.061
andr-0.061
ness-0.060
Token the
Token ID262
Feature activation-4.41e-02

Pos logit contributions
hatt+0.506
Beer+0.489
andr+0.440
coat+0.440
ness+0.435
Neg logit contributions
orem-0.534
ril-0.522
 nerv-0.503
riors-0.488
 wills-0.487
Token new
Token ID649
Feature activation+4.16e-01

Pos logit contributions
orem+0.071
ril+0.069
 nerv+0.067
 wills+0.064
riors+0.064
Neg logit contributions
hatt-0.066
Beer-0.063
andr-0.057
coat-0.057
ness-0.056
Token forecast
Token ID11092
Feature activation+1.20e+00

Pos logit contributions
hatt+0.595
Beer+0.574
andr+0.514
coat+0.510
ness+0.499
Neg logit contributions
orem-0.690
ril-0.673
 nerv-0.652
 wills-0.632
riors-0.629
Token track
Token ID2610
Feature activation+3.70e+00

Pos logit contributions
hatt+1.675
Beer+1.604
coat+1.438
andr+1.435
ness+1.431
Neg logit contributions
orem-2.019
ril-1.976
 nerv-1.897
riors-1.853
 wills-1.844
Token shifting
Token ID15852
Feature activation+8.67e-01

Pos logit contributions
hatt+5.049
Beer+4.778
ness+4.441
coat+4.383
andr+4.266
Neg logit contributions
orem-6.170
ril-6.036
 nerv-5.752
riors-5.641
 wills-5.613
Token the
Token ID262
Feature activation+1.16e-01

Pos logit contributions
hatt+1.248
Beer+1.195
coat+1.075
andr+1.074
ness+1.070
Neg logit contributions
orem-1.425
ril-1.395
 nerv-1.338
riors-1.305
 wills-1.298
Token cone
Token ID27763
Feature activation-2.58e-01

Pos logit contributions
hatt+0.164
Beer+0.157
andr+0.141
coat+0.140
ness+0.139
Neg logit contributions
orem-0.196
ril-0.191
 nerv-0.184
 wills-0.179
riors-0.179
Token of
Token ID286
Feature activation+2.09e-01

Pos logit contributions
orem+0.400
ril+0.393
 nerv+0.376
 wills+0.366
riors+0.365
Neg logit contributions
hatt-0.395
Beer-0.382
andr-0.344
coat-0.343
ness-0.338
Token concern
Token ID2328
Feature activation+2.33e-01

Pos logit contributions
hatt+0.321
Beer+0.309
andr+0.280
coat+0.279
ness+0.275
Neg logit contributions
orem-0.322
ril-0.315
 nerv-0.303
 wills-0.294
riors-0.293
Token equipment
Token ID5112
Feature activation+1.16e+00

Pos logit contributions
hatt+0.626
Beer+0.602
andr+0.544
coat+0.543
ness+0.538
Neg logit contributions
orem-0.648
ril-0.634
 nerv-0.606
 wills-0.590
riors-0.589
Token regulations
Token ID6647
Feature activation+1.53e+00

Pos logit contributions
hatt+1.762
Beer+1.692
coat+1.532
andr+1.530
ness+1.523
Neg logit contributions
orem-1.825
ril-1.786
 nerv-1.710
riors-1.664
 wills-1.656
Token borrowed
Token ID22546
Feature activation+3.98e-01

Pos logit contributions
hatt+2.214
Beer+2.122
coat+1.910
andr+1.908
ness+1.903
Neg logit contributions
orem-2.487
ril-2.436
 nerv-2.336
riors-2.278
 wills-2.266
Token from
Token ID422
Feature activation+1.56e-01

Pos logit contributions
hatt+0.603
Beer+0.579
coat+0.524
andr+0.523
ness+0.520
Neg logit contributions
orem-0.625
ril-0.611
 nerv-0.585
riors-0.570
 wills-0.567
Token modern
Token ID3660
Feature activation-9.47e-01

Pos logit contributions
hatt+0.243
Beer+0.233
coat+0.211
andr+0.211
ness+0.209
Neg logit contributions
orem-0.238
ril-0.232
 nerv-0.223
 wills-0.216
riors-0.215
Token track
Token ID2610
Feature activation+3.70e+00

Pos logit contributions
orem+1.626
ril+1.571
 nerv+1.512
 wills+1.489
riors+1.471
Neg logit contributions
hatt-1.311
Beer-1.254
andr-1.115
coat-1.106
ness-1.072
Token pursuit
Token ID14748
Feature activation+7.60e-01

Pos logit contributions
hatt+5.098
Beer+4.877
coat+4.464
ness+4.431
andr+4.342
Neg logit contributions
orem-6.088
ril-5.967
 nerv-5.714
riors-5.583
 wills-5.537
Token bikes
Token ID16715
Feature activation+1.10e+00

Pos logit contributions
hatt+1.043
Beer+0.998
coat+0.892
andr+0.891
ness+0.886
Neg logit contributions
orem-1.300
ril-1.274
 nerv-1.224
riors-1.195
 wills-1.190
Token.
Token ID13
Feature activation+1.16e-01

Pos logit contributions
hatt+1.524
Beer+1.450
coat+1.306
andr+1.301
ness+1.301
Neg logit contributions
orem-1.855
ril-1.821
 nerv-1.744
 wills-1.704
riors-1.703
Token UC
Token ID14417
Feature activation+9.99e-01

Pos logit contributions
hatt+0.177
Beer+0.170
andr+0.154
coat+0.154
ness+0.153
Neg logit contributions
orem-0.181
ril-0.178
 nerv-0.170
riors-0.166
 wills-0.164
TokenI
Token ID40
Feature activation+3.71e-01

Pos logit contributions
hatt+1.270
Beer+1.214
andr+1.073
coat+1.072
ness+1.065
Neg logit contributions
orem-1.809
ril-1.774
 nerv-1.711
riors-1.671
 wills-1.664
Token philosopher
Token ID23723
Feature activation-1.92e+00

Pos logit contributions
orem+1.513
ril+1.470
 nerv+1.420
riors+1.380
 wills+1.376
Neg logit contributions
hatt-1.575
Beer-1.520
coat-1.382
andr-1.376
ness-1.336
Token-
Token ID12
Feature activation-2.74e-01

Pos logit contributions
orem+2.997
ril+2.958
 nerv+2.836
riors+2.789
 wills+2.748
Neg logit contributions
hatt-2.864
Beer-2.782
andr-2.513
coat-2.501
ness-2.458
Tokenk
Token ID74
Feature activation-5.36e-01

Pos logit contributions
orem+0.487
ril+0.478
 nerv+0.460
riors+0.451
 wills+0.448
Neg logit contributions
hatt-0.356
Beer-0.342
coat-0.303
andr-0.302
ness-0.299
Tokenings
Token ID654
Feature activation+2.50e-02

Pos logit contributions
orem+0.912
ril+0.893
 nerv+0.863
 wills+0.837
riors+0.835
Neg logit contributions
hatt-0.746
Beer-0.709
andr-0.636
coat-0.634
ness-0.634
Token,
Token ID11
Feature activation+2.43e-01

Pos logit contributions
hatt+0.035
Beer+0.034
coat+0.030
andr+0.030
ness+0.030
Neg logit contributions
orem-0.042
ril-0.041
 nerv-0.039
riors-0.038
 wills-0.038
Token Watts
Token ID27555
Feature activation+3.69e+00

Pos logit contributions
hatt+0.373
Beer+0.359
coat+0.325
andr+0.325
ness+0.323
Neg logit contributions
orem-0.377
ril-0.369
 nerv-0.353
riors-0.344
 wills-0.342
TokenUp
Token ID4933
Feature activation+8.90e-01

Pos logit contributions
hatt+5.381
Beer+5.172
coat+4.746
ness+4.709
andr+4.708
Neg logit contributions
orem-5.794
ril-5.707
 nerv-5.348
riors-5.301
terior-5.222
TokenWith
Token ID3152
Feature activation+7.37e-01

Pos logit contributions
hatt+1.025
Beer+0.969
andr+0.847
coat+0.847
ness+0.836
Neg logit contributions
orem-1.721
ril-1.692
 nerv-1.632
riors-1.599
 wills-1.593
TokenThat
Token ID2504
Feature activation+1.29e+00

Pos logit contributions
hatt+0.859
Beer+0.761
andr+0.725
coat+0.698
ness+0.677
Neg logit contributions
orem-1.402
ril-1.400
 nerv-1.329
igation-1.315
 wills-1.306
Token is
Token ID318
Feature activation+5.12e-01

Pos logit contributions
hatt+2.003
Beer+1.931
ness+1.750
coat+1.749
andr+1.745
Neg logit contributions
orem-1.967
ril-1.925
 nerv-1.842
riors-1.787
 wills-1.779
Token now
Token ID783
Feature activation-5.50e-01

Pos logit contributions
hatt+0.756
Beer+0.725
coat+0.654
andr+0.653
ness+0.649
Neg logit contributions
orem-0.824
ril-0.806
 nerv-0.773
riors-0.753
 wills-0.750
Token Barack
Token ID8732
Feature activation+7.66e-01

Pos logit contributions
orem+1.681
ril+1.644
 nerv+1.573
riors+1.545
 wills+1.533
Neg logit contributions
hatt-1.367
Beer-1.304
andr-1.184
coat-1.166
ness-1.160
Token Obama
Token ID2486
Feature activation+6.79e-01

Pos logit contributions
hatt+1.162
Beer+1.117
coat+1.010
andr+1.009
ness+1.003
Neg logit contributions
orem-1.199
ril-1.173
 nerv-1.123
riors-1.093
 wills-1.089
Token gets
Token ID3011
Feature activation+7.63e-01

Pos logit contributions
hatt+1.010
Beer+0.970
coat+0.875
andr+0.874
ness+0.870
Neg logit contributions
orem-1.084
ril-1.060
 nerv-1.015
riors-0.989
 wills-0.985
Token fast
Token ID3049
Feature activation+7.44e-01

Pos logit contributions
hatt+1.129
Beer+1.084
coat+0.979
andr+0.976
ness+0.972
Neg logit contributions
orem-1.222
ril-1.196
 nerv-1.144
riors-1.117
 wills-1.111
Token-
Token ID12
Feature activation+3.32e-02

Pos logit contributions
hatt+1.027
Beer+0.985
andr+0.881
coat+0.878
ness+0.870
Neg logit contributions
orem-1.267
ril-1.241
 nerv-1.194
riors-1.163
 wills-1.161
Tokentrack
Token ID11659
Feature activation+3.69e+00

Pos logit contributions
hatt+0.034
Beer+0.032
andr+0.027
coat+0.027
ness+0.027
Neg logit contributions
orem-0.068
ril-0.067
 nerv-0.064
riors-0.063
 wills-0.063
Token approval
Token ID7546
Feature activation+1.75e+00

Pos logit contributions
hatt+4.840
Beer+4.619
ness+4.248
coat+4.174
andr+4.038
Neg logit contributions
orem-6.302
ril-6.233
 nerv-5.997
riors-5.888
rior-5.805
Token for
Token ID329
Feature activation+1.93e-01

Pos logit contributions
hatt+2.616
Beer+2.499
coat+2.271
ness+2.269
andr+2.248
Neg logit contributions
orem-2.779
ril-2.706
 nerv-2.584
riors-2.523
 wills-2.508
Token TP
Token ID24525
Feature activation+3.72e-02

Pos logit contributions
hatt+0.292
Beer+0.281
coat+0.254
andr+0.254
ness+0.253
Neg logit contributions
orem-0.303
ril-0.296
 nerv-0.284
riors-0.276
 wills-0.275
TokenPA
Token ID4537
Feature activation+4.25e-01

Pos logit contributions
hatt+0.050
Beer+0.048
andr+0.043
coat+0.043
ness+0.042
Neg logit contributions
orem-0.065
ril-0.063
 nerv-0.061
riors-0.059
 wills-0.059
Token
Token ID198
Feature activation+2.20e-01

Pos logit contributions
hatt+0.639
Beer+0.613
andr+0.555
coat+0.554
ness+0.548
Neg logit contributions
orem-0.672
ril-0.658
 nerv-0.630
riors-0.614
 wills-0.613
TokenOn
Token ID2202
Feature activation+5.62e-01

Pos logit contributions
hatt+0.067
Beer+0.063
andr+0.057
coat+0.057
ness+0.056
Neg logit contributions
orem-0.083
ril-0.082
 nerv-0.078
riors-0.077
igation-0.076
Token the
Token ID262
Feature activation+1.26e-01

Pos logit contributions
hatt+0.860
Beer+0.824
coat+0.749
andr+0.747
ness+0.746
Neg logit contributions
orem-0.874
ril-0.854
 nerv-0.817
riors-0.797
 wills-0.792
Token reverse
Token ID9575
Feature activation+1.04e+00

Pos logit contributions
hatt+0.214
Beer+0.207
coat+0.190
andr+0.189
ness+0.189
Neg logit contributions
orem-0.174
ril-0.170
 nerv-0.162
riors-0.157
 wills-0.156
Token side
Token ID1735
Feature activation+9.43e-01

Pos logit contributions
hatt+1.339
Beer+1.282
coat+1.162
ness+1.161
andr+1.134
Neg logit contributions
orem-1.844
ril-1.809
 nerv-1.727
riors-1.704
 wills-1.688
Token,
Token ID11
Feature activation+1.06e-01

Pos logit contributions
hatt+1.404
Beer+1.352
coat+1.237
ness+1.230
andr+1.221
Neg logit contributions
orem-1.497
ril-1.464
 nerv-1.391
riors-1.361
 wills-1.358
Token Watts
Token ID27555
Feature activation+3.67e+00

Pos logit contributions
hatt+0.166
Beer+0.160
coat+0.145
andr+0.145
ness+0.144
Neg logit contributions
orem-0.161
ril-0.157
 nerv-0.150
riors-0.146
 wills-0.145
Token is
Token ID318
Feature activation+5.82e-01

Pos logit contributions
hatt+5.899
Beer+5.603
ness+5.347
coat+5.180
andr+5.134
Neg logit contributions
orem-5.213
ril-5.099
 nerv-4.680
riors-4.650
igation-4.604
Token pictured
Token ID17915
Feature activation-2.66e-01

Pos logit contributions
hatt+0.911
Beer+0.875
coat+0.796
andr+0.793
ness+0.792
Neg logit contributions
orem-0.885
ril-0.864
 nerv-0.825
riors-0.805
 wills-0.799
Token below
Token ID2174
Feature activation+1.50e+00

Pos logit contributions
orem+0.404
ril+0.397
 nerv+0.380
 wills+0.368
riors+0.368
Neg logit contributions
hatt-0.415
Beer-0.401
andr-0.364
coat-0.362
ness-0.358
Token a
Token ID257
Feature activation+2.59e-01

Pos logit contributions
hatt+2.228
Beer+2.125
coat+1.947
ness+1.938
andr+1.909
Neg logit contributions
orem-2.407
ril-2.340
 nerv-2.229
riors-2.196
 wills-2.173
Token line
Token ID1627
Feature activation+6.84e-02

Pos logit contributions
hatt+0.400
Beer+0.385
coat+0.350
ness+0.348
andr+0.348
Neg logit contributions
orem-0.398
ril-0.390
 nerv-0.371
riors-0.364
 wills-0.360
Token
Token ID198
Feature activation+1.88e-01

Pos logit contributions
orem+0.452
ril+0.443
 nerv+0.424
riors+0.413
 wills+0.410
Neg logit contributions
hatt-0.433
Beer-0.415
andr-0.376
coat-0.376
ness-0.373
Token
Token ID198
Feature activation-8.13e-02

Pos logit contributions
hatt+0.305
Beer+0.292
andr+0.269
coat+0.266
ness+0.260
Neg logit contributions
orem-0.270
ril-0.267
 nerv-0.250
riors-0.247
rior-0.246
TokenThe
Token ID464
Feature activation-5.69e-01

Pos logit contributions
orem+0.138
ril+0.135
 nerv+0.128
riors+0.126
rior+0.125
Neg logit contributions
hatt-0.113
Beer-0.107
andr-0.097
coat-0.097
ness-0.095
Token renovations
Token ID44481
Feature activation-6.99e-03

Pos logit contributions
orem+0.878
ril+0.853
 nerv+0.818
riors+0.793
 wills+0.793
Neg logit contributions
hatt-0.879
Beer-0.845
andr-0.768
coat-0.766
ness-0.759
Token include
Token ID2291
Feature activation-1.48e+00

Pos logit contributions
orem+0.011
ril+0.011
 nerv+0.010
riors+0.010
 wills+0.010
Neg logit contributions
hatt-0.011
Beer-0.010
coat-0.009
andr-0.009
ness-0.009
Token bump
Token ID13852
Feature activation+3.64e+00

Pos logit contributions
orem+2.279
ril+2.247
 nerv+2.151
 wills+2.089
riors+2.081
Neg logit contributions
hatt-2.260
Beer-2.171
andr-1.974
coat-1.963
ness-1.938
Tokening
Token ID278
Feature activation-2.74e-01

Pos logit contributions
hatt+4.703
Beer+4.449
coat+3.987
ness+3.984
andr+3.966
Neg logit contributions
orem-6.427
ril-6.235
 nerv-6.004
riors-5.922
igation-5.845
Token the
Token ID262
Feature activation-3.49e-01

Pos logit contributions
orem+0.485
ril+0.476
 nerv+0.459
 wills+0.448
riors+0.447
Neg logit contributions
hatt-0.357
Beer-0.342
andr-0.303
coat-0.303
ness-0.300
Token capacity
Token ID5339
Feature activation+8.19e-01

Pos logit contributions
orem+0.513
ril+0.497
 nerv+0.477
 wills+0.462
riors+0.460
Neg logit contributions
hatt-0.565
Beer-0.545
andr-0.498
coat-0.496
ness-0.492
Token from
Token ID422
Feature activation-3.20e-01

Pos logit contributions
hatt+1.201
Beer+1.152
coat+1.038
ness+1.035
andr+1.035
Neg logit contributions
orem-1.326
ril-1.299
 nerv-1.241
riors-1.213
 wills-1.206
Token 1
Token ID352
Feature activation-5.27e-01

Pos logit contributions
orem+0.474
ril+0.463
 nerv+0.444
riors+0.430
 wills+0.429
Neg logit contributions
hatt-0.511
Beer-0.493
andr-0.448
coat-0.448
ness-0.444
Token saw
Token ID2497
Feature activation-3.94e-01

Pos logit contributions
orem+1.645
ril+1.598
 nerv+1.543
 wills+1.490
igation+1.472
Neg logit contributions
hatt-1.828
Beer-1.811
andr-1.622
coat-1.619
ness-1.588
Token it
Token ID340
Feature activation-3.28e-01

Pos logit contributions
orem+0.576
ril+0.562
 nerv+0.537
 wills+0.521
riors+0.520
Neg logit contributions
hatt-0.639
Beer-0.615
coat-0.561
andr-0.561
ness-0.554
Token listed
Token ID5610
Feature activation-3.52e-01

Pos logit contributions
orem+0.512
ril+0.501
 nerv+0.480
riors+0.466
 wills+0.464
Neg logit contributions
hatt-0.500
Beer-0.482
andr-0.435
coat-0.435
ness-0.431
Token for
Token ID329
Feature activation-2.48e-01

Pos logit contributions
orem+0.544
ril+0.533
 nerv+0.511
riors+0.494
 wills+0.494
Neg logit contributions
hatt-0.539
Beer-0.521
andr-0.470
coat-0.470
ness-0.465
Token the
Token ID262
Feature activation-3.03e-03

Pos logit contributions
orem+0.360
ril+0.352
 nerv+0.336
riors+0.326
 wills+0.324
Neg logit contributions
hatt-0.404
Beer-0.389
coat-0.354
andr-0.354
ness-0.352
Token coax
Token ID37700
Feature activation+3.63e+00

Pos logit contributions
orem+0.004
ril+0.004
 nerv+0.004
riors+0.004
 wills+0.004
Neg logit contributions
hatt-0.005
Beer-0.005
coat-0.004
andr-0.004
ness-0.004
Token connection
Token ID4637
Feature activation-1.55e-01

Pos logit contributions
hatt+5.804
Beer+5.465
ness+5.162
coat+5.061
andr+5.007
Neg logit contributions
orem-5.103
ril-5.035
 nerv-4.806
riors-4.710
 wills-4.645
Token.
Token ID13
Feature activation+2.84e-01

Pos logit contributions
orem+0.253
ril+0.247
 nerv+0.237
riors+0.231
 wills+0.230
Neg logit contributions
hatt-0.225
Beer-0.216
andr-0.194
coat-0.194
ness-0.193
Token Disable
Token ID31529
Feature activation+8.19e-01

Pos logit contributions
hatt+0.431
Beer+0.415
coat+0.375
andr+0.375
ness+0.373
Neg logit contributions
orem-0.444
ril-0.434
 nerv-0.416
riors-0.405
 wills-0.404
Token the
Token ID262
Feature activation+1.69e-01

Pos logit contributions
hatt+1.295
Beer+1.245
coat+1.132
ness+1.129
andr+1.128
Neg logit contributions
orem-1.229
ril-1.205
 nerv-1.152
riors-1.122
 wills-1.111
Token Wireless
Token ID24365
Feature activation+2.65e-01

Pos logit contributions
hatt+0.262
Beer+0.252
andr+0.229
coat+0.229
ness+0.227
Neg logit contributions
orem-0.258
ril-0.251
 nerv-0.241
riors-0.234
 wills-0.233
Token
Token ID198
Feature activation+7.81e-02

Pos logit contributions
hatt+0.375
Beer+0.359
andr+0.331
coat+0.326
ness+0.319
Neg logit contributions
orem-0.334
ril-0.329
 nerv-0.308
riors-0.305
rior-0.302
TokenEx
Token ID3109
Feature activation-1.03e+00

Pos logit contributions
hatt+0.103
Beer+0.097
andr+0.088
coat+0.087
ness+0.086
Neg logit contributions
orem-0.137
ril-0.135
 nerv-0.128
riors-0.127
rior-0.125
Tokenamine
Token ID9862
Feature activation-6.91e-01

Pos logit contributions
orem+1.389
ril+1.352
 nerv+1.273
riors+1.244
rior+1.230
Neg logit contributions
hatt-1.774
Beer-1.722
andr-1.573
ness-1.569
coat-1.568
Token all
Token ID477
Feature activation+2.24e-01

Pos logit contributions
orem+1.041
ril+1.010
 nerv+0.970
 wills+0.943
riors+0.937
Neg logit contributions
hatt-1.092
Beer-1.054
andr-0.953
coat-0.946
ness-0.941
Token the
Token ID262
Feature activation-1.50e-01

Pos logit contributions
hatt+0.356
Beer+0.341
coat+0.312
andr+0.310
ness+0.309
Neg logit contributions
orem-0.334
ril-0.328
 nerv-0.312
riors-0.304
 wills-0.302
Token vit
Token ID9090
Feature activation-4.92e+00

Pos logit contributions
orem+0.226
ril+0.220
 nerv+0.210
riors+0.204
 wills+0.204
Neg logit contributions
hatt-0.237
Beer-0.228
andr-0.207
coat-0.207
ness-0.206
Tokenrified
Token ID41301
Feature activation-5.08e-01

Pos logit contributions
ril+7.498
orem+7.299
igation+6.773
riors+6.720
 nerv+6.704
Neg logit contributions
hatt-7.334
Beer-7.156
coat-6.375
andr-6.331
ness-6.254
Token test
Token ID1332
Feature activation+1.36e-01

Pos logit contributions
orem+0.744
ril+0.725
 nerv+0.694
 wills+0.673
riors+0.672
Neg logit contributions
hatt-0.822
Beer-0.792
andr-0.720
coat-0.719
ness-0.711
Token chamber
Token ID11847
Feature activation+6.59e-02

Pos logit contributions
hatt+0.197
Beer+0.189
coat+0.171
andr+0.170
ness+0.170
Neg logit contributions
orem-0.223
ril-0.218
 nerv-0.210
riors-0.204
 wills-0.203
Token doors
Token ID8215
Feature activation-4.12e-01

Pos logit contributions
hatt+0.102
Beer+0.098
andr+0.089
coat+0.089
ness+0.088
Neg logit contributions
orem-0.101
ril-0.099
 nerv-0.095
riors-0.092
 wills-0.092
Token (
Token ID357
Feature activation+9.77e-01

Pos logit contributions
orem+0.634
ril+0.620
 nerv+0.595
riors+0.576
 wills+0.574
Neg logit contributions
hatt-0.635
Beer-0.614
andr-0.555
coat-0.552
ness-0.547
Token is
Token ID318
Feature activation+4.78e-01

Pos logit contributions
orem+0.340
ril+0.332
 nerv+0.317
riors+0.308
 wills+0.307
Neg logit contributions
hatt-0.389
Beer-0.374
coat-0.342
andr-0.342
ness-0.339
Token on
Token ID319
Feature activation+5.80e-02

Pos logit contributions
hatt+0.706
Beer+0.680
coat+0.614
andr+0.613
ness+0.609
Neg logit contributions
orem-0.764
ril-0.748
 nerv-0.720
riors-0.700
 wills-0.696
Token the
Token ID262
Feature activation-1.47e-01

Pos logit contributions
hatt+0.091
Beer+0.089
coat+0.080
andr+0.080
ness+0.079
Neg logit contributions
orem-0.087
ril-0.085
 nerv-0.082
 wills-0.080
riors-0.079
Token edge
Token ID5743
Feature activation-1.34e+00

Pos logit contributions
orem+0.232
ril+0.226
 nerv+0.219
 wills+0.212
riors+0.212
Neg logit contributions
hatt-0.219
Beer-0.211
coat-0.191
andr-0.190
ness-0.189
Token of
Token ID286
Feature activation+4.63e-02

Pos logit contributions
orem+1.841
ril+1.799
 nerv+1.719
riors+1.663
 wills+1.646
Neg logit contributions
hatt-2.282
Beer-2.211
coat-2.026
andr-2.020
ness-2.002
Token vit
Token ID9090
Feature activation-4.64e+00

Pos logit contributions
hatt+0.070
Beer+0.068
andr+0.061
coat+0.061
ness+0.061
Neg logit contributions
orem-0.073
ril-0.071
 nerv-0.068
riors-0.066
 wills-0.066
Tokenicultural
Token ID26823
Feature activation+6.80e-01

Pos logit contributions
ril+5.676
orem+5.521
igation+5.124
rior+4.911
 nerv+4.810
Neg logit contributions
hatt-8.249
Beer-8.187
andr-7.374
coat-7.362
ness-7.295
Token viability
Token ID32141
Feature activation-1.15e+00

Pos logit contributions
hatt+0.975
Beer+0.935
coat+0.841
andr+0.840
ness+0.832
Neg logit contributions
orem-1.121
ril-1.098
 nerv-1.056
riors-1.028
 wills-1.025
Token,
Token ID11
Feature activation+6.92e-02

Pos logit contributions
orem+1.925
ril+1.888
 nerv+1.834
riors+1.769
igation+1.768
Neg logit contributions
hatt-1.613
Beer-1.552
andr-1.404
coat-1.391
ness-1.355
Token the
Token ID262
Feature activation-1.39e-01

Pos logit contributions
hatt+0.105
Beer+0.101
coat+0.092
andr+0.092
ness+0.091
Neg logit contributions
orem-0.108
ril-0.105
 nerv-0.101
riors-0.098
 wills-0.098
Token math
Token ID10688
Feature activation+2.14e-01

Pos logit contributions
orem+0.223
ril+0.217
 nerv+0.210
riors+0.203
 wills+0.203
Neg logit contributions
hatt-0.206
Beer-0.198
coat-0.179
andr-0.179
ness-0.177
Token arsenal
Token ID24375
Feature activation-1.90e+00

Pos logit contributions
orem+0.838
ril+0.820
 nerv+0.787
riors+0.766
 wills+0.764
Neg logit contributions
hatt-0.754
Beer-0.725
andr-0.652
coat-0.651
ness-0.647
Token of
Token ID286
Feature activation-1.14e-01

Pos logit contributions
orem+2.583
ril+2.543
 nerv+2.424
 wills+2.350
riors+2.350
Neg logit contributions
hatt-3.232
Beer-3.139
andr-2.865
coat-2.843
ness-2.827
Token the
Token ID262
Feature activation-8.49e-02

Pos logit contributions
orem+0.162
ril+0.158
 nerv+0.150
riors+0.146
 wills+0.145
Neg logit contributions
hatt-0.191
Beer-0.184
coat-0.168
andr-0.168
ness-0.167
Token Ban
Token ID10274
Feature activation+6.56e-01

Pos logit contributions
orem+0.129
ril+0.126
 nerv+0.120
riors+0.117
 wills+0.117
Neg logit contributions
hatt-0.133
Beer-0.128
andr-0.116
coat-0.116
ness-0.116
Tokenu
Token ID84
Feature activation-9.94e-01

Pos logit contributions
hatt+0.886
Beer+0.833
andr+0.745
ness+0.743
coat+0.743
Neg logit contributions
orem-1.144
ril-1.113
 nerv-1.081
riors-1.053
 wills-1.052
Token Qur
Token ID17599
Feature activation-4.34e+00

Pos logit contributions
orem+0.912
ril+0.877
 nerv+0.813
riors+0.774
 wills+0.768
Neg logit contributions
hatt-2.154
Beer-2.096
coat-1.959
andr-1.957
ness-1.948
Tokenay
Token ID323
Feature activation-3.32e-01

Pos logit contributions
orem+6.205
ril+6.088
 nerv+5.656
riors+5.504
igation+5.482
Neg logit contributions
Beer-6.693
hatt-6.652
coat-6.047
andr-5.967
ness-5.928
Tokenza
Token ID4496
Feature activation+1.12e+00

Pos logit contributions
orem+0.518
ril+0.508
 nerv+0.482
riors+0.474
rior+0.465
Neg logit contributions
hatt-0.503
Beer-0.485
coat-0.437
andr-0.435
ness-0.428
Token which
Token ID543
Feature activation+3.08e-01

Pos logit contributions
hatt+1.715
Beer+1.632
ness+1.486
coat+1.484
andr+1.480
Neg logit contributions
orem-1.750
ril-1.703
 nerv-1.616
riors-1.585
igation-1.571
Token consisted
Token ID19954
Feature activation-1.49e+00

Pos logit contributions
hatt+0.485
Beer+0.465
coat+0.423
andr+0.423
ness+0.421
Neg logit contributions
orem-0.465
ril-0.454
 nerv-0.435
riors-0.422
 wills-0.419
Token of
Token ID286
Feature activation-3.75e-02

Pos logit contributions
orem+2.077
ril+2.044
 nerv+1.943
riors+1.887
 wills+1.880
Neg logit contributions
hatt-2.488
Beer-2.405
andr-2.193
coat-2.188
ness-2.176
Token been
Token ID587
Feature activation-2.30e-01

Pos logit contributions
orem+0.621
ril+0.609
 nerv+0.578
 wills+0.561
riors+0.561
Neg logit contributions
hatt-0.656
Beer-0.639
andr-0.577
coat-0.571
ness-0.566
Token revealed
Token ID4602
Feature activation-1.93e-01

Pos logit contributions
orem+0.390
ril+0.382
 nerv+0.368
 wills+0.359
riors+0.357
Neg logit contributions
hatt-0.314
Beer-0.309
andr-0.273
coat-0.271
ness-0.265
Token.
Token ID13
Feature activation-5.89e-02

Pos logit contributions
orem+0.314
ril+0.309
 nerv+0.295
riors+0.287
 wills+0.286
Neg logit contributions
hatt-0.279
Beer-0.269
coat-0.242
andr-0.241
ness-0.237
Token
Token ID198
Feature activation-1.60e-02

Pos logit contributions
orem+0.093
ril+0.091
 nerv+0.087
riors+0.085
 wills+0.084
Neg logit contributions
hatt-0.089
Beer-0.086
coat-0.077
andr-0.077
ness-0.077
Token
Token ID198
Feature activation-2.72e-01

Pos logit contributions
orem+0.023
ril+0.023
 nerv+0.021
riors+0.021
rior+0.021
Neg logit contributions
hatt-0.026
Beer-0.025
andr-0.023
coat-0.023
ness-0.022
TokenGil
Token ID40747
Feature activation-4.28e+00

Pos logit contributions
orem+0.459
ril+0.452
 nerv+0.427
riors+0.421
igation+0.417
Neg logit contributions
hatt-0.376
Beer-0.356
coat-0.322
andr-0.322
ness-0.318
Tokenad
Token ID324
Feature activation-3.67e-01

Pos logit contributions
orem+6.426
ril+6.424
 nerv+5.987
 wills+5.876
riors+5.846
Neg logit contributions
hatt-6.318
Beer-6.182
coat-5.560
andr-5.424
Feel-5.373
Token Perry
Token ID14105
Feature activation+9.01e-01

Pos logit contributions
orem+0.579
ril+0.567
 nerv+0.543
riors+0.529
 wills+0.526
Neg logit contributions
hatt-0.552
Beer-0.530
coat-0.479
andr-0.478
ness-0.476
Token,
Token ID11
Feature activation-2.56e-02

Pos logit contributions
hatt+1.242
Beer+1.185
coat+1.062
ness+1.061
andr+1.060
Neg logit contributions
orem-1.536
ril-1.503
 nerv-1.451
riors-1.415
 wills-1.407
Token D
Token ID360
Feature activation+9.88e-01

Pos logit contributions
orem+0.041
ril+0.040
 nerv+0.039
riors+0.038
 wills+0.038
Neg logit contributions
hatt-0.038
Beer-0.036
coat-0.033
andr-0.033
ness-0.033
Tokenror
Token ID1472
Feature activation+8.41e-01

Pos logit contributions
hatt+1.906
Beer+1.834
andr+1.705
ness+1.704
coat+1.698
Neg logit contributions
orem-1.141
ril-1.104
 nerv-1.056
 wills-1.014
riors-1.013
Token last
Token ID938
Feature activation-3.25e-01

Pos logit contributions
hatt+1.398
Beer+1.331
coat+1.202
ness+1.201
andr+1.201
Neg logit contributions
orem-1.576
ril-1.535
 nerv-1.470
riors-1.437
 wills-1.434
Token year
Token ID614
Feature activation+4.33e-01

Pos logit contributions
orem+0.719
ril+0.709
 nerv+0.689
 wills+0.673
riors+0.673
Neg logit contributions
hatt-0.281
Beer-0.262
andr-0.216
coat-0.216
ness-0.210
Token.
Token ID13
Feature activation+1.85e-01

Pos logit contributions
hatt+0.610
Beer+0.584
coat+0.524
andr+0.524
ness+0.521
Neg logit contributions
orem-0.725
ril-0.710
 nerv-0.681
riors-0.665
 wills-0.662
Token
Token ID198
Feature activation+2.38e-01

Pos logit contributions
hatt+0.278
Beer+0.267
coat+0.241
andr+0.241
ness+0.239
Neg logit contributions
orem-0.293
ril-0.286
 nerv-0.274
riors-0.267
 wills-0.265
Token
Token ID198
Feature activation-1.42e-02

Pos logit contributions
hatt+0.387
Beer+0.370
andr+0.341
coat+0.337
ness+0.330
Neg logit contributions
orem-0.343
ril-0.338
 nerv-0.316
riors-0.312
rior-0.311
TokenGil
Token ID40747
Feature activation-4.18e+00

Pos logit contributions
orem+0.025
ril+0.025
 nerv+0.024
riors+0.023
rior+0.023
Neg logit contributions
hatt-0.018
Beer-0.017
coat-0.015
andr-0.015
ness-0.015
Tokenbert
Token ID4835
Feature activation-2.00e-01

Pos logit contributions
ril+4.333
orem+4.245
riors+3.746
igation+3.724
 nerv+3.716
Neg logit contributions
hatt-8.234
Beer-8.114
Feel-7.389
coat-7.365
andr-7.248
Token is
Token ID318
Feature activation+3.10e-01

Pos logit contributions
orem+0.300
ril+0.294
 nerv+0.282
riors+0.273
 wills+0.273
Neg logit contributions
hatt-0.315
Beer-0.305
coat-0.276
andr-0.275
ness-0.273
Token known
Token ID1900
Feature activation+3.22e-01

Pos logit contributions
hatt+0.456
Beer+0.438
coat+0.395
andr+0.394
ness+0.392
Neg logit contributions
orem-0.499
ril-0.488
 nerv-0.468
riors-0.456
 wills-0.454
Token as
Token ID355
Feature activation-4.84e-02

Pos logit contributions
hatt+0.514
Beer+0.495
coat+0.450
andr+0.450
ness+0.448
Neg logit contributions
orem-0.480
ril-0.468
 nerv-0.447
riors-0.435
 wills-0.433
Token a
Token ID257
Feature activation-8.77e-03

Pos logit contributions
orem+0.078
ril+0.076
 nerv+0.073
riors+0.071
 wills+0.071
Neg logit contributions
hatt-0.072
Beer-0.069
coat-0.062
andr-0.062
ness-0.062
Token the
Token ID262
Feature activation-2.62e-01

Pos logit contributions
orem+0.261
ril+0.256
 nerv+0.244
riors+0.238
 wills+0.237
Neg logit contributions
hatt-0.271
Beer-0.261
andr-0.237
coat-0.237
ness-0.235
Token men
Token ID1450
Feature activation-7.08e-01

Pos logit contributions
orem+0.399
ril+0.390
 nerv+0.373
riors+0.363
 wills+0.362
Neg logit contributions
hatt-0.410
Beer-0.394
andr-0.358
coat-0.358
ness-0.355
Token of
Token ID286
Feature activation-1.18e-01

Pos logit contributions
orem+1.127
ril+1.108
 nerv+1.057
riors+1.030
 wills+1.027
Neg logit contributions
hatt-1.051
Beer-1.019
andr-0.914
coat-0.913
ness-0.900
Token Ban
Token ID10274
Feature activation+6.29e-01

Pos logit contributions
orem+0.180
ril+0.176
 nerv+0.168
 wills+0.164
riors+0.164
Neg logit contributions
hatt-0.183
Beer-0.176
andr-0.160
coat-0.160
ness-0.159
Tokenu
Token ID84
Feature activation-1.18e+00

Pos logit contributions
hatt+0.922
Beer+0.882
andr+0.795
coat+0.795
ness+0.791
Neg logit contributions
orem-1.020
ril-0.997
 nerv-0.957
riors-0.933
 wills-0.929
Token Qur
Token ID17599
Feature activation-4.16e+00

Pos logit contributions
orem+1.797
ril+1.747
 nerv+1.671
 wills+1.628
riors+1.627
Neg logit contributions
hatt-1.839
Beer-1.772
coat-1.624
andr-1.615
ness-1.595
Tokenay
Token ID323
Feature activation-3.86e-01

Pos logit contributions
orem+6.444
ril+6.382
 nerv+5.917
riors+5.804
igation+5.748
Neg logit contributions
Beer-5.918
hatt-5.887
andr-5.253
coat-5.220
Feel-5.170
Tokenza
Token ID4496
Feature activation+1.33e+00

Pos logit contributions
orem+0.651
ril+0.636
 nerv+0.612
riors+0.596
 wills+0.596
Neg logit contributions
hatt-0.541
Beer-0.518
andr-0.464
coat-0.464
ness-0.462
Token,
Token ID11
Feature activation-1.00e-02

Pos logit contributions
hatt+1.921
Beer+1.820
ness+1.649
andr+1.647
coat+1.638
Neg logit contributions
orem-2.175
ril-2.128
 nerv-2.042
riors-1.996
 wills-1.984
Token the
Token ID262
Feature activation-2.00e-01

Pos logit contributions
orem+0.016
ril+0.016
 nerv+0.015
riors+0.015
 wills+0.015
Neg logit contributions
hatt-0.015
Beer-0.014
coat-0.013
andr-0.013
ness-0.013
Token ensl
Token ID25563
Feature activation+2.03e+00

Pos logit contributions
orem+0.308
ril+0.301
 nerv+0.288
 wills+0.280
riors+0.280
Neg logit contributions
hatt-0.310
Beer-0.298
andr-0.271
coat-0.270
ness-0.268
Token/
Token ID14
Feature activation+4.46e-01

Pos logit contributions
orem+0.166
ril+0.164
 nerv+0.157
riors+0.153
 wills+0.152
Neg logit contributions
hatt-0.160
Beer-0.155
andr-0.140
coat-0.139
ness-0.137
TokenAP
Token ID2969
Feature activation-4.68e-01

Pos logit contributions
hatt+0.576
Beer+0.550
andr+0.488
coat+0.487
ness+0.484
Neg logit contributions
orem-0.798
ril-0.783
 nerv-0.752
riors-0.737
 wills-0.733
Token)
Token ID8
Feature activation-3.66e-01

Pos logit contributions
orem+0.831
ril+0.813
 nerv+0.784
riors+0.765
 wills+0.763
Neg logit contributions
hatt-0.613
Beer-0.584
coat-0.520
andr-0.519
ness-0.518
Token
Token ID198
Feature activation+1.84e-01

Pos logit contributions
orem+0.581
ril+0.567
 nerv+0.546
 wills+0.530
riors+0.529
Neg logit contributions
hatt-0.549
Beer-0.527
coat-0.477
andr-0.476
ness-0.474
Token
Token ID198
Feature activation-3.87e-02

Pos logit contributions
hatt+0.298
Beer+0.285
andr+0.262
coat+0.259
ness+0.254
Neg logit contributions
orem-0.269
ril-0.265
 nerv-0.249
riors-0.245
rior-0.243
TokenGil
Token ID40747
Feature activation-4.09e+00

Pos logit contributions
orem+0.067
ril+0.066
 nerv+0.062
riors+0.062
igation+0.061
Neg logit contributions
hatt-0.052
Beer-0.049
andr-0.044
coat-0.044
ness-0.044
Tokenbert
Token ID4835
Feature activation-4.98e-01

Pos logit contributions
orem+4.394
ril+4.352
riors+3.845
 nerv+3.838
igation+3.822
Neg logit contributions
hatt-7.966
Beer-7.841
coat-7.131
Feel-7.072
andr-7.028
Token and
Token ID290
Feature activation-4.06e-01

Pos logit contributions
orem+0.774
ril+0.757
 nerv+0.729
 wills+0.710
riors+0.704
Neg logit contributions
hatt-0.757
Beer-0.733
andr-0.660
coat-0.658
ness-0.647
Token the
Token ID262
Feature activation-4.77e-01

Pos logit contributions
orem+0.599
ril+0.584
 nerv+0.556
riors+0.540
 wills+0.538
Neg logit contributions
hatt-0.654
Beer-0.631
andr-0.572
coat-0.572
ness-0.567
Token ACLU
Token ID24381
Feature activation-5.11e-01

Pos logit contributions
orem+0.588
ril+0.567
 nerv+0.534
 wills+0.516
riors+0.516
Neg logit contributions
hatt-0.886
Beer-0.860
andr-0.790
coat-0.790
ness-0.785
Token have
Token ID423
Feature activation-1.17e+00

Pos logit contributions
orem+0.717
ril+0.700
 nerv+0.666
 wills+0.646
riors+0.645
Neg logit contributions
hatt-0.858
Beer-0.830
andr-0.756
coat-0.754
ness-0.747
Token Mohammad
Token ID29674
Feature activation-7.43e-01

Pos logit contributions
hatt+1.758
Beer+1.687
ness+1.530
andr+1.523
coat+1.513
Neg logit contributions
orem-1.934
ril-1.896
 nerv-1.804
riors-1.766
 wills-1.751
Token School
Token ID3961
Feature activation+2.23e+00

Pos logit contributions
orem+1.150
ril+1.123
 nerv+1.082
riors+1.047
 wills+1.045
Neg logit contributions
hatt-1.139
Beer-1.097
andr-0.990
coat-0.989
ness-0.972
Token teaching
Token ID7743
Feature activation+1.87e+00

Pos logit contributions
hatt+3.421
Beer+3.289
ness+3.034
coat+3.017
andr+2.981
Neg logit contributions
orem-3.389
ril-3.308
 nerv-3.153
riors-3.074
 wills-3.060
Token "
Token ID366
Feature activation+9.18e-01

Pos logit contributions
hatt+2.809
Beer+2.694
ness+2.476
coat+2.459
andr+2.436
Neg logit contributions
orem-2.904
ril-2.860
 nerv-2.723
riors-2.666
igation-2.625
Tokena
Token ID64
Feature activation+3.35e-01

Pos logit contributions
hatt+1.270
Beer+1.216
andr+1.088
coat+1.088
ness+1.079
Neg logit contributions
orem-1.562
ril-1.530
 nerv-1.468
riors-1.434
 wills-1.428
Token Qur
Token ID17599
Feature activation-4.06e+00

Pos logit contributions
hatt+0.492
Beer+0.473
andr+0.426
coat+0.425
ness+0.420
Neg logit contributions
orem-0.543
ril-0.531
 nerv-0.511
riors-0.497
 wills-0.495
Token'
Token ID6
Feature activation-1.03e-02

Pos logit contributions
orem+6.029
ril+5.945
 nerv+5.536
riors+5.425
igation+5.407
Neg logit contributions
hatt-6.267
Beer-6.241
coat-5.602
andr-5.578
ness-5.431
Tokenan
Token ID272
Feature activation-3.93e-01

Pos logit contributions
orem+0.018
ril+0.018
 nerv+0.017
riors+0.017
 wills+0.016
Neg logit contributions
hatt-0.014
Beer-0.013
coat-0.012
andr-0.012
ness-0.012
Token-
Token ID12
Feature activation-8.66e-02

Pos logit contributions
orem+0.622
ril+0.609
 nerv+0.586
riors+0.571
 wills+0.567
Neg logit contributions
hatt-0.587
Beer-0.566
andr-0.511
coat-0.509
ness-0.503
Tokenguided
Token ID23657
Feature activation+1.97e-01

Pos logit contributions
orem+0.148
ril+0.146
 nerv+0.140
riors+0.137
 wills+0.136
Neg logit contributions
hatt-0.117
Beer-0.113
andr-0.101
coat-0.100
ness-0.099
Token journey
Token ID7002
Feature activation+6.99e-01

Pos logit contributions
hatt+0.295
Beer+0.285
coat+0.257
andr+0.257
ness+0.251
Neg logit contributions
orem-0.314
ril-0.306
 nerv-0.295
riors-0.286
 wills-0.286
TokenNo
Token ID2949
Feature activation-3.69e-01

Pos logit contributions
orem+0.341
ril+0.336
 nerv+0.318
riors+0.314
igation+0.311
Neg logit contributions
hatt-0.253
Beer-0.240
coat-0.216
andr-0.215
ness-0.213
Token woman
Token ID2415
Feature activation-4.37e-01

Pos logit contributions
orem+0.604
ril+0.590
 nerv+0.565
riors+0.551
 wills+0.550
Neg logit contributions
hatt-0.534
Beer-0.513
andr-0.461
coat-0.461
ness-0.457
Token of
Token ID286
Feature activation-1.13e-01

Pos logit contributions
orem+0.643
ril+0.628
 nerv+0.600
riors+0.583
 wills+0.581
Neg logit contributions
hatt-0.703
Beer-0.678
andr-0.618
coat-0.616
ness-0.610
Token Ban
Token ID10274
Feature activation+3.53e-01

Pos logit contributions
orem+0.170
ril+0.166
 nerv+0.159
riors+0.154
 wills+0.154
Neg logit contributions
hatt-0.180
Beer-0.173
andr-0.158
coat-0.157
ness-0.156
Tokenu
Token ID84
Feature activation-1.04e+00

Pos logit contributions
hatt+0.475
Beer+0.447
andr+0.400
ness+0.399
coat+0.398
Neg logit contributions
orem-0.615
ril-0.601
 nerv-0.584
 wills-0.570
riors-0.570
Token Qur
Token ID17599
Feature activation-3.99e+00

Pos logit contributions
orem+1.310
ril+1.273
 nerv+1.209
riors+1.166
 wills+1.162
Neg logit contributions
hatt-1.879
Beer-1.822
coat-1.682
andr-1.678
ness-1.664
Tokenay
Token ID323
Feature activation-4.41e-01

Pos logit contributions
orem+5.443
ril+5.362
igation+4.773
 nerv+4.741
terior+4.694
Neg logit contributions
Beer-6.450
hatt-6.281
coat-5.711
Feel-5.684
andr-5.612
Tokenza
Token ID4496
Feature activation+1.18e+00

Pos logit contributions
orem+0.674
ril+0.662
 nerv+0.625
riors+0.613
igation+0.603
Neg logit contributions
hatt-0.682
Beer-0.659
coat-0.594
andr-0.590
ness-0.577
Token was
Token ID373
Feature activation+5.51e-01

Pos logit contributions
hatt+1.824
Beer+1.737
ness+1.600
coat+1.584
andr+1.574
Neg logit contributions
orem-1.823
ril-1.778
 nerv-1.690
riors-1.655
igation-1.634
Token killed
Token ID2923
Feature activation-6.54e-01

Pos logit contributions
hatt+0.812
Beer+0.777
coat+0.703
ness+0.701
andr+0.699
Neg logit contributions
orem-0.886
ril-0.867
 nerv-0.829
riors-0.810
 wills-0.804
Token except
Token ID2845
Feature activation+1.04e+00

Pos logit contributions
orem+1.006
ril+0.985
 nerv+0.949
 wills+0.918
riors+0.917
Neg logit contributions
hatt-1.006
Beer-0.972
andr-0.877
coat-0.875
ness-0.862
Token,
Token ID11
Feature activation+1.09e-01

Pos logit contributions
hatt+0.239
Beer+0.228
andr+0.203
coat+0.203
ness+0.201
Neg logit contributions
orem-0.310
ril-0.304
 nerv-0.293
riors-0.286
 wills-0.285
Token Survivor
Token ID23740
Feature activation-2.76e-01

Pos logit contributions
hatt+0.171
Beer+0.165
coat+0.150
andr+0.150
ness+0.149
Neg logit contributions
orem-0.164
ril-0.161
 nerv-0.154
riors-0.149
 wills-0.149
Token South
Token ID2520
Feature activation+2.85e-02

Pos logit contributions
orem+0.421
ril+0.413
 nerv+0.394
riors+0.384
 wills+0.382
Neg logit contributions
hatt-0.429
Beer-0.413
andr-0.374
coat-0.373
ness-0.371
Token Pacific
Token ID8211
Feature activation-4.75e-01

Pos logit contributions
hatt+0.041
Beer+0.040
andr+0.036
coat+0.035
ness+0.035
Neg logit contributions
orem-0.047
ril-0.046
 nerv-0.044
riors-0.043
 wills-0.043
Token),
Token ID828
Feature activation-4.97e-01

Pos logit contributions
orem+0.818
ril+0.802
 nerv+0.772
riors+0.756
 wills+0.750
Neg logit contributions
hatt-0.646
Beer-0.618
andr-0.551
coat-0.549
ness-0.543
Token voic
Token ID40268
Feature activation-3.94e+00

Pos logit contributions
orem+0.822
ril+0.805
 nerv+0.774
riors+0.754
 wills+0.752
Neg logit contributions
hatt-0.711
Beer-0.681
coat-0.612
andr-0.611
ness-0.607
Tokenem
Token ID368
Feature activation-3.55e-01

Pos logit contributions
orem+4.349
ril+4.244
 nerv+3.768
riors+3.757
igation+3.740
Neg logit contributions
hatt-7.645
Beer-7.438
coat-6.884
andr-6.843
ness-6.690
Tokenails
Token ID1768
Feature activation-1.44e+00

Pos logit contributions
orem+0.208
ril+0.197
 nerv+0.172
riors+0.160
 wills+0.158
Neg logit contributions
hatt-0.884
Beer-0.866
coat-0.815
andr-0.815
ness-0.811
Token with
Token ID351
Feature activation+3.69e-01

Pos logit contributions
orem+2.339
ril+2.291
 nerv+2.211
riors+2.154
 wills+2.153
Neg logit contributions
hatt-2.074
Beer-1.995
coat-1.790
andr-1.780
ness-1.749
Token Mike
Token ID4995
Feature activation+1.17e-01

Pos logit contributions
hatt+0.541
Beer+0.519
coat+0.468
andr+0.467
ness+0.465
Neg logit contributions
orem-0.598
ril-0.585
 nerv-0.561
riors-0.547
 wills-0.544
Token Bloom
Token ID11891
Feature activation+1.82e+00

Pos logit contributions
hatt+0.172
Beer+0.165
coat+0.149
andr+0.149
ness+0.148
Neg logit contributions
orem-0.188
ril-0.184
 nerv-0.176
riors-0.172
 wills-0.171
Token for
Token ID329
Feature activation-1.57e-01

Pos logit contributions
hatt+0.592
Beer+0.570
andr+0.517
coat+0.516
ness+0.512
Neg logit contributions
orem-0.580
ril-0.568
 nerv-0.545
riors-0.528
 wills-0.527
Token the
Token ID262
Feature activation-3.06e-02

Pos logit contributions
orem+0.220
ril+0.215
 nerv+0.205
riors+0.199
 wills+0.198
Neg logit contributions
hatt-0.264
Beer-0.255
coat-0.233
andr-0.233
ness-0.232
Token Black
Token ID2619
Feature activation+1.01e+00

Pos logit contributions
orem+0.043
ril+0.042
 nerv+0.040
riors+0.039
 wills+0.039
Neg logit contributions
hatt-0.051
Beer-0.049
andr-0.045
coat-0.045
ness-0.045
Tokenberry
Token ID8396
Feature activation-1.58e+00

Pos logit contributions
hatt+1.129
Beer+1.069
ness+0.934
coat+0.931
andr+0.926
Neg logit contributions
orem-2.013
ril-1.957
 nerv-1.898
riors-1.860
 wills-1.857
Token or
Token ID393
Feature activation-5.39e-02

Pos logit contributions
orem+2.405
ril+2.372
 nerv+2.283
riors+2.207
 wills+2.196
Neg logit contributions
hatt-2.427
Beer-2.353
coat-2.127
andr-2.117
ness-2.088
Token Palm
Token ID18358
Feature activation-3.91e+00

Pos logit contributions
orem+0.077
ril+0.075
 nerv+0.071
riors+0.069
 wills+0.069
Neg logit contributions
hatt-0.089
Beer-0.086
andr-0.079
coat-0.079
ness-0.079
Token Pre
Token ID3771
Feature activation+1.13e+00

Pos logit contributions
orem+5.913
ril+5.831
 nerv+5.614
riors+5.432
igation+5.405
Neg logit contributions
hatt-5.860
Beer-5.703
coat-5.105
andr-5.095
ness-4.964
Token?
Token ID30
Feature activation-2.25e-01

Pos logit contributions
hatt+1.631
Beer+1.563
coat+1.410
ness+1.408
andr+1.406
Neg logit contributions
orem-1.874
ril-1.818
 nerv-1.753
riors-1.708
 wills-1.702
Token We
Token ID775
Feature activation-4.04e-02

Pos logit contributions
orem+0.359
ril+0.352
 nerv+0.337
riors+0.328
 wills+0.327
Neg logit contributions
hatt-0.335
Beer-0.322
coat-0.291
andr-0.290
ness-0.288
Token
Token ID447
Feature activation+1.08e-01

Pos logit contributions
orem+0.067
ril+0.065
 nerv+0.063
riors+0.061
 wills+0.061
Neg logit contributions
hatt-0.058
Beer-0.056
andr-0.050
coat-0.050
ness-0.049
Token
Token ID247
Feature activation+3.20e-01

Pos logit contributions
hatt+0.138
Beer+0.131
coat+0.116
andr+0.116
ness+0.115
Neg logit contributions
orem-0.194
ril-0.190
 nerv-0.183
riors-0.179
 wills-0.178
Token felt
Token ID2936
Feature activation+5.79e-01

Pos logit contributions
hatt+1.448
Beer+1.388
coat+1.249
ness+1.247
andr+1.243
Neg logit contributions
orem-1.697
ril-1.661
 nerv-1.588
riors-1.556
 wills-1.544
Token in
Token ID287
Feature activation+3.67e-01

Pos logit contributions
hatt+0.866
Beer+0.832
coat+0.751
andr+0.750
ness+0.746
Neg logit contributions
orem-0.920
ril-0.900
 nerv-0.862
riors-0.840
 wills-0.836
Token Syria
Token ID4392
Feature activation-1.19e+00

Pos logit contributions
hatt+0.576
Beer+0.554
coat+0.502
andr+0.502
ness+0.500
Neg logit contributions
orem-0.558
ril-0.545
 nerv-0.520
riors-0.507
 wills-0.503
Token and
Token ID290
Feature activation+7.98e-02

Pos logit contributions
orem+1.937
ril+1.914
 nerv+1.871
riors+1.803
 wills+1.786
Neg logit contributions
hatt-1.676
Beer-1.617
coat-1.446
andr-1.444
ness-1.422
Token Mes
Token ID14937
Feature activation-9.70e-01

Pos logit contributions
hatt+0.129
Beer+0.124
coat+0.113
andr+0.113
ness+0.113
Neg logit contributions
orem-0.117
ril-0.114
 nerv-0.109
riors-0.106
 wills-0.106
Tokenopot
Token ID43372
Feature activation-3.89e+00

Pos logit contributions
orem+0.863
ril+0.838
 nerv+0.763
 wills+0.719
riors+0.716
Neg logit contributions
hatt-2.115
Beer-2.063
coat-1.928
andr-1.927
ness-1.915
Tokenamia
Token ID49442
Feature activation-3.55e-01

Pos logit contributions
orem+2.739
ril+2.535
 nerv+2.219
riors+2.189
igation+2.173
Neg logit contributions
Beer-8.874
hatt-8.830
coat-8.338
Feel-8.181
andr-8.156
Token.
Token ID13
Feature activation+3.12e-01

Pos logit contributions
orem+0.572
ril+0.562
 nerv+0.546
riors+0.527
 wills+0.524
Neg logit contributions
hatt-0.520
Beer-0.501
coat-0.449
andr-0.449
ness-0.443
Token As
Token ID1081
Feature activation-6.79e-02

Pos logit contributions
hatt+0.471
Beer+0.454
andr+0.410
coat+0.409
ness+0.408
Neg logit contributions
orem-0.492
ril-0.481
 nerv-0.460
riors-0.448
 wills-0.448
Token with
Token ID351
Feature activation+3.43e-01

Pos logit contributions
orem+0.104
ril+0.102
 nerv+0.097
riors+0.095
 wills+0.094
Neg logit contributions
hatt-0.105
Beer-0.101
coat-0.092
andr-0.092
ness-0.091
Token so
Token ID523
Feature activation-7.18e-02

Pos logit contributions
hatt+0.551
Beer+0.530
coat+0.483
andr+0.483
ness+0.481
Neg logit contributions
orem-0.507
ril-0.495
 nerv-0.472
riors-0.459
 wills-0.456
TokenThe
Token ID464
Feature activation-4.10e-01

Pos logit contributions
orem+0.498
ril+0.490
 nerv+0.464
riors+0.458
igation+0.453
Neg logit contributions
hatt-0.374
Beer-0.352
andr-0.317
coat-0.317
ness-0.314
Token imminent
Token ID21161
Feature activation-2.47e-01

Pos logit contributions
orem+0.638
ril+0.622
 nerv+0.596
riors+0.579
 wills+0.577
Neg logit contributions
hatt-0.629
Beer-0.605
coat-0.548
andr-0.547
ness-0.543
Token merger
Token ID24589
Feature activation-9.32e-01

Pos logit contributions
orem+0.391
ril+0.383
 nerv+0.367
riors+0.356
 wills+0.356
Neg logit contributions
hatt-0.370
Beer-0.355
coat-0.321
andr-0.321
ness-0.317
Token between
Token ID1022
Feature activation-3.52e-01

Pos logit contributions
orem+1.278
ril+1.251
 nerv+1.205
 wills+1.166
igation+1.156
Neg logit contributions
hatt-1.580
Beer-1.523
andr-1.398
coat-1.393
ness-1.366
Token Time
Token ID3862
Feature activation+3.09e-01

Pos logit contributions
orem+0.528
ril+0.514
 nerv+0.493
 wills+0.478
riors+0.477
Neg logit contributions
hatt-0.559
Beer-0.537
andr-0.489
coat-0.488
ness-0.485
Token Warner
Token ID14469
Feature activation-3.89e+00

Pos logit contributions
hatt+0.465
Beer+0.447
coat+0.403
andr+0.403
ness+0.401
Neg logit contributions
orem-0.490
ril-0.479
 nerv-0.459
riors-0.447
 wills-0.445
Token Cable
Token ID20249
Feature activation-4.56e-01

Pos logit contributions
orem+5.459
ril+5.421
 nerv+5.223
 wills+5.171
riors+5.087
Neg logit contributions
hatt-6.154
Beer-5.863
andr-5.412
coat-5.246
ness-5.228
Token and
Token ID290
Feature activation+7.50e-03

Pos logit contributions
orem+0.770
ril+0.755
 nerv+0.727
riors+0.709
 wills+0.708
Neg logit contributions
hatt-0.635
Beer-0.609
coat-0.544
andr-0.543
ness-0.538
Token Comcast
Token ID21830
Feature activation-1.87e+00

Pos logit contributions
hatt+0.012
Beer+0.011
andr+0.010
coat+0.010
ness+0.010
Neg logit contributions
orem-0.011
ril-0.011
 nerv-0.011
 wills-0.010
riors-0.010
Token herald
Token ID28783
Feature activation-8.48e-02

Pos logit contributions
orem+2.795
ril+2.706
 nerv+2.639
 wills+2.579
riors+2.530
Neg logit contributions
hatt-2.949
Beer-2.828
coat-2.562
andr-2.562
ness-2.485
Tokens
Token ID82
Feature activation-6.22e-01

Pos logit contributions
orem+0.195
ril+0.193
 nerv+0.186
 wills+0.183
riors+0.183
Neg logit contributions
hatt-0.067
Beer-0.061
andr-0.049
coat-0.049
ness-0.048
Token living
Token ID2877
Feature activation-1.01e+00

Pos logit contributions
hatt+0.030
Beer+0.029
coat+0.026
andr+0.026
ness+0.026
Neg logit contributions
orem-0.035
ril-0.034
 nerv-0.032
riors-0.032
 wills-0.032
Token on
Token ID319
Feature activation+1.39e-01

Pos logit contributions
orem+1.568
ril+1.540
 nerv+1.476
 wills+1.438
riors+1.430
Neg logit contributions
hatt-1.544
Beer-1.491
andr-1.342
coat-1.335
ness-1.322
Token the
Token ID262
Feature activation-1.31e-01

Pos logit contributions
hatt+0.215
Beer+0.207
andr+0.188
coat+0.188
ness+0.186
Neg logit contributions
orem-0.214
ril-0.209
 nerv-0.200
riors-0.195
 wills-0.194
Token streets
Token ID6483
Feature activation+2.06e-01

Pos logit contributions
orem+0.205
ril+0.200
 nerv+0.192
riors+0.187
 wills+0.186
Neg logit contributions
hatt-0.199
Beer-0.191
andr-0.173
coat-0.173
ness-0.171
Token of
Token ID286
Feature activation-2.52e-01

Pos logit contributions
hatt+0.310
Beer+0.297
coat+0.269
andr+0.268
ness+0.267
Neg logit contributions
orem-0.327
ril-0.320
 nerv-0.306
riors-0.298
 wills-0.297
Token Gotham
Token ID30129
Feature activation-3.84e+00

Pos logit contributions
orem+0.312
ril+0.304
 nerv+0.288
riors+0.277
 wills+0.277
Neg logit contributions
hatt-0.464
Beer-0.450
andr-0.414
coat-0.413
ness-0.412
Token.
Token ID13
Feature activation+1.08e-01

Pos logit contributions
orem+5.247
ril+5.139
 nerv+5.022
riors+4.805
 wills+4.753
Neg logit contributions
hatt-6.090
Beer-6.042
andr-5.512
coat-5.323
ness-5.263
Token You
Token ID921
Feature activation+7.29e-01

Pos logit contributions
hatt+0.147
Beer+0.141
coat+0.126
andr+0.126
ness+0.125
Neg logit contributions
orem-0.185
ril-0.181
 nerv-0.174
riors-0.170
 wills-0.169
Token know
Token ID760
Feature activation+9.46e-01

Pos logit contributions
hatt+1.003
Beer+0.960
coat+0.858
andr+0.857
ness+0.851
Neg logit contributions
orem-1.246
ril-1.221
 nerv-1.174
riors-1.146
 wills-1.141
Token how
Token ID703
Feature activation+8.80e-01

Pos logit contributions
hatt+1.346
Beer+1.287
coat+1.158
andr+1.155
ness+1.154
Neg logit contributions
orem-1.574
ril-1.541
 nerv-1.476
riors-1.442
 wills-1.435
Token Alfred
Token ID22044
Feature activation-5.51e-01

Pos logit contributions
hatt+1.388
Beer+1.333
coat+1.215
andr+1.211
ness+1.209
Neg logit contributions
orem-1.333
ril-1.295
 nerv-1.231
riors-1.204
 wills-1.196
Token the
Token ID262
Feature activation+8.03e-02

Pos logit contributions
hatt+0.102
Beer+0.098
coat+0.089
andr+0.089
ness+0.088
Neg logit contributions
orem-0.097
ril-0.095
 nerv-0.090
riors-0.088
 wills-0.087
Token venue
Token ID14359
Feature activation-3.81e-02

Pos logit contributions
hatt+0.131
Beer+0.126
coat+0.115
andr+0.115
ness+0.115
Neg logit contributions
orem-0.116
ril-0.114
 nerv-0.108
riors-0.105
 wills-0.105
Token
Token ID447
Feature activation+5.27e-02

Pos logit contributions
orem+0.063
ril+0.062
 nerv+0.059
riors+0.058
 wills+0.057
Neg logit contributions
hatt-0.055
Beer-0.052
coat-0.047
andr-0.047
ness-0.047
Token
Token ID247
Feature activation+1.65e-01

Pos logit contributions
hatt+0.072
Beer+0.068
coat+0.061
andr+0.061
ness+0.060
Neg logit contributions
orem-0.091
ril-0.089
 nerv-0.085
riors-0.084
rior-0.083
Tokens
Token ID82
Feature activation-4.88e-01

Pos logit contributions
hatt+0.120
Beer+0.110
coat+0.087
andr+0.087
ness+0.085
Neg logit contributions
orem-0.390
ril-0.384
 nerv-0.374
riors-0.367
 wills-0.366
Token voic
Token ID40268
Feature activation-3.82e+00

Pos logit contributions
orem+0.719
ril+0.699
 nerv+0.670
 wills+0.651
riors+0.648
Neg logit contributions
hatt-0.787
Beer-0.756
coat-0.690
andr-0.688
ness-0.682
Tokenemail
Token ID12888
Feature activation-2.10e+00

Pos logit contributions
orem+3.794
ril+3.753
igation+3.266
 nerv+3.249
 wills+3.205
Neg logit contributions
hatt-7.807
Beer-7.639
coat-7.119
andr-7.010
ness-6.896
Token at
Token ID379
Feature activation+2.03e-02

Pos logit contributions
orem+3.234
ril+3.153
 nerv+3.026
 wills+2.956
riors+2.921
Neg logit contributions
hatt-3.211
Beer-3.082
coat-2.816
andr-2.774
ness-2.735
Token the
Token ID262
Feature activation-1.24e-01

Pos logit contributions
hatt+0.033
Beer+0.031
coat+0.029
andr+0.029
ness+0.028
Neg logit contributions
orem-0.030
ril-0.029
 nerv-0.028
riors-0.027
 wills-0.027
Token time
Token ID640
Feature activation-5.21e-01

Pos logit contributions
orem+0.215
ril+0.210
 nerv+0.203
 wills+0.197
riors+0.197
Neg logit contributions
hatt-0.167
Beer-0.159
coat-0.143
andr-0.143
ness-0.141
Token.
Token ID13
Feature activation-4.09e-02

Pos logit contributions
orem+0.848
ril+0.832
 nerv+0.798
riors+0.778
 wills+0.774
Neg logit contributions
hatt-0.756
Beer-0.725
andr-0.653
coat-0.653
ness-0.645
Token Vu
Token ID35816
Feature activation-1.27e+00

Pos logit contributions
orem+0.671
ril+0.657
 nerv+0.630
riors+0.613
 wills+0.612
Neg logit contributions
hatt-0.607
Beer-0.582
coat-0.523
andr-0.523
ness-0.520
Tokenitton
Token ID47304
Feature activation-4.63e-01

Pos logit contributions
orem+1.121
ril+1.072
 nerv+0.980
 wills+0.934
riors+0.915
Neg logit contributions
hatt-2.794
Beer-2.715
coat-2.531
andr-2.529
ness-2.518
Token,
Token ID11
Feature activation+1.29e-01

Pos logit contributions
orem+0.800
ril+0.785
 nerv+0.755
riors+0.735
 wills+0.735
Neg logit contributions
hatt-0.627
Beer-0.600
andr-0.535
coat-0.533
ness-0.528
Token
Token ID564
Feature activation-3.02e-01

Pos logit contributions
hatt+0.192
Beer+0.184
coat+0.166
andr+0.166
ness+0.165
Neg logit contributions
orem-0.206
ril-0.201
 nerv-0.193
riors-0.188
 wills-0.187
Token
Token ID250
Feature activation+1.83e-01

Pos logit contributions
orem+0.675
ril+0.665
 nerv+0.645
riors+0.633
 wills+0.631
Neg logit contributions
hatt-0.257
Beer-0.238
andr-0.197
coat-0.197
ness-0.194
TokenGil
Token ID40747
Feature activation-3.77e+00

Pos logit contributions
hatt+0.238
Beer+0.225
andr+0.201
coat+0.201
ness+0.199
Neg logit contributions
orem-0.326
ril-0.321
 nerv-0.307
riors-0.301
 wills-0.299
Tokenmore
Token ID3549
Feature activation-3.62e-01

Pos logit contributions
orem+5.390
ril+5.374
 nerv+5.016
riors+4.892
igation+4.877
Neg logit contributions
hatt-6.037
Beer-5.816
coat-5.312
andr-5.255
ness-5.173
Token Girls
Token ID12002
Feature activation+7.39e-02

Pos logit contributions
orem+0.536
ril+0.523
 nerv+0.500
riors+0.486
 wills+0.482
Neg logit contributions
hatt-0.583
Beer-0.562
coat-0.511
andr-0.510
ness-0.509
Token,
Token ID11
Feature activation-1.77e-02

Pos logit contributions
hatt+0.113
Beer+0.109
coat+0.099
andr+0.099
ness+0.098
Neg logit contributions
orem-0.115
ril-0.112
 nerv-0.107
riors-0.104
 wills-0.104
Token
Token ID447
Feature activation+7.88e-02

Pos logit contributions
orem+0.027
ril+0.027
 nerv+0.025
riors+0.025
 wills+0.025
Neg logit contributions
hatt-0.027
Beer-0.026
coat-0.024
andr-0.024
ness-0.024
Token
Token ID251
Feature activation+1.04e-01

Pos logit contributions
hatt+0.061
Beer+0.056
coat+0.046
andr+0.046
ness+0.045
Neg logit contributions
orem-0.182
ril-0.179
 nerv-0.174
riors-0.171
 wills-0.170
Token San
Token ID2986
Feature activation-6.80e-01

Pos logit contributions
hatt+0.112
Beer+0.108
andr+0.098
coat+0.098
ness+0.097
Neg logit contributions
orem-0.100
ril-0.098
 nerv-0.093
riors-0.091
 wills-0.090
Token Diego
Token ID9500
Feature activation-9.55e-01

Pos logit contributions
orem+0.837
ril+0.816
 nerv+0.769
riors+0.746
 wills+0.738
Neg logit contributions
hatt-1.258
Beer-1.221
coat-1.123
andr-1.122
ness-1.114
Token,
Token ID11
Feature activation+1.48e-01

Pos logit contributions
orem+1.723
ril+1.690
 nerv+1.627
riors+1.591
 wills+1.585
Neg logit contributions
hatt-1.223
Beer-1.166
coat-1.033
andr-1.033
ness-1.027
Token Dallas
Token ID8533
Feature activation+2.09e-01

Pos logit contributions
hatt+0.237
Beer+0.228
andr+0.208
coat+0.208
ness+0.207
Neg logit contributions
orem-0.218
ril-0.213
 nerv-0.204
riors-0.198
 wills-0.197
Token,
Token ID11
Feature activation+1.55e-01

Pos logit contributions
hatt+0.257
Beer+0.245
ness+0.217
andr+0.215
coat+0.214
Neg logit contributions
orem-0.389
ril-0.382
 nerv-0.368
riors-0.360
 wills-0.358
Token Palm
Token ID18358
Feature activation-3.75e+00

Pos logit contributions
hatt+0.256
Beer+0.246
andr+0.225
coat+0.224
ness+0.224
Neg logit contributions
orem-0.224
ril-0.218
 nerv-0.208
riors-0.202
 wills-0.201
Token Beach
Token ID8511
Feature activation-1.23e+00

Pos logit contributions
orem+3.857
ril+3.698
 nerv+3.387
riors+3.298
igation+3.286
Neg logit contributions
hatt-7.606
Beer-7.468
andr-6.922
coat-6.858
ness-6.782
Token,
Token ID11
Feature activation+4.03e-02

Pos logit contributions
orem+2.141
ril+2.097
 nerv+2.020
riors+1.971
 wills+1.963
Neg logit contributions
hatt-1.654
Beer-1.585
andr-1.411
coat-1.409
ness-1.394
Token Florida
Token ID4744
Feature activation-2.38e-01

Pos logit contributions
hatt+0.067
Beer+0.064
andr+0.059
coat+0.059
ness+0.058
Neg logit contributions
orem-0.058
ril-0.056
 nerv-0.054
riors-0.052
 wills-0.052
Token,
Token ID11
Feature activation+9.37e-02

Pos logit contributions
orem+0.434
ril+0.426
 nerv+0.409
riors+0.401
 wills+0.398
Neg logit contributions
hatt-0.301
Beer-0.287
ness-0.254
coat-0.254
andr-0.253
Token Moreno
Token ID43269
Feature activation-1.02e+00

Pos logit contributions
hatt+0.154
Beer+0.148
andr+0.135
coat+0.135
ness+0.135
Neg logit contributions
orem-0.135
ril-0.132
 nerv-0.126
riors-0.122
 wills-0.122
Token,
Token ID11
Feature activation-5.96e-01

Pos logit contributions
orem+0.698
ril+0.684
 nerv+0.657
riors+0.641
 wills+0.639
Neg logit contributions
hatt-0.567
Beer-0.543
coat-0.486
andr-0.484
ness-0.483
Token Mass
Token ID5674
Feature activation+1.25e-01

Pos logit contributions
orem+0.845
ril+0.822
 nerv+0.789
 wills+0.770
riors+0.764
Neg logit contributions
hatt-0.982
Beer-0.953
andr-0.874
coat-0.865
ness-0.860
Token.
Token ID13
Feature activation-8.73e-01

Pos logit contributions
hatt+0.178
Beer+0.170
coat+0.153
ness+0.153
andr+0.152
Neg logit contributions
orem-0.208
ril-0.203
 nerv-0.196
riors-0.190
 wills-0.190
Token --
Token ID1377
Feature activation-4.99e-01

Pos logit contributions
orem+1.244
ril+1.215
 nerv+1.157
riors+1.124
 wills+1.118
Neg logit contributions
hatt-1.445
Beer-1.393
andr-1.272
coat-1.272
ness-1.264
Token Boston
Token ID6182
Feature activation-2.86e+00

Pos logit contributions
orem+0.760
ril+0.743
 nerv+0.711
riors+0.692
 wills+0.689
Neg logit contributions
hatt-0.777
Beer-0.747
andr-0.678
coat-0.678
ness-0.672
Token Celtics
Token ID24116
Feature activation-3.73e+00

Pos logit contributions
orem+3.011
ril+2.948
 nerv+2.756
 wills+2.665
riors+2.644
Neg logit contributions
hatt-5.700
Beer-5.512
andr-5.166
coat-5.089
ness-5.031
Token swing
Token ID9628
Feature activation-1.72e+00

Pos logit contributions
orem+5.315
ril+5.147
 nerv+4.922
 wills+4.874
riors+4.847
Neg logit contributions
hatt-5.856
Beer-5.762
andr-5.187
coat-5.063
Feel-4.890
Tokenman
Token ID805
Feature activation-3.99e-01

Pos logit contributions
orem+2.416
ril+2.369
 nerv+2.236
riors+2.176
 wills+2.170
Neg logit contributions
hatt-2.888
Beer-2.802
coat-2.518
andr-2.514
ness-2.491
Token Jae
Token ID34521
Feature activation+5.49e-01

Pos logit contributions
orem+0.630
ril+0.619
 nerv+0.593
 wills+0.580
riors+0.578
Neg logit contributions
hatt-0.596
Beer-0.574
coat-0.516
andr-0.515
ness-0.504
Token Crow
Token ID15502
Feature activation+5.12e-01

Pos logit contributions
hatt+1.023
Beer+0.991
coat+0.915
andr+0.914
ness+0.910
Neg logit contributions
orem-0.669
ril-0.650
 nerv-0.616
riors-0.594
 wills-0.591
Tokender
Token ID1082
Feature activation-2.31e-02

Pos logit contributions
hatt+0.666
Beer+0.634
coat+0.563
andr+0.561
ness+0.560
Neg logit contributions
orem-0.912
ril-0.893
 nerv-0.863
 wills-0.839
riors-0.839
Token "
Token ID366
Feature activation+7.98e-01

Pos logit contributions
orem+0.884
ril+0.861
 nerv+0.823
 wills+0.804
riors+0.799
Neg logit contributions
hatt-0.885
Beer-0.851
coat-0.768
andr-0.768
ness-0.759
TokenShow
Token ID15307
Feature activation+3.31e-01

Pos logit contributions
hatt+1.084
Beer+1.037
coat+0.925
andr+0.925
ness+0.919
Neg logit contributions
orem-1.376
ril-1.349
 nerv-1.297
riors-1.266
 wills-1.261
Token Spe
Token ID2531
Feature activation+1.54e-01

Pos logit contributions
hatt+0.527
Beer+0.508
ness+0.461
coat+0.461
andr+0.460
Neg logit contributions
orem-0.493
ril-0.483
 nerv-0.461
riors-0.449
 wills-0.445
Tokenlling
Token ID2680
Feature activation-2.04e-01

Pos logit contributions
hatt+0.237
Beer+0.228
coat+0.206
andr+0.206
ness+0.206
Neg logit contributions
orem-0.237
ril-0.231
 nerv-0.222
riors-0.216
 wills-0.215
Token and
Token ID290
Feature activation-9.88e-02

Pos logit contributions
orem+0.303
ril+0.295
 nerv+0.282
riors+0.274
 wills+0.273
Neg logit contributions
hatt-0.326
Beer-0.314
andr-0.286
coat-0.286
ness-0.283
Token Gram
Token ID20159
Feature activation-3.71e+00

Pos logit contributions
orem+0.147
ril+0.143
 nerv+0.137
riors+0.133
 wills+0.132
Neg logit contributions
hatt-0.158
Beer-0.152
coat-0.139
andr-0.139
ness-0.138
Tokenmar
Token ID3876
Feature activation-5.23e-01

Pos logit contributions
orem+3.980
ril+3.910
 nerv+3.548
 wills+3.425
igation+3.421
Neg logit contributions
hatt-7.366
Beer-7.127
andr-6.586
coat-6.475
Feel-6.408
Token"
Token ID1
Feature activation-6.31e-02

Pos logit contributions
orem+0.777
ril+0.757
 nerv+0.724
riors+0.703
 wills+0.701
Neg logit contributions
hatt-0.835
Beer-0.805
andr-0.732
coat-0.730
ness-0.723
Token from
Token ID422
Feature activation-5.80e-02

Pos logit contributions
orem+0.100
ril+0.098
 nerv+0.093
riors+0.091
 wills+0.091
Neg logit contributions
hatt-0.095
Beer-0.091
coat-0.082
andr-0.082
ness-0.082
Token the
Token ID262
Feature activation-5.79e-02

Pos logit contributions
orem+0.089
ril+0.087
 nerv+0.083
riors+0.081
 wills+0.080
Neg logit contributions
hatt-0.090
Beer-0.087
coat-0.079
andr-0.079
ness-0.078
Token Spe
Token ID2531
Feature activation+2.19e-01

Pos logit contributions
orem+0.085
ril+0.083
 nerv+0.079
riors+0.077
 wills+0.077
Neg logit contributions
hatt-0.094
Beer-0.090
coat-0.082
andr-0.082
ness-0.082
Token,
Token ID11
Feature activation-1.43e-01

Pos logit contributions
orem+1.685
ril+1.649
 nerv+1.597
riors+1.558
 wills+1.553
Neg logit contributions
hatt-1.263
Beer-1.203
andr-1.073
coat-1.068
ness-1.051
Token P
Token ID350
Feature activation-1.14e-01

Pos logit contributions
orem+0.226
ril+0.220
 nerv+0.212
riors+0.206
 wills+0.205
Neg logit contributions
hatt-0.215
Beer-0.206
andr-0.186
coat-0.186
ness-0.185
Tokenious
Token ID699
Feature activation-3.65e-01

Pos logit contributions
orem+0.170
ril+0.167
 nerv+0.160
 wills+0.155
riors+0.154
Neg logit contributions
hatt-0.182
Beer-0.174
coat-0.159
andr-0.159
ness-0.158
Token,
Token ID11
Feature activation-1.05e-01

Pos logit contributions
orem+0.640
ril+0.627
 nerv+0.604
riors+0.590
 wills+0.588
Neg logit contributions
hatt-0.485
Beer-0.463
andr-0.412
coat-0.411
ness-0.407
Token Sanct
Token ID43990
Feature activation-1.09e+00

Pos logit contributions
orem+0.167
ril+0.163
 nerv+0.156
riors+0.152
 wills+0.152
Neg logit contributions
hatt-0.158
Beer-0.152
andr-0.137
coat-0.137
ness-0.136
Tokenimon
Token ID20473
Feature activation-3.70e+00

Pos logit contributions
orem+1.199
ril+1.166
 nerv+1.077
riors+1.035
 wills+1.027
Neg logit contributions
hatt-2.179
Beer-2.117
andr-1.951
coat-1.951
ness-1.937
Tokenious
Token ID699
Feature activation-3.72e-01

Pos logit contributions
orem+4.188
ril+4.013
 nerv+3.655
rior+3.604
igation+3.561
Neg logit contributions
hatt-7.045
Beer-6.933
andr-6.371
Feel-6.279
coat-6.241
Token
Token ID198
Feature activation+1.08e-01

Pos logit contributions
orem+0.608
ril+0.596
 nerv+0.571
riors+0.557
 wills+0.555
Neg logit contributions
hatt-0.539
Beer-0.517
coat-0.465
andr-0.465
ness-0.462
Token
Token ID198
Feature activation-7.20e-02

Pos logit contributions
hatt+0.177
Beer+0.170
andr+0.156
coat+0.154
ness+0.151
Neg logit contributions
orem-0.155
ril-0.152
 nerv-0.143
riors-0.141
rior-0.140
TokenWhy
Token ID5195
Feature activation-1.20e+00

Pos logit contributions
orem+0.144
ril+0.142
 nerv+0.137
riors+0.134
 wills+0.134
Neg logit contributions
hatt-0.078
Beer-0.074
coat-0.064
andr-0.064
ness-0.063
Token 1939
Token ID24414
Feature activation+9.70e-02

Pos logit contributions
orem+1.600
ril+1.568
 nerv+1.503
riors+1.451
 wills+1.449
Neg logit contributions
hatt-2.063
Beer-1.987
andr-1.830
coat-1.814
ness-1.790
Tokenists
Token ID1023
Feature activation+4.94e-01

Pos logit contributions
hatt+1.522
Beer+1.460
coat+1.346
andr+1.342
ness+1.340
Neg logit contributions
orem-1.236
ril-1.199
 nerv-1.141
 wills-1.104
riors-1.096
Token,
Token ID11
Feature activation+2.94e-01

Pos logit contributions
hatt+0.731
Beer+0.701
coat+0.632
andr+0.632
ness+0.628
Neg logit contributions
orem-0.792
ril-0.775
 nerv-0.742
riors-0.723
 wills-0.720
Token the
Token ID262
Feature activation+2.67e-01

Pos logit contributions
hatt+0.437
Beer+0.419
coat+0.379
andr+0.378
ness+0.376
Neg logit contributions
orem-0.470
ril-0.459
 nerv-0.440
riors-0.429
 wills-0.427
Token more
Token ID517
Feature activation+2.60e-01

Pos logit contributions
hatt+0.394
Beer+0.378
coat+0.341
andr+0.340
ness+0.338
Neg logit contributions
orem-0.431
ril-0.422
 nerv-0.405
riors-0.394
 wills-0.393
Token successful
Token ID4388
Feature activation-3.23e-01

Pos logit contributions
hatt+0.390
Beer+0.374
coat+0.338
andr+0.338
ness+0.336
Neg logit contributions
orem-0.413
ril-0.404
 nerv-0.387
riors-0.377
 wills-0.375
Token fellow
Token ID5891
Feature activation+1.97e+00

Pos logit contributions
orem+0.496
ril+0.486
 nerv+0.466
riors+0.454
 wills+0.452
Neg logit contributions
hatt-0.498
Beer-0.481
andr-0.434
coat-0.433
ness-0.428
Token worship
Token ID11892
Feature activation+1.80e+00

Pos logit contributions
hatt+2.878
Beer+2.714
ness+2.489
coat+2.478
andr+2.461
Neg logit contributions
orem-3.186
ril-3.122
 nerv-2.992
igation-2.892
 wills-2.889
Tokeners
Token ID364
Feature activation+1.57e-01

Pos logit contributions
hatt+1.976
Beer+1.855
ness+1.617
andr+1.616
coat+1.614
Neg logit contributions
orem-3.565
ril-3.487
 nerv-3.387
 wills-3.294
riors-3.261
Token of
Token ID286
Feature activation+4.25e-01

Pos logit contributions
hatt+0.260
Beer+0.251
coat+0.229
andr+0.229
ness+0.228
Neg logit contributions
orem-0.223
ril-0.218
 nerv-0.207
riors-0.201
 wills-0.201
Token the
Token ID262
Feature activation+4.27e-01

Pos logit contributions
hatt+0.625
Beer+0.600
coat+0.540
andr+0.540
ness+0.536
Neg logit contributions
orem-0.685
ril-0.670
 nerv-0.643
riors-0.626
 wills-0.624
Token Lenin
Token ID22899
Feature activation+1.16e+00

Pos logit contributions
hatt+0.627
Beer+0.602
coat+0.542
andr+0.541
ness+0.538
Neg logit contributions
orem-0.690
ril-0.675
 nerv-0.648
riors-0.631
 wills-0.629
Token with
Token ID351
Feature activation+4.26e-01

Pos logit contributions
hatt+0.283
Beer+0.273
coat+0.248
ness+0.248
andr+0.248
Neg logit contributions
orem-0.267
ril-0.260
 nerv-0.249
riors-0.243
 wills-0.241
Token a
Token ID257
Feature activation-1.16e-01

Pos logit contributions
hatt+0.657
Beer+0.632
coat+0.572
andr+0.571
ness+0.570
Neg logit contributions
orem-0.659
ril-0.643
 nerv-0.614
riors-0.599
 wills-0.596
Token football
Token ID4346
Feature activation-6.23e-01

Pos logit contributions
orem+0.185
ril+0.182
 nerv+0.175
riors+0.169
 wills+0.169
Neg logit contributions
hatt-0.171
Beer-0.165
andr-0.148
coat-0.148
ness-0.147
Token treatment
Token ID3513
Feature activation-6.98e-01

Pos logit contributions
orem+0.997
ril+0.976
 nerv+0.941
riors+0.919
rior+0.906
Neg logit contributions
hatt-0.919
Beer-0.887
andr-0.797
coat-0.789
ness-0.780
Token!)
Token ID8133
Feature activation-2.34e-01

Pos logit contributions
orem+1.159
ril+1.142
 nerv+1.100
riors+1.069
 wills+1.058
Neg logit contributions
hatt-0.987
Beer-0.949
andr-0.850
coat-0.843
ness-0.835
Token HA
Token ID14558
Feature activation+2.00e+00

Pos logit contributions
orem+0.363
ril+0.355
 nerv+0.341
riors+0.331
 wills+0.329
Neg logit contributions
hatt-0.359
Beer-0.345
coat-0.312
andr-0.312
ness-0.310
TokenIRD
Token ID46833
Feature activation+9.09e-01

Pos logit contributions
hatt+2.380
Beer+2.268
ness+1.989
coat+1.987
andr+1.960
Neg logit contributions
orem-3.738
ril-3.646
 nerv-3.528
riors-3.482
 wills-3.466
TokenRI
Token ID7112
Feature activation+1.24e-01

Pos logit contributions
hatt+1.322
Beer+1.270
ness+1.145
coat+1.141
andr+1.140
Neg logit contributions
orem-1.479
ril-1.439
 nerv-1.388
 wills-1.350
riors-1.349
TokenER
Token ID1137
Feature activation-2.77e-01

Pos logit contributions
hatt+0.165
Beer+0.158
coat+0.140
andr+0.140
ness+0.140
Neg logit contributions
orem-0.218
ril-0.214
 nerv-0.206
riors-0.201
 wills-0.201
Token
Token ID198
Feature activation-7.92e-02

Pos logit contributions
orem+0.428
ril+0.419
 nerv+0.401
riors+0.390
 wills+0.388
Neg logit contributions
hatt-0.427
Beer-0.411
andr-0.372
coat-0.372
ness-0.369
Token
Token ID198
Feature activation-2.71e-01

Pos logit contributions
orem+0.113
ril+0.111
 nerv+0.104
riors+0.103
rior+0.102
Neg logit contributions
hatt-0.131
Beer-0.125
andr-0.115
coat-0.113
ness-0.111
Token day
Token ID1110
Feature activation+1.34e-01

Pos logit contributions
orem+0.461
ril+0.451
 nerv+0.434
 wills+0.421
riors+0.420
Neg logit contributions
hatt-0.422
Beer-0.404
andr-0.366
coat-0.363
ness-0.358
Token,
Token ID11
Feature activation-2.35e-01

Pos logit contributions
hatt+0.194
Beer+0.187
coat+0.168
andr+0.168
ness+0.167
Neg logit contributions
orem-0.219
ril-0.214
 nerv-0.205
riors-0.200
 wills-0.199
Token
Token ID447
Feature activation-4.40e-01

Pos logit contributions
orem+0.377
ril+0.370
 nerv+0.356
riors+0.347
 wills+0.345
Neg logit contributions
hatt-0.345
Beer-0.332
coat-0.299
andr-0.299
ness-0.296
Token
Token ID251
Feature activation+2.21e-01

Pos logit contributions
orem+0.910
ril+0.897
 nerv+0.868
riors+0.851
 wills+0.847
Neg logit contributions
hatt-0.444
Beer-0.417
coat-0.357
andr-0.356
ness-0.351
Token said
Token ID531
Feature activation-3.32e-01

Pos logit contributions
hatt+0.362
Beer+0.349
andr+0.318
coat+0.318
ness+0.317
Neg logit contributions
orem-0.320
ril-0.311
 nerv-0.297
riors-0.288
 wills-0.287
Token Brenda
Token ID49495
Feature activation+1.99e+00

Pos logit contributions
orem+0.511
ril+0.501
 nerv+0.478
riors+0.466
 wills+0.464
Neg logit contributions
hatt-0.513
Beer-0.493
coat-0.447
andr-0.447
ness-0.443
Token
Token ID447
Feature activation-3.09e-01

Pos logit contributions
hatt+3.106
Beer+2.993
ness+2.731
coat+2.712
andr+2.690
Neg logit contributions
orem-2.992
ril-2.882
 nerv-2.786
 wills-2.702
riors-2.692
Token
Token ID247
Feature activation+2.12e-01

Pos logit contributions
orem+0.437
ril+0.428
 nerv+0.406
riors+0.396
rior+0.391
Neg logit contributions
hatt-0.515
Beer-0.495
coat-0.454
andr-0.453
ness-0.449
Tokens
Token ID82
Feature activation-5.66e-01

Pos logit contributions
hatt+0.218
Beer+0.205
coat+0.175
andr+0.175
ness+0.174
Neg logit contributions
orem-0.435
ril-0.428
 nerv-0.414
riors-0.406
 wills-0.405
Token oldest
Token ID13325
Feature activation-1.95e-01

Pos logit contributions
orem+0.847
ril+0.827
 nerv+0.793
riors+0.770
 wills+0.767
Neg logit contributions
hatt-0.899
Beer-0.866
andr-0.786
coat-0.785
ness-0.775
Token daughter
Token ID4957
Feature activation-4.18e-01

Pos logit contributions
orem+0.271
ril+0.264
 nerv+0.252
riors+0.243
 wills+0.243
Neg logit contributions
hatt-0.332
Beer-0.321
andr-0.293
coat-0.293
ness-0.289
Token2
Token ID17
Feature activation+6.15e-01

Pos logit contributions
hatt+0.487
Beer+0.466
coat+0.418
andr+0.418
ness+0.415
Neg logit contributions
orem-0.579
ril-0.567
 nerv-0.544
riors-0.531
 wills-0.528
Token-
Token ID12
Feature activation+5.22e-01

Pos logit contributions
hatt+0.829
Beer+0.790
coat+0.705
andr+0.704
ness+0.702
Neg logit contributions
orem-1.068
ril-1.043
 nerv-1.004
riors-0.986
 wills-0.978
Tokenethyl
Token ID21610
Feature activation+1.97e+00

Pos logit contributions
hatt+0.722
Beer+0.690
coat+0.619
andr+0.618
ness+0.615
Neg logit contributions
orem-0.887
ril-0.868
 nerv-0.835
riors-0.817
 wills-0.813
Token-
Token ID12
Feature activation+6.65e-01

Pos logit contributions
hatt+2.715
Beer+2.576
coat+2.341
ness+2.329
andr+2.322
Neg logit contributions
orem-3.304
ril-3.237
 nerv-3.135
riors-3.083
 wills-3.064
TokenN
Token ID45
Feature activation+5.33e-02

Pos logit contributions
hatt+0.929
Beer+0.887
coat+0.795
andr+0.795
ness+0.791
Neg logit contributions
orem-1.122
ril-1.098
 nerv-1.056
riors-1.032
 wills-1.029
Token-(
Token ID30420
Feature activation+2.17e+00

Pos logit contributions
hatt+0.076
Beer+0.072
coat+0.065
andr+0.065
ness+0.064
Neg logit contributions
orem-0.089
ril-0.087
 nerv-0.084
riors-0.082
 wills-0.082
Tokent
Token ID83
Feature activation+6.32e-01

Pos logit contributions
hatt+2.986
Beer+2.835
coat+2.557
ness+2.549
andr+2.546
Neg logit contributions
orem-3.694
ril-3.588
 nerv-3.464
riors-3.419
 wills-3.414
Tokenet
Token ID316
Feature activation+8.29e-02

Pos logit contributions
hatt+0.678
Beer+0.636
coat+0.555
andr+0.551
ness+0.550
Neg logit contributions
orem-1.264
ril-1.246
 nerv-1.209
riors-1.183
 wills-1.181
Tokenrah
Token ID11392
Feature activation+9.05e-01

Pos logit contributions
hatt+0.123
Beer+0.118
coat+0.107
andr+0.107
ness+0.106
Neg logit contributions
orem-0.132
ril-0.130
 nerv-0.124
riors-0.121
 wills-0.121
Tokenyd
Token ID5173
Feature activation+7.98e-01

Pos logit contributions
hatt+0.960
Beer+0.904
andr+0.779
coat+0.778
ness+0.772
Neg logit contributions
orem-1.832
ril-1.800
 nerv-1.744
riors-1.707
 wills-1.704
Tokenro
Token ID305
Feature activation+1.09e+00

Pos logit contributions
hatt+1.014
Beer+0.952
coat+0.851
andr+0.844
ness+0.844
Neg logit contributions
orem-1.449
ril-1.412
 nerv-1.383
 wills-1.354
riors-1.347
Tokenicycle
Token ID35298
Feature activation+7.87e-01

Pos logit contributions
hatt+1.777
Beer+1.698
coat+1.557
andr+1.555
ness+1.550
Neg logit contributions
orem-1.621
ril-1.586
 nerv-1.527
 wills-1.481
riors-1.477
Token keeps
Token ID7622
Feature activation+2.12e-01

Pos logit contributions
hatt+1.153
Beer+1.106
coat+0.999
ness+0.996
andr+0.995
Neg logit contributions
orem-1.273
ril-1.250
 nerv-1.189
riors-1.164
 wills-1.154
Token our
Token ID674
Feature activation+1.32e-01

Pos logit contributions
hatt+0.318
Beer+0.306
andr+0.277
coat+0.276
ness+0.274
Neg logit contributions
orem-0.335
ril-0.327
 nerv-0.315
riors-0.306
 wills-0.305
Token dreams
Token ID10625
Feature activation+1.59e-01

Pos logit contributions
hatt+0.198
Beer+0.190
coat+0.172
andr+0.171
ness+0.170
Neg logit contributions
orem-0.210
ril-0.205
 nerv-0.197
riors-0.191
 wills-0.191
Token of
Token ID286
Feature activation+1.96e-01

Pos logit contributions
hatt+0.246
Beer+0.237
andr+0.216
coat+0.214
ness+0.209
Neg logit contributions
orem-0.241
ril-0.238
 nerv-0.230
 wills-0.223
riors-0.222
Token speed
Token ID2866
Feature activation+2.03e+00

Pos logit contributions
hatt+0.286
Beer+0.274
coat+0.247
andr+0.246
ness+0.245
Neg logit contributions
orem-0.320
ril-0.313
 nerv-0.300
riors-0.293
 wills-0.291
Tokener
Token ID263
Feature activation-3.85e-01

Pos logit contributions
hatt+2.830
Beer+2.709
coat+2.425
andr+2.421
ness+2.417
Neg logit contributions
orem-3.435
ril-3.358
 nerv-3.219
riors-3.149
 wills-3.137
Token bikes
Token ID16715
Feature activation+9.63e-01

Pos logit contributions
orem+0.642
ril+0.631
 nerv+0.607
riors+0.595
 wills+0.592
Neg logit contributions
hatt-0.541
Beer-0.520
andr-0.467
coat-0.466
ness-0.454
Token alive
Token ID6776
Feature activation-1.99e-01

Pos logit contributions
hatt+1.388
Beer+1.335
andr+1.201
coat+1.198
ness+1.183
Neg logit contributions
orem-1.577
ril-1.551
 nerv-1.492
riors-1.449
 wills-1.448
Token --
Token ID1377
Feature activation-7.40e-02

Pos logit contributions
orem+0.323
ril+0.316
 nerv+0.304
riors+0.296
 wills+0.295
Neg logit contributions
hatt-0.291
Beer-0.280
andr-0.252
coat-0.251
ness-0.249
Token if
Token ID611
Feature activation-1.26e+00

Pos logit contributions
orem+0.123
ril+0.120
 nerv+0.116
riors+0.113
 wills+0.113
Neg logit contributions
hatt-0.105
Beer-0.101
coat-0.091
andr-0.090
ness-0.089
Token14
Token ID1415
Feature activation+4.26e-01

Pos logit contributions
hatt+0.113
Beer+0.108
andr+0.096
coat+0.096
ness+0.096
Neg logit contributions
orem-0.143
ril-0.140
 nerv-0.135
riors-0.131
 wills-0.131
Token dates
Token ID9667
Feature activation-1.28e-01

Pos logit contributions
hatt+0.650
Beer+0.625
andr+0.565
coat+0.565
ness+0.561
Neg logit contributions
orem-0.665
ril-0.650
 nerv-0.622
riors-0.605
 wills-0.603
Token in
Token ID287
Feature activation+3.70e-01

Pos logit contributions
orem+0.212
ril+0.207
 nerv+0.200
riors+0.194
 wills+0.194
Neg logit contributions
hatt-0.183
Beer-0.175
andr-0.157
coat-0.157
ness-0.155
Token the
Token ID262
Feature activation+1.24e-01

Pos logit contributions
hatt+0.569
Beer+0.548
andr+0.496
coat+0.495
ness+0.491
Neg logit contributions
orem-0.571
ril-0.558
 nerv-0.535
riors-0.520
 wills-0.518
Token range
Token ID2837
Feature activation-1.27e+00

Pos logit contributions
hatt+0.192
Beer+0.185
coat+0.167
andr+0.167
ness+0.166
Neg logit contributions
orem-0.189
ril-0.185
 nerv-0.177
riors-0.172
 wills-0.172
Token of
Token ID286
Feature activation-5.81e-02

Pos logit contributions
orem+1.752
ril+1.717
 nerv+1.644
riors+1.582
 wills+1.575
Neg logit contributions
hatt-2.152
Beer-2.079
andr-1.893
coat-1.893
ness-1.864
Token 22
Token ID2534
Feature activation-1.14e+00

Pos logit contributions
orem+0.087
ril+0.085
 nerv+0.081
riors+0.079
 wills+0.079
Neg logit contributions
hatt-0.092
Beer-0.089
coat-0.081
andr-0.081
ness-0.080
Token,
Token ID11
Feature activation+1.38e-01

Pos logit contributions
orem+1.884
ril+1.855
 nerv+1.778
riors+1.732
 wills+1.726
Neg logit contributions
hatt-1.614
Beer-1.548
andr-1.392
coat-1.390
ness-1.364
Token000
Token ID830
Feature activation+9.47e-01

Pos logit contributions
hatt+0.187
Beer+0.179
coat+0.159
andr+0.159
ness+0.159
Neg logit contributions
orem-0.240
ril-0.235
 nerv-0.226
riors-0.221
 wills-0.220
Token to
Token ID284
Feature activation+4.82e-02

Pos logit contributions
hatt+1.335
Beer+1.285
ness+1.154
andr+1.151
coat+1.148
Neg logit contributions
orem-1.581
ril-1.536
 nerv-1.480
riors-1.445
 wills-1.435
Token 39
Token ID5014
Feature activation+3.20e-01

Pos logit contributions
hatt+0.075
Beer+0.072
coat+0.065
andr+0.065
ness+0.064
Neg logit contributions
orem-0.074
ril-0.072
 nerv-0.069
riors-0.067
 wills-0.067
Token two
Token ID734
Feature activation-3.66e-01

Pos logit contributions
hatt+0.318
Beer+0.305
andr+0.274
coat+0.274
ness+0.271
Neg logit contributions
orem-0.368
ril-0.361
 nerv-0.348
 wills-0.337
riors-0.337
Token leads
Token ID5983
Feature activation+2.46e-01

Pos logit contributions
orem+0.581
ril+0.571
 nerv+0.550
 wills+0.534
riors+0.531
Neg logit contributions
hatt-0.545
Beer-0.526
andr-0.475
coat-0.471
ness-0.466
Token.
Token ID13
Feature activation+1.09e-01

Pos logit contributions
hatt+0.361
Beer+0.348
andr+0.313
coat+0.311
ness+0.307
Neg logit contributions
orem-0.396
ril-0.389
 nerv-0.373
 wills-0.363
riors-0.362
Token Hun
Token ID5900
Feature activation+1.13e+00

Pos logit contributions
hatt+0.163
Beer+0.157
andr+0.142
coat+0.141
ness+0.140
Neg logit contributions
orem-0.172
ril-0.168
 nerv-0.161
riors-0.157
 wills-0.156
Tokennam
Token ID7402
Feature activation-7.12e-01

Pos logit contributions
hatt+1.834
Beer+1.773
coat+1.614
andr+1.610
ness+1.592
Neg logit contributions
orem-1.636
ril-1.603
 nerv-1.522
riors-1.484
 wills-1.469
Token joins
Token ID15449
Feature activation+1.52e+00

Pos logit contributions
orem+1.054
ril+1.041
 nerv+0.997
 wills+0.967
riors+0.965
Neg logit contributions
hatt-1.132
Beer-1.092
andr-0.990
coat-0.984
ness-0.975
Token a
Token ID257
Feature activation+1.46e-01

Pos logit contributions
hatt+2.227
Beer+2.130
coat+1.939
ness+1.925
andr+1.918
Neg logit contributions
orem-2.461
ril-2.395
 nerv-2.293
riors-2.247
 wills-2.228
Token list
Token ID1351
Feature activation-2.54e-01

Pos logit contributions
hatt+0.214
Beer+0.205
coat+0.185
andr+0.185
ness+0.184
Neg logit contributions
orem-0.237
ril-0.231
 nerv-0.221
riors-0.216
 wills-0.215
Token of
Token ID286
Feature activation+2.63e-02

Pos logit contributions
orem+0.360
ril+0.351
 nerv+0.334
riors+0.325
 wills+0.323
Neg logit contributions
hatt-0.423
Beer-0.408
coat-0.373
andr-0.372
ness-0.371
Token actors
Token ID10544
Feature activation-7.72e-01

Pos logit contributions
hatt+0.040
Beer+0.039
andr+0.035
coat+0.035
ness+0.035
Neg logit contributions
orem-0.041
ril-0.040
 nerv-0.038
riors-0.037
 wills-0.037
Token being
Token ID852
Feature activation+1.89e-01

Pos logit contributions
orem+1.176
ril+1.160
 nerv+1.121
 wills+1.081
riors+1.074
Neg logit contributions
hatt-1.189
Beer-1.148
andr-1.045
coat-1.037
ness-1.012
Token have
Token ID423
Feature activation-5.37e-01

Pos logit contributions
hatt+0.755
Beer+0.724
coat+0.649
andr+0.649
ness+0.644
Neg logit contributions
orem-0.885
ril-0.866
 nerv-0.832
riors-0.811
 wills-0.808
Token to
Token ID284
Feature activation-2.99e-02

Pos logit contributions
orem+0.858
ril+0.840
 nerv+0.806
riors+0.783
 wills+0.781
Neg logit contributions
hatt-0.798
Beer-0.768
andr-0.691
coat-0.690
ness-0.684
Token be
Token ID307
Feature activation+2.94e-01

Pos logit contributions
orem+0.045
ril+0.044
 nerv+0.042
riors+0.041
 wills+0.041
Neg logit contributions
hatt-0.047
Beer-0.045
andr-0.041
coat-0.041
ness-0.041
Token a
Token ID257
Feature activation-2.19e-01

Pos logit contributions
hatt+0.419
Beer+0.402
coat+0.361
andr+0.360
ness+0.359
Neg logit contributions
orem-0.487
ril-0.477
 nerv-0.457
riors-0.446
 wills-0.444
Token practicing
Token ID18207
Feature activation-1.19e+00

Pos logit contributions
orem+0.342
ril+0.334
 nerv+0.321
riors+0.312
 wills+0.310
Neg logit contributions
hatt-0.334
Beer-0.321
andr-0.290
coat-0.290
ness-0.288
Token Lac
Token ID23115
Feature activation-1.49e-01

Pos logit contributions
orem+1.751
ril+1.710
 nerv+1.656
 wills+1.596
riors+1.588
Neg logit contributions
hatt-1.895
Beer-1.835
andr-1.658
coat-1.656
ness-1.636
Tokenanian
Token ID38336
Feature activation-4.88e-01

Pos logit contributions
orem+0.285
ril+0.280
 nerv+0.270
riors+0.264
 wills+0.263
Neg logit contributions
hatt-0.173
Beer-0.166
andr-0.144
coat-0.144
ness-0.143
Token psych
Token ID3795
Feature activation-3.49e-01

Pos logit contributions
orem+0.780
ril+0.763
 nerv+0.735
riors+0.714
 wills+0.710
Neg logit contributions
hatt-0.725
Beer-0.698
andr-0.628
coat-0.627
ness-0.622
Tokenoan
Token ID24611
Feature activation-1.72e+00

Pos logit contributions
orem+0.397
ril+0.385
 nerv+0.362
riors+0.349
 wills+0.347
Neg logit contributions
hatt-0.679
Beer-0.657
coat-0.609
andr-0.609
ness-0.607
Tokenalyst
Token ID21470
Feature activation-7.60e-01

Pos logit contributions
orem+2.234
ril+2.178
 nerv+2.066
riors+1.994
rior+1.985
Neg logit contributions
hatt-3.037
Beer-2.980
andr-2.706
coat-2.705
ness-2.689
Token to
Token ID284
Feature activation+9.95e-02

Pos logit contributions
orem+1.192
ril+1.171
 nerv+1.130
riors+1.091
 wills+1.081
Neg logit contributions
hatt-1.139
Beer-1.111
andr-0.998
coat-0.989
ness-0.975
Token way
Token ID835
Feature activation+8.05e-01

Pos logit contributions
orem+1.327
ril+1.300
 nerv+1.270
 wills+1.227
riors+1.226
Neg logit contributions
hatt-1.048
Beer-1.003
andr-0.896
coat-0.890
ness-0.870
Token to
Token ID284
Feature activation-1.86e-01

Pos logit contributions
hatt+1.147
Beer+1.094
ness+0.991
coat+0.985
andr+0.980
Neg logit contributions
orem-1.348
ril-1.302
 nerv-1.252
 wills-1.226
riors-1.219
Token kick
Token ID4829
Feature activation-2.43e-01

Pos logit contributions
orem+0.292
ril+0.287
 nerv+0.277
riors+0.268
 wills+0.267
Neg logit contributions
hatt-0.278
Beer-0.268
andr-0.241
coat-0.240
ness-0.238
Token start
Token ID923
Feature activation-5.15e-01

Pos logit contributions
orem+0.416
ril+0.410
 nerv+0.393
 wills+0.383
riors+0.383
Neg logit contributions
hatt-0.332
Beer-0.319
andr-0.285
coat-0.282
ness-0.280
Token a
Token ID257
Feature activation-4.32e-02

Pos logit contributions
orem+0.737
ril+0.729
 nerv+0.698
 wills+0.675
riors+0.672
Neg logit contributions
hatt-0.841
Beer-0.813
andr-0.744
coat-0.734
ness-0.725
Token child
Token ID1200
Feature activation+6.99e-01

Pos logit contributions
orem+0.076
ril+0.075
 nerv+0.073
 wills+0.071
riors+0.071
Neg logit contributions
hatt-0.056
Beer-0.054
andr-0.048
coat-0.048
ness-0.047
Token
Token ID447
Feature activation+9.82e-03

Pos logit contributions
hatt+0.986
Beer+0.946
andr+0.848
coat+0.847
ness+0.841
Neg logit contributions
orem-1.168
ril-1.147
 nerv-1.100
riors-1.073
 wills-1.069
Token
Token ID247
Feature activation-8.26e-02

Pos logit contributions
hatt+0.016
Beer+0.015
andr+0.014
coat+0.014
ness+0.014
Neg logit contributions
orem-0.014
ril-0.014
 nerv-0.013
riors-0.013
 wills-0.013
Tokens
Token ID82
Feature activation-3.48e-01

Pos logit contributions
orem+0.136
ril+0.134
 nerv+0.128
riors+0.125
 wills+0.124
Neg logit contributions
hatt-0.118
Beer-0.114
coat-0.102
andr-0.102
ness-0.101
Token play
Token ID711
Feature activation-9.54e-01

Pos logit contributions
orem+0.572
ril+0.563
 nerv+0.544
 wills+0.526
riors+0.526
Neg logit contributions
hatt-0.495
Beer-0.478
andr-0.428
coat-0.425
ness-0.417
Token and
Token ID290
Feature activation-2.69e-01

Pos logit contributions
ril+1.573
orem+1.572
 nerv+1.502
riors+1.473
 wills+1.463
Neg logit contributions
hatt-1.330
Beer-1.297
andr-1.148
coat-1.136
ness-1.111
Token need
Token ID761
Feature activation-4.26e-03

Pos logit contributions
hatt+1.413
Beer+1.357
coat+1.230
andr+1.228
ness+1.228
Neg logit contributions
orem-1.416
ril-1.386
 nerv-1.320
riors-1.289
 wills-1.281
Token to
Token ID284
Feature activation-2.39e-01

Pos logit contributions
orem+0.007
ril+0.007
 nerv+0.006
riors+0.006
 wills+0.006
Neg logit contributions
hatt-0.006
Beer-0.006
andr-0.006
coat-0.005
ness-0.005
Token be
Token ID307
Feature activation+4.34e-01

Pos logit contributions
orem+0.344
ril+0.335
 nerv+0.320
riors+0.311
 wills+0.309
Neg logit contributions
hatt-0.393
Beer-0.381
andr-0.347
coat-0.345
ness-0.342
Token studied
Token ID9713
Feature activation+9.19e-02

Pos logit contributions
hatt+0.677
Beer+0.655
andr+0.594
coat+0.591
ness+0.587
Neg logit contributions
orem-0.659
ril-0.644
 nerv-0.618
riors-0.599
 wills-0.598
Token further
Token ID2252
Feature activation+9.16e-01

Pos logit contributions
hatt+0.139
Beer+0.133
andr+0.120
coat+0.120
ness+0.119
Neg logit contributions
orem-0.145
ril-0.142
 nerv-0.136
riors-0.132
 wills-0.132
Token,
Token ID11
Feature activation+1.19e-01

Pos logit contributions
hatt+1.310
Beer+1.255
coat+1.130
andr+1.127
ness+1.125
Neg logit contributions
orem-1.515
ril-1.483
 nerv-1.420
riors-1.387
 wills-1.382
Token my
Token ID616
Feature activation+7.95e-01

Pos logit contributions
hatt+0.174
Beer+0.167
coat+0.150
andr+0.150
ness+0.149
Neg logit contributions
orem-0.192
ril-0.188
 nerv-0.180
riors-0.176
 wills-0.175
Token advice
Token ID5608
Feature activation+1.68e-01

Pos logit contributions
hatt+1.205
Beer+1.157
coat+1.047
andr+1.045
ness+1.042
Neg logit contributions
orem-1.245
ril-1.219
 nerv-1.165
riors-1.137
 wills-1.131
Token for
Token ID329
Feature activation+1.66e-01

Pos logit contributions
hatt+0.257
Beer+0.247
andr+0.223
coat+0.222
ness+0.220
Neg logit contributions
orem-0.262
ril-0.256
 nerv-0.245
riors-0.239
 wills-0.238
Token policy
Token ID2450
Feature activation-5.43e-01

Pos logit contributions
hatt+0.257
Beer+0.247
coat+0.224
andr+0.224
ness+0.223
Neg logit contributions
orem-0.256
ril-0.251
 nerv-0.239
riors-0.233
 wills-0.232
Token makers
Token ID14429
Feature activation+3.01e-02

Pos logit contributions
orem+0.792
ril+0.776
 nerv+0.743
riors+0.724
 wills+0.719
Neg logit contributions
hatt-0.881
Beer-0.847
andr-0.772
coat-0.769
ness-0.763
Token another
Token ID1194
Feature activation+5.36e-01

Pos logit contributions
orem+1.156
ril+1.131
 nerv+1.089
 wills+1.054
riors+1.047
Neg logit contributions
hatt-1.109
Beer-1.078
andr-0.971
coat-0.964
ness-0.945
Token drawing
Token ID8263
Feature activation-4.78e-01

Pos logit contributions
hatt+0.800
Beer+0.769
coat+0.694
andr+0.693
ness+0.689
Neg logit contributions
orem-0.854
ril-0.835
 nerv-0.800
riors-0.780
 wills-0.776
Token or
Token ID393
Feature activation-4.75e-02

Pos logit contributions
orem+0.773
ril+0.759
 nerv+0.730
riors+0.705
 wills+0.704
Neg logit contributions
hatt-0.700
Beer-0.675
andr-0.607
coat-0.603
ness-0.596
Token poem
Token ID21247
Feature activation-1.16e+00

Pos logit contributions
orem+0.063
ril+0.062
 nerv+0.059
riors+0.057
 wills+0.056
Neg logit contributions
hatt-0.083
Beer-0.081
andr-0.074
coat-0.074
ness-0.073
Token shortly
Token ID8972
Feature activation+1.21e-01

Pos logit contributions
orem+1.830
ril+1.793
 nerv+1.741
 wills+1.669
riors+1.667
Neg logit contributions
hatt-1.735
Beer-1.684
andr-1.512
coat-1.493
ness-1.465
Token after
Token ID706
Feature activation-4.46e-01

Pos logit contributions
hatt+0.218
Beer+0.211
coat+0.194
andr+0.194
ness+0.193
Neg logit contributions
orem-0.156
ril-0.152
 nerv-0.144
riors-0.139
 wills-0.139
Token finishing
Token ID12848
Feature activation-3.06e-01

Pos logit contributions
orem+0.677
ril+0.662
 nerv+0.635
 wills+0.615
riors+0.614
Neg logit contributions
hatt-0.697
Beer-0.672
andr-0.610
coat-0.607
ness-0.600
Token the
Token ID262
Feature activation-3.76e-02

Pos logit contributions
orem+0.487
ril+0.475
 nerv+0.457
riors+0.443
 wills+0.443
Neg logit contributions
hatt-0.459
Beer-0.441
andr-0.399
coat-0.396
ness-0.392
Token first
Token ID717
Feature activation+6.44e-01

Pos logit contributions
orem+0.059
ril+0.057
 nerv+0.055
 wills+0.053
riors+0.053
Neg logit contributions
hatt-0.057
Beer-0.055
andr-0.050
coat-0.050
ness-0.049
Token.
Token ID13
Feature activation+7.27e-02

Pos logit contributions
hatt+0.892
Beer+0.853
coat+0.765
andr+0.762
ness+0.761
Neg logit contributions
orem-1.095
ril-1.073
 nerv-1.029
riors-1.007
 wills-1.001
Token
Token ID198
Feature activation+3.68e-01

Pos logit contributions
hatt+0.111
Beer+0.106
coat+0.096
andr+0.096
ness+0.096
Neg logit contributions
orem-0.114
ril-0.111
 nerv-0.106
riors-0.104
 wills-0.103
Tokenov
Token ID709
Feature activation-1.56e+00

Pos logit contributions
hatt+1.025
Beer+0.991
coat+0.914
andr+0.913
ness+0.911
Neg logit contributions
orem-0.706
ril-0.686
 nerv-0.653
riors-0.629
 wills-0.627
Token,
Token ID11
Feature activation+3.72e-01

Pos logit contributions
orem+2.439
ril+2.418
 nerv+2.308
riors+2.258
 wills+2.238
Neg logit contributions
hatt-2.292
Beer-2.216
coat-1.998
andr-1.991
ness-1.953
Token now
Token ID783
Feature activation+7.08e-02

Pos logit contributions
hatt+0.579
Beer+0.556
andr+0.505
coat+0.505
ness+0.504
Neg logit contributions
orem-0.570
ril-0.555
 nerv-0.530
riors-0.518
 wills-0.514
Token 88
Token ID9193
Feature activation-4.34e-01

Pos logit contributions
hatt+0.108
Beer+0.104
coat+0.094
andr+0.094
ness+0.093
Neg logit contributions
orem-0.110
ril-0.108
 nerv-0.103
riors-0.100
 wills-0.100
Token,
Token ID11
Feature activation+1.54e-01

Pos logit contributions
orem+0.733
ril+0.718
 nerv+0.690
riors+0.673
 wills+0.671
Neg logit contributions
hatt-0.607
Beer-0.580
coat-0.520
andr-0.520
ness-0.512
Token Philadelphia
Token ID8857
Feature activation-8.92e-01

Pos logit contributions
hatt+0.235
Beer+0.226
andr+0.204
coat+0.204
ness+0.203
Neg logit contributions
orem-0.240
ril-0.234
 nerv-0.224
riors-0.218
 wills-0.217
Token
Token ID447
Feature activation+1.03e-01

Pos logit contributions
orem+1.338
ril+1.308
 nerv+1.252
riors+1.215
 wills+1.214
Neg logit contributions
hatt-1.410
Beer-1.352
andr-1.233
coat-1.228
ness-1.209
Token
Token ID247
Feature activation+3.45e-02

Pos logit contributions
hatt+0.124
Beer+0.118
coat+0.103
andr+0.103
ness+0.103
Neg logit contributions
orem-0.193
ril-0.189
 nerv-0.182
riors-0.178
 wills-0.178
Tokens
Token ID82
Feature activation-2.06e-01

Pos logit contributions
hatt+0.043
Beer+0.041
andr+0.036
coat+0.036
ness+0.036
Neg logit contributions
orem-0.063
ril-0.062
 nerv-0.060
riors-0.059
 wills-0.058
Token accents
Token ID39271
Feature activation+6.62e-01

Pos logit contributions
orem+0.329
ril+0.323
 nerv+0.310
riors+0.301
 wills+0.300
Neg logit contributions
hatt-0.307
Beer-0.295
coat-0.266
andr-0.265
ness-0.262
Token are
Token ID389
Feature activation+1.97e-01

Pos logit contributions
hatt+1.007
Beer+0.967
coat+0.876
andr+0.875
ness+0.872
Neg logit contributions
orem-1.033
ril-1.011
 nerv-0.967
riors-0.942
 wills-0.938
Token
Token ID447
Feature activation-1.74e-01

Pos logit contributions
orem+1.303
ril+1.278
 nerv+1.230
riors+1.200
 wills+1.195
Neg logit contributions
hatt-0.996
Beer-0.952
coat-0.847
andr-0.847
ness-0.839
Token
Token ID247
Feature activation+2.24e-02

Pos logit contributions
orem+0.232
ril+0.227
 nerv+0.215
riors+0.209
rior+0.206
Neg logit contributions
hatt-0.305
Beer-0.293
coat-0.269
andr-0.269
ness-0.267
Tokens
Token ID82
Feature activation-3.79e-01

Pos logit contributions
hatt+0.018
Beer+0.017
coat+0.014
andr+0.014
ness+0.014
Neg logit contributions
orem-0.051
ril-0.050
 nerv-0.048
riors-0.048
 wills-0.047
Token sake
Token ID11060
Feature activation-7.46e-01

Pos logit contributions
orem+0.648
ril+0.635
 nerv+0.611
riors+0.595
 wills+0.592
Neg logit contributions
hatt-0.522
Beer-0.501
coat-0.447
andr-0.446
ness-0.441
Token,
Token ID11
Feature activation-7.11e-02

Pos logit contributions
orem+1.331
ril+1.305
 nerv+1.257
riors+1.228
 wills+1.221
Neg logit contributions
hatt-0.969
Beer-0.926
coat-0.822
andr-0.821
ness-0.814
Token American
Token ID1605
Feature activation-5.17e-01

Pos logit contributions
orem+0.110
ril+0.108
 nerv+0.103
riors+0.100
 wills+0.100
Neg logit contributions
hatt-0.109
Beer-0.105
coat-0.095
andr-0.095
ness-0.094
Token Horror
Token ID22732
Feature activation-1.55e+00

Pos logit contributions
orem+0.558
ril+0.538
 nerv+0.508
riors+0.482
 wills+0.481
Neg logit contributions
hatt-1.038
Beer-1.005
andr-0.935
coat-0.934
ness-0.925
Token Story
Token ID8362
Feature activation-7.09e-01

Pos logit contributions
orem+1.577
ril+1.556
 nerv+1.404
riors+1.389
rior+1.360
Neg logit contributions
hatt-3.152
Beer-3.076
andr-2.871
coat-2.844
ness-2.795
Token:
Token ID25
Feature activation-1.29e-01

Pos logit contributions
orem+1.092
ril+1.067
 nerv+1.026
riors+0.993
 wills+0.990
Neg logit contributions
hatt-1.097
Beer-1.054
andr-0.956
coat-0.954
ness-0.944
Token Murder
Token ID23375
Feature activation+3.97e-01

Pos logit contributions
orem+0.204
ril+0.199
 nerv+0.191
riors+0.186
 wills+0.184
Neg logit contributions
hatt-0.194
Beer-0.186
coat-0.169
andr-0.168
ness-0.167
Token House
Token ID2097
Feature activation+7.88e-01

Pos logit contributions
hatt+0.613
Beer+0.589
andr+0.535
coat+0.533
ness+0.529
Neg logit contributions
orem-0.611
ril-0.597
 nerv-0.571
riors-0.557
 wills-0.554
Token That
Token ID1320
Feature activation+4.12e-01

Pos logit contributions
orem+0.371
ril+0.365
 nerv+0.348
riors+0.340
 wills+0.337
Neg logit contributions
hatt-0.355
Beer-0.340
andr-0.308
coat-0.308
ness-0.304
Token is
Token ID318
Feature activation+5.46e-01

Pos logit contributions
hatt+0.603
Beer+0.579
andr+0.521
coat+0.520
ness+0.514
Neg logit contributions
orem-0.665
ril-0.653
 nerv-0.626
riors-0.609
 wills-0.607
Token not
Token ID407
Feature activation-2.51e-01

Pos logit contributions
hatt+0.782
Beer+0.750
andr+0.673
coat+0.673
ness+0.667
Neg logit contributions
orem-0.902
ril-0.884
 nerv-0.850
riors-0.826
 wills-0.824
Token even
Token ID772
Feature activation+5.12e-01

Pos logit contributions
orem+0.395
ril+0.388
 nerv+0.376
 wills+0.362
riors+0.359
Neg logit contributions
hatt-0.376
Beer-0.363
andr-0.326
coat-0.326
ness-0.318
Token the
Token ID262
Feature activation+9.11e-05

Pos logit contributions
hatt+0.759
Beer+0.730
andr+0.658
coat+0.658
ness+0.652
Neg logit contributions
orem-0.820
ril-0.803
 nerv-0.771
riors-0.748
 wills-0.746
Token worst
Token ID5290
Feature activation-3.85e-01

Pos logit contributions
hatt+0.000
Beer+0.000
andr+0.000
coat+0.000
ness+0.000
Neg logit contributions
orem-0.000
ril-0.000
 nerv-0.000
riors-0.000
 wills-0.000
Token of
Token ID286
Feature activation+1.55e-01

Pos logit contributions
orem+0.601
ril+0.588
 nerv+0.563
riors+0.547
 wills+0.545
Neg logit contributions
hatt-0.586
Beer-0.563
andr-0.510
coat-0.508
ness-0.503
Token it
Token ID340
Feature activation-8.67e-02

Pos logit contributions
hatt+0.261
Beer+0.252
coat+0.230
ness+0.230
andr+0.229
Neg logit contributions
orem-0.219
ril-0.214
 nerv-0.202
riors-0.198
 wills-0.195
Token.
Token ID13
Feature activation-1.30e-01

Pos logit contributions
orem+0.142
ril+0.139
 nerv+0.134
riors+0.130
 wills+0.129
Neg logit contributions
hatt-0.125
Beer-0.120
andr-0.108
coat-0.108
ness-0.106
Token
Token ID198
Feature activation+8.18e-02

Pos logit contributions
orem+0.203
ril+0.199
 nerv+0.190
riors+0.185
 wills+0.183
Neg logit contributions
hatt-0.199
Beer-0.191
andr-0.173
coat-0.173
ness-0.171
Token
Token ID198
Feature activation-1.31e-01

Pos logit contributions
hatt+0.134
Beer+0.128
andr+0.118
coat+0.116
ness+0.114
Neg logit contributions
orem-0.118
ril-0.116
 nerv-0.108
riors-0.107
rior-0.106
Token our
Token ID674
Feature activation-1.45e-01

Pos logit contributions
orem+0.873
ril+0.863
 nerv+0.835
 wills+0.811
riors+0.803
Neg logit contributions
hatt-0.794
Beer-0.765
andr-0.689
coat-0.677
ness-0.666
Token legs
Token ID7405
Feature activation-5.02e-01

Pos logit contributions
orem+0.226
ril+0.222
 nerv+0.214
 wills+0.210
riors+0.207
Neg logit contributions
hatt-0.219
Beer-0.213
andr-0.192
coat-0.190
ness-0.187
Token open
Token ID1280
Feature activation-8.59e-01

Pos logit contributions
orem+0.800
ril+0.788
 nerv+0.766
 wills+0.751
riors+0.733
Neg logit contributions
hatt-0.734
Beer-0.719
andr-0.638
coat-0.628
ness-0.617
Token.
Token ID13
Feature activation-2.88e-01

Pos logit contributions
orem+1.384
ril+1.371
 nerv+1.333
 wills+1.294
riors+1.274
Neg logit contributions
hatt-1.243
Beer-1.206
andr-1.083
coat-1.062
ness-1.032
Token I
Token ID314
Feature activation-4.98e-01

Pos logit contributions
orem+0.455
ril+0.447
 nerv+0.428
riors+0.417
 wills+0.414
Neg logit contributions
hatt-0.430
Beer-0.412
andr-0.373
coat-0.372
ness-0.368
Token found
Token ID1043
Feature activation-5.74e-01

Pos logit contributions
orem+0.786
ril+0.782
 nerv+0.754
 wills+0.728
riors+0.723
Neg logit contributions
hatt-0.736
Beer-0.720
andr-0.642
coat-0.639
ness-0.624
Token it
Token ID340
Feature activation-5.03e-01

Pos logit contributions
orem+0.884
ril+0.870
 nerv+0.841
 wills+0.816
riors+0.809
Neg logit contributions
hatt-0.877
Beer-0.847
andr-0.765
coat-0.760
ness-0.745
Token painful
Token ID12132
Feature activation-6.98e-01

Pos logit contributions
orem+0.859
ril+0.848
 nerv+0.837
 wills+0.805
riors+0.791
Neg logit contributions
hatt-0.681
Beer-0.654
andr-0.585
coat-0.579
ness-0.560
Token.
Token ID13
Feature activation-3.02e-01

Pos logit contributions
orem+1.106
ril+1.095
 nerv+1.070
 wills+1.022
riors+1.020
Neg logit contributions
hatt-1.031
Beer-0.999
andr-0.900
coat-0.887
ness-0.853
Token When
Token ID1649
Feature activation-1.67e+00

Pos logit contributions
orem+0.478
ril+0.470
 nerv+0.450
riors+0.439
 wills+0.435
Neg logit contributions
hatt-0.450
Beer-0.430
andr-0.390
coat-0.389
ness-0.384
Token he
Token ID339
Feature activation-7.76e-01

Pos logit contributions
orem+2.371
ril+2.348
 nerv+2.269
 wills+2.196
riors+2.172
Neg logit contributions
hatt-2.731
Beer-2.656
andr-2.418
coat-2.398
ness-2.346
Tokend
Token ID67
Feature activation-1.07e-01

Pos logit contributions
orem+0.411
ril+0.408
 nerv+0.392
riors+0.383
rior+0.380
Neg logit contributions
hatt-0.244
Beer-0.232
andr-0.205
coat-0.201
ness-0.198
Token recounted
Token ID34187
Feature activation+7.66e-02

Pos logit contributions
orem+0.159
ril+0.156
 nerv+0.149
riors+0.145
 wills+0.144
Neg logit contributions
hatt-0.171
Beer-0.165
andr-0.150
coat-0.150
ness-0.149
Token in
Token ID287
Feature activation+1.57e-01

Pos logit contributions
hatt+0.114
Beer+0.110
andr+0.099
coat+0.099
ness+0.098
Neg logit contributions
orem-0.122
ril-0.119
 nerv-0.115
riors-0.111
 wills-0.111
Token the
Token ID262
Feature activation-1.32e-01

Pos logit contributions
hatt+0.243
Beer+0.234
coat+0.212
andr+0.212
ness+0.211
Neg logit contributions
orem-0.241
ril-0.236
 nerv-0.226
riors-0.220
 wills-0.219
Token New
Token ID968
Feature activation-9.84e-01

Pos logit contributions
orem+0.192
ril+0.188
 nerv+0.179
riors+0.174
 wills+0.173
Neg logit contributions
hatt-0.214
Beer-0.206
coat-0.188
andr-0.188
ness-0.187
Token York
Token ID1971
Feature activation-2.65e+00

Pos logit contributions
orem+1.025
ril+1.003
 nerv+0.934
riors+0.898
 wills+0.888
Neg logit contributions
hatt-1.995
Beer-1.932
andr-1.800
coat-1.793
ness-1.775
Token Times
Token ID3782
Feature activation-1.53e+00

Pos logit contributions
orem+2.214
ril+2.150
 nerv+2.020
 wills+1.882
riors+1.873
Neg logit contributions
hatt-5.829
Beer-5.652
andr-5.317
coat-5.293
ness-5.234
Token recently
Token ID2904
Feature activation+1.93e-01

Pos logit contributions
orem+2.424
ril+2.390
 nerv+2.300
riors+2.209
igation+2.206
Neg logit contributions
hatt-2.233
Beer-2.151
andr-1.956
coat-1.937
ness-1.915
Token,
Token ID11
Feature activation+4.94e-02

Pos logit contributions
hatt+0.258
Beer+0.247
andr+0.220
coat+0.220
ness+0.217
Neg logit contributions
orem-0.338
ril-0.332
 nerv-0.319
riors-0.311
 wills-0.310
Token edible
Token ID35988
Feature activation+1.47e+00

Pos logit contributions
hatt+0.075
Beer+0.072
coat+0.066
andr+0.066
ness+0.065
Neg logit contributions
orem-0.077
ril-0.075
 nerv-0.072
riors-0.070
 wills-0.070
Token tet
Token ID28408
Feature activation+6.35e-01

Pos logit contributions
hatt+2.290
Beer+2.208
ness+2.044
coat+2.001
andr+1.996
Neg logit contributions
orem-2.244
ril-2.180
 nerv-2.059
riors-2.037
 wills-1.999
Token
Token ID198
Feature activation+4.17e-02

Pos logit contributions
hatt+0.442
Beer+0.422
andr+0.389
coat+0.384
ness+0.375
Neg logit contributions
orem-0.389
ril-0.384
 nerv-0.359
riors-0.354
rior-0.352
TokenThat
Token ID2504
Feature activation+4.59e-01

Pos logit contributions
hatt+0.051
Beer+0.048
coat+0.043
andr+0.043
ness+0.042
Neg logit contributions
orem-0.077
ril-0.076
 nerv-0.072
riors-0.071
rior-0.071
Token being
Token ID852
Feature activation+7.74e-02

Pos logit contributions
hatt+0.677
Beer+0.650
coat+0.586
andr+0.585
ness+0.582
Neg logit contributions
orem-0.738
ril-0.723
 nerv-0.693
riors-0.675
 wills-0.672
Token said
Token ID531
Feature activation-2.65e-01

Pos logit contributions
hatt+0.113
Beer+0.108
coat+0.098
andr+0.098
ness+0.097
Neg logit contributions
orem-0.126
ril-0.123
 nerv-0.118
riors-0.115
 wills-0.114
Token,
Token ID11
Feature activation+2.78e-02

Pos logit contributions
orem+0.479
ril+0.470
 nerv+0.452
riors+0.442
 wills+0.440
Neg logit contributions
hatt-0.338
Beer-0.323
coat-0.286
andr-0.286
ness-0.284
Token Vil
Token ID34037
Feature activation-2.64e+00

Pos logit contributions
hatt+0.043
Beer+0.041
coat+0.038
andr+0.038
ness+0.037
Neg logit contributions
orem-0.043
ril-0.042
 nerv-0.040
riors-0.039
 wills-0.039
Tokenma
Token ID2611
Feature activation+3.00e-01

Pos logit contributions
orem+1.949
ril+1.833
igation+1.539
riors+1.519
rior+1.513
Neg logit contributions
hatt-6.120
Beer-5.995
coat-5.594
andr-5.583
Feel-5.505
Token and
Token ID290
Feature activation-2.05e-01

Pos logit contributions
hatt+0.463
Beer+0.445
coat+0.403
andr+0.403
ness+0.401
Neg logit contributions
orem-0.462
ril-0.451
 nerv-0.431
riors-0.420
 wills-0.417
Token the
Token ID262
Feature activation-3.03e-01

Pos logit contributions
orem+0.304
ril+0.297
 nerv+0.284
riors+0.276
 wills+0.275
Neg logit contributions
hatt-0.327
Beer-0.315
coat-0.287
andr-0.287
ness-0.285
Token NFL
Token ID5134
Feature activation-1.67e+00

Pos logit contributions
orem+0.414
ril+0.403
 nerv+0.384
riors+0.372
 wills+0.370
Neg logit contributions
hatt-0.521
Beer-0.503
andr-0.460
coat-0.460
ness-0.457
TokenPA
Token ID4537
Feature activation+7.57e-02

Pos logit contributions
orem+2.554
ril+2.502
 nerv+2.409
riors+2.380
 wills+2.354
Neg logit contributions
hatt-2.543
Beer-2.418
andr-2.205
coat-2.173
ness-2.147
Token by
Token ID416
Feature activation+5.19e-01

Pos logit contributions
orem+1.422
ril+1.404
 nerv+1.342
riors+1.305
 wills+1.296
Neg logit contributions
hatt-1.499
Beer-1.441
andr-1.306
coat-1.301
ness-1.272
Token the
Token ID262
Feature activation+1.05e-01

Pos logit contributions
hatt+0.807
Beer+0.776
coat+0.705
andr+0.704
ness+0.702
Neg logit contributions
orem-0.792
ril-0.774
 nerv-0.739
riors-0.720
 wills-0.715
Token majority
Token ID3741
Feature activation-1.23e+00

Pos logit contributions
hatt+0.159
Beer+0.152
coat+0.138
andr+0.138
ness+0.137
Neg logit contributions
orem-0.165
ril-0.162
 nerv-0.155
riors-0.151
 wills-0.150
Token of
Token ID286
Feature activation-3.64e-01

Pos logit contributions
orem+1.699
ril+1.656
 nerv+1.578
riors+1.528
 wills+1.523
Neg logit contributions
hatt-2.102
Beer-2.030
andr-1.855
coat-1.854
ness-1.843
Token feminist
Token ID14314
Feature activation-2.11e+00

Pos logit contributions
orem+0.537
ril+0.524
 nerv+0.502
riors+0.487
 wills+0.486
Neg logit contributions
hatt-0.584
Beer-0.564
andr-0.512
coat-0.512
ness-0.508
Token philosophers
Token ID24858
Feature activation-2.66e+00

Pos logit contributions
orem+2.736
ril+2.689
 nerv+2.645
 wills+2.554
riors+2.511
Neg logit contributions
hatt-3.694
Beer-3.592
coat-3.267
andr-3.261
ness-3.151
Token.
Token ID13
Feature activation+4.45e-03

Pos logit contributions
orem+3.914
ril+3.851
 nerv+3.824
 wills+3.609
riors+3.605
Neg logit contributions
hatt-4.104
Beer-3.984
andr-3.618
coat-3.547
Feel-3.444
Token I
Token ID314
Feature activation-7.51e-02

Pos logit contributions
hatt+0.007
Beer+0.006
coat+0.006
andr+0.006
ness+0.006
Neg logit contributions
orem-0.007
ril-0.007
 nerv-0.007
riors-0.006
 wills-0.006
Token do
Token ID466
Feature activation-2.62e-01

Pos logit contributions
orem+0.116
ril+0.114
 nerv+0.109
riors+0.105
 wills+0.105
Neg logit contributions
hatt-0.116
Beer-0.112
andr-0.101
coat-0.101
ness-0.099
Token not
Token ID407
Feature activation-3.62e-02

Pos logit contributions
orem+0.448
ril+0.441
 nerv+0.425
riors+0.413
 wills+0.413
Neg logit contributions
hatt-0.358
Beer-0.344
andr-0.306
coat-0.305
ness-0.299
Token see
Token ID766
Feature activation-7.11e-01

Pos logit contributions
orem+0.056
ril+0.054
 nerv+0.052
 wills+0.051
riors+0.050
Neg logit contributions
hatt-0.056
Beer-0.054
andr-0.049
coat-0.049
ness-0.048
Token slider
Token ID28982
Feature activation+1.50e-02

Pos logit contributions
orem+1.191
ril+1.164
 nerv+1.142
 wills+1.108
rior+1.100
Neg logit contributions
hatt-0.916
Beer-0.871
andr-0.783
coat-0.768
ness-0.737
Token after
Token ID706
Feature activation-6.16e-01

Pos logit contributions
hatt+0.022
Beer+0.021
andr+0.019
coat+0.019
ness+0.018
Neg logit contributions
orem-0.024
ril-0.024
 nerv-0.023
riors-0.023
 wills-0.022
Token shifting
Token ID15852
Feature activation+2.57e-01

Pos logit contributions
orem+0.926
ril+0.915
 nerv+0.883
 wills+0.847
riors+0.844
Neg logit contributions
hatt-0.962
Beer-0.930
andr-0.841
coat-0.837
ness-0.830
Token to
Token ID284
Feature activation-6.77e-04

Pos logit contributions
hatt+0.382
Beer+0.368
andr+0.330
coat+0.329
ness+0.326
Neg logit contributions
orem-0.408
ril-0.401
 nerv-0.385
 wills-0.374
riors-0.373
Token the
Token ID262
Feature activation-7.92e-02

Pos logit contributions
orem+0.001
ril+0.001
 nerv+0.001
riors+0.001
 wills+0.001
Neg logit contributions
hatt-0.001
Beer-0.001
coat-0.001
andr-0.001
ness-0.001
Token pen
Token ID3112
Feature activation-2.72e+00

Pos logit contributions
orem+0.104
ril+0.101
 nerv+0.096
riors+0.093
 wills+0.092
Neg logit contributions
hatt-0.140
Beer-0.136
andr-0.125
coat-0.125
ness-0.124
Token last
Token ID938
Feature activation-1.14e-01

Pos logit contributions
ril+4.101
orem+4.063
 nerv+3.897
riors+3.777
rior+3.771
Neg logit contributions
hatt-4.071
Beer-4.011
andr-3.543
coat-3.495
Feel-3.432
Token year
Token ID614
Feature activation+3.37e-01

Pos logit contributions
orem+0.217
ril+0.213
 nerv+0.207
 wills+0.201
riors+0.201
Neg logit contributions
hatt-0.135
Beer-0.128
andr-0.112
coat-0.112
ness-0.110
Token,
Token ID11
Feature activation-5.55e-02

Pos logit contributions
hatt+0.478
Beer+0.459
andr+0.411
coat+0.411
ness+0.407
Neg logit contributions
orem-0.560
ril-0.550
 nerv-0.529
riors-0.515
 wills-0.512
Token am
Token ID716
Feature activation+8.80e-02

Pos logit contributions
orem+0.095
ril+0.093
 nerv+0.090
 wills+0.087
riors+0.087
Neg logit contributions
hatt-0.076
Beer-0.073
coat-0.065
andr-0.065
ness-0.065
Tokenassing
Token ID19696
Feature activation-3.12e-02

Pos logit contributions
hatt+0.145
Beer+0.140
coat+0.128
andr+0.128
ness+0.127
Neg logit contributions
orem-0.126
ril-0.123
 nerv-0.118
riors-0.114
 wills-0.114
Token (
Token ID357
Feature activation+1.20e+00

Pos logit contributions
orem+0.488
ril+0.477
 nerv+0.456
riors+0.444
 wills+0.442
Neg logit contributions
hatt-0.479
Beer-0.461
coat-0.417
andr-0.417
ness-0.415
Tokent
Token ID83
Feature activation+3.24e-02

Pos logit contributions
hatt+1.743
Beer+1.673
coat+1.509
andr+1.505
ness+1.500
Neg logit contributions
orem-1.945
ril-1.893
 nerv-1.831
 wills-1.785
riors-1.783
Token
Token ID447
Feature activation-2.28e-01

Pos logit contributions
hatt+0.046
Beer+0.044
coat+0.040
andr+0.040
ness+0.040
Neg logit contributions
orem-0.054
ril-0.053
 nerv-0.051
riors-0.049
 wills-0.049
Token
Token ID247
Feature activation-5.71e-02

Pos logit contributions
orem+0.323
ril+0.315
 nerv+0.301
riors+0.292
 wills+0.291
Neg logit contributions
hatt-0.380
Beer-0.366
coat-0.335
andr-0.334
ness-0.333
Token)
Token ID8
Feature activation-4.14e-01

Pos logit contributions
orem+0.098
ril+0.096
 nerv+0.093
riors+0.091
 wills+0.090
Neg logit contributions
hatt-0.078
Beer-0.074
coat-0.066
andr-0.066
ness-0.066
Token exp
Token ID1033
Feature activation-3.02e+00

Pos logit contributions
orem+0.618
ril+0.603
 nerv+0.577
riors+0.560
 wills+0.558
Neg logit contributions
hatt-0.659
Beer-0.635
coat-0.577
andr-0.577
ness-0.573
Token(
Token ID7
Feature activation+9.83e-01

Pos logit contributions
orem+3.911
ril+3.827
 nerv+3.674
riors+3.501
rior+3.497
Neg logit contributions
hatt-5.245
Beer-5.049
coat-4.621
andr-4.609
Feel-4.525
Token-(
Token ID30420
Feature activation+9.17e-01

Pos logit contributions
hatt+1.450
Beer+1.397
coat+1.259
andr+1.257
ness+1.252
Neg logit contributions
orem-1.581
ril-1.542
 nerv-1.485
riors-1.447
 wills-1.445
Tokent
Token ID83
Feature activation+1.52e-01

Pos logit contributions
hatt+1.347
Beer+1.293
coat+1.168
andr+1.164
ness+1.161
Neg logit contributions
orem-1.483
ril-1.441
 nerv-1.395
 wills-1.358
riors-1.356
Token-
Token ID12
Feature activation-2.18e-02

Pos logit contributions
hatt+0.222
Beer+0.213
coat+0.192
andr+0.191
ness+0.191
Neg logit contributions
orem-0.246
ril-0.240
 nerv-0.231
riors-0.225
 wills-0.224
Tokent
Token ID83
Feature activation+1.03e-01

Pos logit contributions
orem+0.034
ril+0.033
 nerv+0.031
riors+0.031
 wills+0.030
Neg logit contributions
hatt-0.034
Beer-0.032
andr-0.029
coat-0.029
ness-0.029