TOP ACTIVATIONS
MAX = 8.665

also produced strong runs . Jama al Charles also participated in
targets has committed to the Semin oles while another is off
Korean state . The only recognizable special restriction American tourists receive
. Germany 's Bayer had its 200 m euro
Europe Russian state energy company Gaz prom has resumed some gas
Russian TV stations showed a Gaz prom official ordering a res
1 ] W EP , recognizable by its key of 10
/ t att oo - recogn ition - research - threat
are , and what the Semin oles chances are .
tobacco " over whelming ." Cig arettes are " the only
June 2007 , Singapore and Brune i celebrated the 40 th
immune system attacks the new organ , with graft - vers
Ast ur ias , the Bas que Country , the Canary
has the state title of Brune i in Latin script .[
F DA Commissioner Scott Gott lie b called the amount
the ob verse of the Brune i version is similar to
He yn went to a Jud as Priest concert in Land
. Sac ram ents . Bapt ism . Conf irmation .
Cuban President Fidel Castro , Cuban dissidents who advocate greater human
almost identical except that the Brune i version has their state

MIN ACTIVATIONS
MIN = -8.964

of life beyond the plat itudes ? I am certain
of 15 Photos : Carly Fiorina 's political career Fiorina ,
to this woman with sentimental plat itudes , Lac an
respects these people and never condesc ends to them , evidenced
Times Square in the old Naval Air Station in South We
of 15 Photos : Carly Fiorina 's political career Fiorina speaks
of 15 Photos : Carly Fiorina 's political career Fiorina arrives
controversial editor . Some of Milo 's colleagues at Breitbart reportedly
of 15 Photos : Carly Fiorina 's political career Fiorina speaks
documented about so - called sexism and racism on the left
thank you @ mr _ se an h ug
of 15 Photos : Carly Fiorina 's political career Fiorina concedes
Morgan have clashed in a sexism row . Sus
of 15 Photos : Carly Fiorina 's political career Box er
threatened to walk out if Milo was not let go .
ing | Create your own warp drive website for your business
Carly Fiorina 's political career Fiorina , right , poses for
that because one of my tweets asking " when Sam Bac
a Rolling Stone reporter as Fiorina appeared on TV . "
35 p . m .: Milo has resigned .

INTERVAL 4.258 - 8.665
CONTAINS 0.354%

Jamaica . Credit : AP Cuban authorities organised a mass exodus
co - op ting of punk fashion by popular designers and
down the momentum of popular reform movements . Israel found the
his two half centuries in Kingston , Jamaica in the 2006
rejected his book The Magic Finger , he would leave them

INTERVAL -0.150 - 4.258
CONTAINS 54.933%

. V ini ar summoned around 20 traders and
lu . Using it on a widespread prevent ative scale could
the name a teenage boy memor ably gives his penis in
An nie Hall ( 1977 )
Department . Stre ng thening rural transport , last mile connectivity

INTERVAL -4.557 - -0.150
CONTAINS 44.370%

s supreme leader , Ay at ollah Ali Kham
I see no other alternative too , but I have no
those living in Wa ik iki where the tourism industry has
and said , It s not easy
voter file the Democratic National Committee makes available to candidates to

INTERVAL -8.964 - -4.557
CONTAINS 0.343%

of the Year voting to Marcus Paige .[ 103 ] He
block the Milwaukee Bucks ' Sterling Brown , who powered through
. The top eight airports commanded about half of all passenger
were being rigged to change Donald Trump votes to Hillary Clinton
drones for such things as traffic control and surveillance . McDonnell
Token also
Token ID635
Feature activation-5.70e-02

Pos logit contributions
poke+0.355
horse+0.342
plate+0.327
 Hawth+0.308
 Trafford+0.308
Neg logit contributions
 tremend-0.477
 streng-0.416
aughs-0.406
utical-0.402
 Libre-0.383
Token produced
Token ID4635
Feature activation-3.00e-02

Pos logit contributions
poke+0.041
horse+0.039
plate+0.037
 Hawth+0.035
 Trafford+0.035
Neg logit contributions
 tremend-0.058
 streng-0.050
aughs-0.049
utical-0.049
 Libre-0.047
Token strong
Token ID1913
Feature activation+8.00e-01

Pos logit contributions
poke+0.022
horse+0.021
plate+0.020
 Hawth+0.019
 Trafford+0.019
Neg logit contributions
 tremend-0.029
 streng-0.026
aughs-0.025
utical-0.025
 Libre-0.024
Token runs
Token ID4539
Feature activation-3.40e+00

Pos logit contributions
 tremend+0.778
 streng+0.682
aughs+0.661
utical+0.655
 Libre+0.623
Neg logit contributions
poke-0.598
horse-0.577
plate-0.551
 Hawth-0.521
 Trafford-0.517
Token.
Token ID13
Feature activation-1.47e-01

Pos logit contributions
poke+2.175
horse+2.114
plate+1.996
 Hawth+1.860
 Trafford+1.842
Neg logit contributions
 tremend-3.645
 streng-3.225
aughs-3.171
utical-3.135
 Libre-2.993
Token Jama
Token ID21661
Feature activation+8.66e+00

Pos logit contributions
poke+0.112
horse+0.108
plate+0.103
 Hawth+0.098
 Trafford+0.098
Neg logit contributions
 tremend-0.142
 streng-0.124
aughs-0.120
utical-0.118
 Libre-0.112
Tokenal
Token ID282
Feature activation+3.14e-01

Pos logit contributions
 tremend+7.785
 streng+7.022
aughs+6.951
utical+6.856
 Libre+6.593
Neg logit contributions
poke-6.186
horse-5.908
plate-5.764
 Trafford-5.385
fleet-5.350
Token Charles
Token ID7516
Feature activation-1.08e+00

Pos logit contributions
 tremend+0.316
 streng+0.280
aughs+0.273
utical+0.268
 Libre+0.259
Neg logit contributions
poke-0.220
horse-0.211
plate-0.202
 Trafford-0.189
 Hawth-0.188
Token also
Token ID635
Feature activation+2.47e-01

Pos logit contributions
poke+0.730
horse+0.704
plate+0.667
 Trafford+0.623
 Hawth+0.622
Neg logit contributions
 tremend-1.133
 streng-0.999
aughs-0.975
utical-0.966
 Libre-0.923
Token participated
Token ID14888
Feature activation+3.34e+00

Pos logit contributions
 tremend+0.249
 streng+0.218
aughs+0.214
utical+0.211
 Libre+0.201
Neg logit contributions
poke-0.176
horse-0.170
plate-0.161
 Hawth-0.152
 Trafford-0.151
Token in
Token ID287
Feature activation-5.64e-01

Pos logit contributions
 tremend+3.346
 streng+2.967
aughs+2.847
utical+2.785
 Libre+2.705
Neg logit contributions
poke-2.345
horse-2.232
plate-2.136
 Trafford-2.036
fleet-2.014
Token targets
Token ID6670
Feature activation-1.17e+00

Pos logit contributions
 tremend+0.717
 streng+0.624
aughs+0.613
utical+0.601
 Libre+0.561
Neg logit contributions
poke-0.616
horse-0.600
plate-0.572
 Hawth-0.547
 Trafford-0.545
Token has
Token ID468
Feature activation-2.56e-01

Pos logit contributions
poke+0.791
horse+0.763
plate+0.725
 Hawth+0.681
 Trafford+0.680
Neg logit contributions
 tremend-1.221
 streng-1.085
aughs-1.057
utical-1.038
 Libre-0.994
Token committed
Token ID5364
Feature activation+1.92e+00

Pos logit contributions
poke+0.204
horse+0.198
plate+0.191
 Hawth+0.181
 Trafford+0.180
Neg logit contributions
 tremend-0.234
 streng-0.203
aughs-0.199
utical-0.195
 Libre-0.184
Token to
Token ID284
Feature activation-7.18e-02

Pos logit contributions
 tremend+1.982
 streng+1.764
aughs+1.706
utical+1.683
 Libre+1.629
Neg logit contributions
poke-1.305
horse-1.248
plate-1.191
 Trafford-1.118
 Hawth-1.107
Token the
Token ID262
Feature activation-8.45e-02

Pos logit contributions
poke+0.048
horse+0.045
plate+0.043
 Hawth+0.041
 Trafford+0.041
Neg logit contributions
 tremend-0.076
 streng-0.067
aughs-0.066
utical-0.065
 Libre-0.062
Token Semin
Token ID40563
Feature activation+8.45e+00

Pos logit contributions
poke+0.055
horse+0.052
plate+0.050
 Hawth+0.047
 Trafford+0.047
Neg logit contributions
 tremend-0.091
 streng-0.081
aughs-0.079
utical-0.077
 Libre-0.073
Tokenoles
Token ID4316
Feature activation+7.68e-01

Pos logit contributions
 tremend+6.725
aughs+6.015
 streng+5.969
utical+5.899
 Libre+5.726
Neg logit contributions
poke-7.005
horse-6.763
plate-6.478
 Trafford-6.257
 Hawth-6.219
Token while
Token ID981
Feature activation+5.16e-01

Pos logit contributions
 tremend+0.790
 streng+0.702
aughs+0.681
utical+0.671
 Libre+0.647
Neg logit contributions
poke-0.524
horse-0.502
plate-0.478
 Trafford-0.449
 Hawth-0.447
Token another
Token ID1194
Feature activation-7.52e-01

Pos logit contributions
 tremend+0.510
 streng+0.450
aughs+0.439
utical+0.430
 Libre+0.410
Neg logit contributions
poke-0.375
horse-0.362
plate-0.345
 Hawth-0.327
 Trafford-0.327
Token is
Token ID318
Feature activation-1.54e-01

Pos logit contributions
poke+0.507
horse+0.490
plate+0.463
 Hawth+0.442
 Trafford+0.437
Neg logit contributions
 tremend-0.785
 streng-0.695
aughs-0.687
utical-0.667
 Libre-0.632
Token off
Token ID572
Feature activation-7.73e-01

Pos logit contributions
poke+0.109
horse+0.107
plate+0.102
 Hawth+0.097
 Trafford+0.096
Neg logit contributions
 tremend-0.154
 streng-0.135
aughs-0.135
utical-0.131
 Libre-0.123
Token Korean
Token ID6983
Feature activation+3.16e+00

Pos logit contributions
 tremend+1.348
 streng+1.193
aughs+1.157
utical+1.141
 Libre+1.101
Neg logit contributions
poke-0.940
horse-0.903
plate-0.859
 Trafford-0.812
 Hawth-0.808
Token state
Token ID1181
Feature activation+1.61e+00

Pos logit contributions
 tremend+2.636
 streng+2.273
aughs+2.195
utical+2.147
 Libre+2.038
Neg logit contributions
poke-2.777
horse-2.690
plate-2.595
 Trafford-2.474
 Hawth-2.469
Token.
Token ID13
Feature activation+4.07e-01

Pos logit contributions
 tremend+1.605
 streng+1.420
aughs+1.376
utical+1.359
 Libre+1.309
Neg logit contributions
poke-1.141
horse-1.090
plate-1.038
 Trafford-0.985
 Hawth-0.979
Token The
Token ID383
Feature activation-8.42e-02

Pos logit contributions
 tremend+0.401
 streng+0.347
aughs+0.330
utical+0.323
 toget+0.307
Neg logit contributions
poke-0.314
horse-0.304
plate-0.290
 Hawth-0.279
 Trafford-0.278
Token only
Token ID691
Feature activation-1.67e-01

Pos logit contributions
poke+0.065
horse+0.063
plate+0.060
 Hawth+0.058
 Trafford+0.057
Neg logit contributions
 tremend-0.079
 streng-0.069
aughs-0.068
utical-0.066
 Libre-0.063
Token recognizable
Token ID30264
Feature activation+8.31e+00

Pos logit contributions
poke+0.130
horse+0.125
plate+0.121
 Hawth+0.115
 Trafford+0.114
Neg logit contributions
 tremend-0.158
 streng-0.137
aughs-0.134
utical-0.131
 Libre-0.123
Token special
Token ID2041
Feature activation+1.19e-01

Pos logit contributions
 tremend+7.248
 streng+6.551
aughs+6.234
 Libre+6.107
utical+6.082
Neg logit contributions
poke-6.350
horse-6.125
plate-5.817
fleet-5.631
 Trafford-5.517
Token restriction
Token ID17504
Feature activation+2.10e+00

Pos logit contributions
 tremend+0.109
 streng+0.095
aughs+0.092
utical+0.091
 Libre+0.086
Neg logit contributions
poke-0.095
horse-0.092
plate-0.089
 Trafford-0.084
 Hawth-0.084
Token American
Token ID1605
Feature activation+1.27e+00

Pos logit contributions
 tremend+2.179
 streng+1.936
aughs+1.881
utical+1.849
 Libre+1.781
Neg logit contributions
poke-1.420
horse-1.364
plate-1.303
 Trafford-1.217
 Hawth-1.215
Token tourists
Token ID15930
Feature activation+1.76e+00

Pos logit contributions
 tremend+1.249
 streng+1.100
aughs+1.069
utical+1.052
 Libre+1.005
Neg logit contributions
poke-0.928
horse-0.892
plate-0.859
 Trafford-0.810
 Hawth-0.808
Token receive
Token ID3328
Feature activation+1.77e+00

Pos logit contributions
 tremend+1.642
 streng+1.433
aughs+1.390
utical+1.365
 Libre+1.303
Neg logit contributions
poke-1.383
horse-1.331
plate-1.286
 Hawth-1.215
 Trafford-1.207
Token.
Token ID13
Feature activation+2.44e-01

Pos logit contributions
 tremend+1.413
 streng+1.251
aughs+1.218
utical+1.197
 Libre+1.149
Neg logit contributions
poke-0.966
horse-0.928
plate-0.886
 Trafford-0.832
 Hawth-0.830
Token
Token ID198
Feature activation+2.11e-02

Pos logit contributions
 tremend+0.211
 streng+0.185
aughs+0.181
utical+0.178
 Libre+0.171
Neg logit contributions
poke-0.203
horse-0.195
plate-0.187
 Trafford-0.178
 Hawth-0.177
Token
Token ID198
Feature activation+2.08e-02

Pos logit contributions
 tremend+0.021
 streng+0.018
aughs+0.017
utical+0.017
 toget+0.016
Neg logit contributions
poke-0.016
horse-0.016
plate-0.015
 Hawth-0.014
 Trafford-0.014
TokenGermany
Token ID27079
Feature activation+2.35e+00

Pos logit contributions
 tremend+0.019
 streng+0.017
aughs+0.016
utical+0.015
 Libre+0.015
Neg logit contributions
poke-0.017
horse-0.017
plate-0.016
fleet-0.015
grid-0.015
Token's
Token ID338
Feature activation+2.17e+00

Pos logit contributions
 tremend+2.302
 streng+2.025
aughs+1.967
utical+1.931
 Libre+1.853
Neg logit contributions
poke-1.736
horse-1.671
plate-1.599
 Trafford-1.509
 Hawth-1.505
Token Bayer
Token ID48009
Feature activation+8.28e+00

Pos logit contributions
 tremend+1.995
 streng+1.741
aughs+1.693
utical+1.659
 Libre+1.580
Neg logit contributions
poke-1.722
horse-1.661
plate-1.594
 Trafford-1.516
 Hawth-1.514
Token had
Token ID550
Feature activation+1.46e+00

Pos logit contributions
 tremend+7.713
 streng+7.002
aughs+6.623
utical+6.602
 Libre+6.386
Neg logit contributions
poke-5.972
horse-5.701
plate-5.565
 Trafford-5.186
fleet-5.123
Token its
Token ID663
Feature activation+2.38e+00

Pos logit contributions
 tremend+1.396
 streng+1.218
aughs+1.189
utical+1.165
 Libre+1.110
Neg logit contributions
poke-1.113
horse-1.075
plate-1.034
 Hawth-0.974
 Trafford-0.971
Token 200
Token ID939
Feature activation+1.16e+00

Pos logit contributions
 tremend+2.184
 streng+1.907
aughs+1.854
utical+1.817
 Libre+1.730
Neg logit contributions
poke-1.893
horse-1.824
plate-1.755
 Trafford-1.663
 Hawth-1.662
Tokenm
Token ID76
Feature activation-2.21e+00

Pos logit contributions
 tremend+1.158
 streng+1.025
aughs+0.994
utical+0.978
 Libre+0.941
Neg logit contributions
poke-0.824
horse-0.792
plate-0.756
 Trafford-0.713
 Hawth-0.710
Token euro
Token ID11063
Feature activation+3.16e+00

Pos logit contributions
poke+1.748
horse+1.694
plate+1.626
 Hawth+1.532
grid+1.528
Neg logit contributions
 tremend-2.015
 streng-1.745
aughs-1.717
utical-1.680
 Libre-1.595
Token Europe
Token ID2031
Feature activation+2.16e+00

Pos logit contributions
 tremend+1.538
 streng+1.340
aughs+1.301
utical+1.272
 Libre+1.212
Neg logit contributions
poke-1.374
horse-1.327
plate-1.274
 Trafford-1.209
 Hawth-1.208
Token Russian
Token ID3394
Feature activation+2.17e+00

Pos logit contributions
 tremend+2.245
 streng+1.999
aughs+1.942
utical+1.916
 Libre+1.851
Neg logit contributions
poke-1.449
horse-1.383
plate-1.316
 Trafford-1.242
 Hawth-1.234
Token state
Token ID1181
Feature activation+2.81e+00

Pos logit contributions
 tremend+2.068
 streng+1.818
aughs+1.762
utical+1.731
 Libre+1.658
Neg logit contributions
poke-1.653
horse-1.593
plate-1.527
 Trafford-1.444
 Hawth-1.439
Token energy
Token ID2568
Feature activation-1.56e-02

Pos logit contributions
 tremend+2.442
 streng+2.122
aughs+2.043
utical+2.018
 Libre+1.936
Neg logit contributions
poke-2.359
horse-2.266
plate-2.187
 Trafford-2.089
 Hawth-2.082
Token company
Token ID1664
Feature activation+1.43e+00

Pos logit contributions
poke+0.012
horse+0.011
plate+0.011
 Hawth+0.010
 Trafford+0.010
Neg logit contributions
 tremend-0.015
 streng-0.013
aughs-0.013
utical-0.012
 Libre-0.012
Token Gaz
Token ID21347
Feature activation+8.26e+00

Pos logit contributions
 tremend+1.003
 streng+0.838
aughs+0.802
utical+0.779
 Libre+0.732
Neg logit contributions
poke-1.446
horse-1.408
plate-1.364
 Trafford-1.309
 Hawth-1.307
Tokenprom
Token ID16963
Feature activation+1.81e+00

Pos logit contributions
 tremend+7.097
 streng+6.198
aughs+6.072
utical+6.030
 Libre+5.893
Neg logit contributions
poke-6.212
horse-5.985
plate-5.950
 Trafford-5.832
 Hawth-5.720
Token has
Token ID468
Feature activation+2.26e-01

Pos logit contributions
 tremend+1.835
 streng+1.628
aughs+1.580
utical+1.555
 Libre+1.496
Neg logit contributions
poke-1.266
horse-1.215
plate-1.159
 Trafford-1.092
 Hawth-1.087
Token resumed
Token ID28291
Feature activation+3.68e+00

Pos logit contributions
 tremend+0.227
 streng+0.199
aughs+0.195
utical+0.191
 Libre+0.183
Neg logit contributions
poke-0.161
horse-0.155
plate-0.149
 Hawth-0.139
 Trafford-0.139
Token some
Token ID617
Feature activation+2.36e+00

Pos logit contributions
 tremend+3.278
 streng+2.878
aughs+2.738
utical+2.731
 Libre+2.624
Neg logit contributions
poke-2.964
horse-2.861
plate-2.750
 Trafford-2.622
fleet-2.605
Token gas
Token ID3623
Feature activation+2.94e+00

Pos logit contributions
 tremend+2.168
 streng+1.898
aughs+1.834
utical+1.802
 Libre+1.727
Neg logit contributions
poke-1.874
horse-1.807
plate-1.734
 Trafford-1.646
 Hawth-1.641
Token Russian
Token ID3394
Feature activation+2.53e+00

Pos logit contributions
 tremend+0.328
 streng+0.285
aughs+0.275
utical+0.269
 Libre+0.256
Neg logit contributions
poke-0.286
horse-0.277
plate-0.265
 Trafford-0.252
 Hawth-0.252
Token TV
Token ID3195
Feature activation+5.85e+00

Pos logit contributions
 tremend+2.262
 streng+1.977
aughs+1.904
utical+1.870
 Libre+1.798
Neg logit contributions
poke-2.066
horse-1.993
plate-1.912
 Trafford-1.819
 Hawth-1.813
Token stations
Token ID8985
Feature activation-4.59e-01

Pos logit contributions
 tremend+5.452
 streng+4.853
aughs+4.710
utical+4.563
 Libre+4.511
Neg logit contributions
poke-4.302
horse-4.124
plate-4.004
 Hawth-3.801
 Trafford-3.795
Token showed
Token ID3751
Feature activation+2.38e+00

Pos logit contributions
poke+0.325
horse+0.311
plate+0.296
 Trafford+0.278
 Hawth+0.278
Neg logit contributions
 tremend-0.469
 streng-0.411
aughs-0.400
utical-0.395
 Libre-0.373
Token a
Token ID257
Feature activation+5.66e-01

Pos logit contributions
 tremend+2.185
 streng+1.916
aughs+1.851
utical+1.818
 Libre+1.752
Neg logit contributions
poke-1.880
horse-1.810
plate-1.737
 Trafford-1.648
 Hawth-1.641
Token Gaz
Token ID21347
Feature activation+8.24e+00

Pos logit contributions
 tremend+0.542
 streng+0.476
aughs+0.465
utical+0.456
 Libre+0.430
Neg logit contributions
poke-0.431
horse-0.416
plate-0.400
 Hawth-0.377
 Trafford-0.375
Tokenprom
Token ID16963
Feature activation+1.75e+00

Pos logit contributions
 tremend+7.249
 streng+6.396
utical+6.275
aughs+6.210
 Libre+6.100
Neg logit contributions
poke-5.970
horse-5.756
plate-5.558
 Hawth-5.477
 Trafford-5.441
Token official
Token ID1743
Feature activation+8.95e-01

Pos logit contributions
 tremend+1.801
 streng+1.601
aughs+1.556
utical+1.531
 Libre+1.473
Neg logit contributions
poke-1.190
horse-1.141
plate-1.088
 Trafford-1.021
 Hawth-1.018
Token ordering
Token ID16216
Feature activation-1.57e+00

Pos logit contributions
 tremend+0.932
 streng+0.828
aughs+0.807
utical+0.794
 Libre+0.762
Neg logit contributions
poke-0.602
horse-0.578
plate-0.552
 Trafford-0.515
 Hawth-0.515
Token a
Token ID257
Feature activation+5.75e-01

Pos logit contributions
poke+1.171
horse+1.137
plate+1.088
 Hawth+1.022
 Trafford+1.022
Neg logit contributions
 tremend-1.536
 streng-1.340
aughs-1.313
utical-1.277
 Libre-1.206
Token res
Token ID581
Feature activation+4.99e+00

Pos logit contributions
 tremend+0.545
 streng+0.478
aughs+0.466
utical+0.455
 Libre+0.432
Neg logit contributions
poke-0.444
horse-0.428
plate-0.411
 Hawth-0.388
 Trafford-0.387
Token1
Token ID16
Feature activation+1.89e-01

Pos logit contributions
 tremend+1.786
 streng+1.560
aughs+1.509
utical+1.479
 Libre+1.410
Neg logit contributions
poke-1.532
horse-1.478
plate-1.416
 Hawth-1.340
 Trafford-1.339
Token]
Token ID60
Feature activation+2.06e+00

Pos logit contributions
 tremend+0.177
 streng+0.155
aughs+0.151
utical+0.148
 Libre+0.143
Neg logit contributions
poke-0.145
horse-0.140
plate-0.134
 Trafford-0.128
 Hawth-0.127
Token W
Token ID370
Feature activation+1.05e+00

Pos logit contributions
 tremend+1.897
 streng+1.658
aughs+1.604
utical+1.575
 Libre+1.507
Neg logit contributions
poke-1.633
horse-1.576
plate-1.512
 Trafford-1.435
 Hawth-1.431
TokenEP
Token ID8905
Feature activation+6.48e-01

Pos logit contributions
 tremend+0.983
 streng+0.847
aughs+0.805
utical+0.794
 Libre+0.758
Neg logit contributions
poke-0.859
horse-0.821
plate-0.793
 Trafford-0.747
 Hawth-0.745
Token,
Token ID11
Feature activation+2.54e-01

Pos logit contributions
 tremend+0.656
 streng+0.574
aughs+0.562
utical+0.551
 Libre+0.527
Neg logit contributions
poke-0.459
horse-0.442
plate-0.424
 Hawth-0.395
 Trafford-0.394
Token recognizable
Token ID30264
Feature activation+8.11e+00

Pos logit contributions
 tremend+0.256
 streng+0.224
aughs+0.220
utical+0.216
 Libre+0.205
Neg logit contributions
poke-0.181
horse-0.174
plate-0.167
 Hawth-0.157
 Trafford-0.157
Token by
Token ID416
Feature activation+1.69e+00

Pos logit contributions
 tremend+7.400
 streng+6.613
aughs+6.281
utical+6.263
 Libre+6.156
Neg logit contributions
poke-6.062
horse-5.767
plate-5.481
 Trafford-5.240
fleet-5.236
Token its
Token ID663
Feature activation+2.29e+00

Pos logit contributions
 tremend+1.514
 streng+1.320
aughs+1.275
utical+1.251
 Libre+1.197
Neg logit contributions
poke-1.388
horse-1.341
plate-1.288
 Trafford-1.224
 Hawth-1.220
Token key
Token ID1994
Feature activation+2.20e+00

Pos logit contributions
 tremend+2.083
 streng+1.815
aughs+1.763
utical+1.730
 Libre+1.646
Neg logit contributions
poke-1.847
horse-1.784
plate-1.717
 Trafford-1.629
 Hawth-1.627
Token of
Token ID286
Feature activation+4.70e-01

Pos logit contributions
 tremend+1.970
 streng+1.711
aughs+1.655
utical+1.628
 Libre+1.548
Neg logit contributions
poke-1.811
horse-1.749
plate-1.690
 Trafford-1.596
 Hawth-1.592
Token 10
Token ID838
Feature activation+1.16e+00

Pos logit contributions
 tremend+0.450
 streng+0.394
aughs+0.384
utical+0.378
 Libre+0.359
Neg logit contributions
poke-0.357
horse-0.343
plate-0.330
 Hawth-0.312
 Trafford-0.312
Token/
Token ID14
Feature activation+5.51e-01

Pos logit contributions
 tremend+0.312
 streng+0.277
aughs+0.268
utical+0.263
 Libre+0.253
Neg logit contributions
poke-0.177
horse-0.169
plate-0.161
 Hawth-0.149
 Trafford-0.149
Tokent
Token ID83
Feature activation-2.20e+00

Pos logit contributions
 tremend+0.548
 streng+0.483
aughs+0.468
utical+0.458
 Libre+0.441
Neg logit contributions
poke-0.404
horse-0.388
plate-0.372
 Trafford-0.346
fleet-0.345
Tokenatt
Token ID1078
Feature activation-2.15e+00

Pos logit contributions
poke+1.149
horse+1.081
plate+1.024
 Trafford+0.921
 Hawth+0.920
Neg logit contributions
 tremend-2.652
 streng-2.386
aughs-2.308
utical-2.275
 Libre-2.210
Tokenoo
Token ID2238
Feature activation+3.95e-01

Pos logit contributions
poke+2.002
horse+1.935
plate+1.879
 Trafford+1.784
 Hawth+1.779
Neg logit contributions
 tremend-1.688
 streng-1.436
aughs-1.367
utical-1.336
 Libre-1.268
Token-
Token ID12
Feature activation+3.19e-01

Pos logit contributions
 tremend+0.369
 streng+0.324
aughs+0.315
utical+0.310
 Libre+0.297
Neg logit contributions
poke-0.305
horse-0.293
plate-0.280
 Trafford-0.268
 Hawth-0.267
Tokenrecogn
Token ID26243
Feature activation+8.10e+00

Pos logit contributions
 tremend+0.296
 streng+0.259
aughs+0.250
utical+0.245
 Libre+0.234
Neg logit contributions
poke-0.254
horse-0.245
plate-0.236
 Trafford-0.221
fleet-0.221
Tokenition
Token ID653
Feature activation+3.07e+00

Pos logit contributions
 tremend+2.153
 streng+1.531
utical+1.494
aughs+1.453
 Libre+1.102
Neg logit contributions
poke-10.811
horse-10.595
plate-10.355
 Hawth-10.221
 Trafford-10.199
Token-
Token ID12
Feature activation+8.94e-01

Pos logit contributions
 tremend+2.631
 streng+2.320
aughs+2.274
utical+2.254
 Libre+2.146
Neg logit contributions
poke-2.502
horse-2.394
plate-2.273
 Trafford-2.244
 Hawth-2.215
Tokenresearch
Token ID34033
Feature activation-1.79e+00

Pos logit contributions
 tremend+0.890
 streng+0.787
aughs+0.763
utical+0.750
 Libre+0.721
Neg logit contributions
poke-0.642
horse-0.618
plate-0.590
 Trafford-0.555
 Hawth-0.554
Token-
Token ID12
Feature activation+9.32e-01

Pos logit contributions
poke+1.314
horse+1.265
plate+1.210
 Trafford+1.142
 Hawth+1.138
Neg logit contributions
 tremend-1.745
 streng-1.540
aughs-1.492
utical-1.467
 Libre-1.409
Tokenthreat
Token ID19971
Feature activation-2.86e+00

Pos logit contributions
 tremend+0.908
 streng+0.802
aughs+0.777
utical+0.764
 Libre+0.734
Neg logit contributions
poke-0.687
horse-0.661
plate-0.633
 Trafford-0.598
 Hawth-0.596
Token are
Token ID389
Feature activation-9.54e-01

Pos logit contributions
 tremend+0.304
 streng+0.270
aughs+0.264
utical+0.258
 Libre+0.248
Neg logit contributions
poke-0.192
horse-0.186
plate-0.176
 Hawth-0.166
 Trafford-0.165
Token,
Token ID11
Feature activation+1.76e-01

Pos logit contributions
poke+0.608
horse+0.590
plate+0.559
 Hawth+0.523
 Trafford+0.520
Neg logit contributions
 tremend-1.027
 streng-0.911
aughs-0.894
utical-0.877
 Libre-0.842
Token and
Token ID290
Feature activation+3.09e-01

Pos logit contributions
 tremend+0.180
 streng+0.159
aughs+0.155
utical+0.152
 Libre+0.146
Neg logit contributions
poke-0.121
horse-0.117
plate-0.112
 Hawth-0.105
 Trafford-0.105
Token what
Token ID644
Feature activation+2.37e+00

Pos logit contributions
 tremend+0.321
 streng+0.284
aughs+0.279
utical+0.272
 Libre+0.258
Neg logit contributions
poke-0.210
horse-0.202
plate-0.193
 Hawth-0.184
 Trafford-0.181
Token the
Token ID262
Feature activation+2.74e-01

Pos logit contributions
 tremend+2.314
 streng+2.035
aughs+1.983
utical+1.947
 Libre+1.861
Neg logit contributions
poke-1.744
horse-1.681
plate-1.609
 Trafford-1.518
 Hawth-1.517
Token Semin
Token ID40563
Feature activation+8.09e+00

Pos logit contributions
 tremend+0.265
 streng+0.231
aughs+0.228
utical+0.222
 Libre+0.208
Neg logit contributions
poke-0.206
horse-0.200
plate-0.191
 Hawth-0.182
 Trafford-0.180
Tokenoles
Token ID4316
Feature activation+6.76e-01

Pos logit contributions
 tremend+6.397
aughs+5.811
utical+5.715
 streng+5.660
 Libre+5.435
Neg logit contributions
poke-6.661
horse-6.481
plate-6.171
 Trafford-6.027
 Hawth-5.992
Token chances
Token ID8395
Feature activation+8.31e-01

Pos logit contributions
 tremend+0.671
 streng+0.590
aughs+0.576
utical+0.563
 Libre+0.536
Neg logit contributions
poke-0.492
horse-0.474
plate-0.455
 Hawth-0.430
 Trafford-0.427
Token are
Token ID389
Feature activation-6.81e-01

Pos logit contributions
 tremend+0.819
 streng+0.724
aughs+0.702
utical+0.690
 Libre+0.663
Neg logit contributions
poke-0.605
horse-0.582
plate-0.556
 Trafford-0.525
 Hawth-0.523
Token.
Token ID13
Feature activation+2.45e-01

Pos logit contributions
poke+0.465
horse+0.451
plate+0.431
 Hawth+0.404
 Trafford+0.400
Neg logit contributions
 tremend-0.705
 streng-0.622
aughs-0.608
utical-0.598
 Libre-0.570
Token
Token ID198
Feature activation-4.58e-02

Pos logit contributions
 tremend+0.215
 streng+0.188
aughs+0.183
utical+0.180
 Libre+0.174
Neg logit contributions
poke-0.202
horse-0.195
plate-0.188
 Trafford-0.178
fleet-0.176
Token tobacco
Token ID11219
Feature activation+2.64e+00

Pos logit contributions
 tremend+0.053
 streng+0.046
aughs+0.044
utical+0.043
 Libre+0.040
Neg logit contributions
poke-0.056
horse-0.054
plate-0.052
 Hawth-0.050
 Trafford-0.050
Token "
Token ID366
Feature activation+9.95e-01

Pos logit contributions
 tremend+2.588
 streng+2.288
aughs+2.217
utical+2.187
 Libre+2.100
Neg logit contributions
poke-1.920
horse-1.843
plate-1.759
 Trafford-1.668
 Hawth-1.658
Tokenover
Token ID2502
Feature activation+1.12e+00

Pos logit contributions
 tremend+1.005
 streng+0.891
aughs+0.865
utical+0.850
 Libre+0.818
Neg logit contributions
poke-0.698
horse-0.670
plate-0.640
 Trafford-0.603
 Hawth-0.601
Tokenwhelming
Token ID36433
Feature activation+2.37e+00

Pos logit contributions
 tremend+1.069
 streng+0.941
aughs+0.912
utical+0.894
 Libre+0.858
Neg logit contributions
poke-0.861
horse-0.830
plate-0.795
 Trafford-0.748
 Hawth-0.747
Token."
Token ID526
Feature activation+1.59e+00

Pos logit contributions
 tremend+2.264
 streng+1.981
aughs+1.914
utical+1.886
 Libre+1.815
Neg logit contributions
poke-1.791
horse-1.714
plate-1.641
 Trafford-1.566
 Hawth-1.557
Token Cig
Token ID32616
Feature activation+8.07e+00

Pos logit contributions
 tremend+1.456
 streng+1.276
aughs+1.239
utical+1.217
 Libre+1.167
Neg logit contributions
poke-1.262
horse-1.218
plate-1.169
 Trafford-1.107
 Hawth-1.103
Tokenarettes
Token ID13890
Feature activation+2.64e+00

Pos logit contributions
 tremend+4.523
 streng+3.591
aughs+3.568
utical+3.510
 Libre+3.260
Neg logit contributions
poke-8.944
horse-8.685
plate-8.421
 Trafford-8.195
 Hawth-8.169
Token are
Token ID389
Feature activation-6.76e-01

Pos logit contributions
 tremend+2.591
 streng+2.287
aughs+2.219
utical+2.180
 Libre+2.093
Neg logit contributions
poke-1.935
horse-1.863
plate-1.781
 Trafford-1.681
 Hawth-1.678
Token "
Token ID366
Feature activation+1.41e+00

Pos logit contributions
poke+0.483
horse+0.477
plate+0.451
 Hawth+0.433
 Trafford+0.422
Neg logit contributions
 tremend-0.671
 streng-0.588
aughs-0.577
utical-0.561
 Libre-0.536
Tokenthe
Token ID1169
Feature activation-8.76e-01

Pos logit contributions
 tremend+1.366
 streng+1.204
aughs+1.167
utical+1.146
 Libre+1.101
Neg logit contributions
poke-1.055
horse-1.017
plate-0.973
 Trafford-0.916
 Hawth-0.913
Token only
Token ID691
Feature activation-6.39e-01

Pos logit contributions
poke+0.705
horse+0.684
plate+0.650
 Hawth+0.630
 Trafford+0.628
Neg logit contributions
 tremend-0.798
 streng-0.695
aughs-0.678
utical-0.661
 Libre-0.621
Token June
Token ID2795
Feature activation+6.76e-01

Pos logit contributions
 tremend+1.812
 streng+1.607
aughs+1.564
utical+1.533
 Libre+1.476
Neg logit contributions
poke-1.175
horse-1.127
plate-1.077
 Trafford-1.009
 Hawth-1.005
Token 2007
Token ID4343
Feature activation+2.11e+00

Pos logit contributions
 tremend+0.639
 streng+0.558
aughs+0.540
utical+0.529
 Libre+0.501
Neg logit contributions
poke-0.526
horse-0.509
plate-0.491
 Trafford-0.463
 Hawth-0.462
Token,
Token ID11
Feature activation-9.50e-02

Pos logit contributions
 tremend+2.127
 streng+1.893
aughs+1.834
utical+1.810
 Libre+1.751
Neg logit contributions
poke-1.469
horse-1.407
plate-1.335
 Trafford-1.259
 Hawth-1.255
Token Singapore
Token ID12551
Feature activation+2.31e+00

Pos logit contributions
poke+0.069
horse+0.067
plate+0.064
 Trafford+0.060
 Hawth+0.060
Neg logit contributions
 tremend-0.094
 streng-0.082
aughs-0.080
utical-0.079
 Libre-0.075
Token and
Token ID290
Feature activation+1.30e-02

Pos logit contributions
 tremend+2.174
 streng+1.899
aughs+1.845
utical+1.807
 Libre+1.722
Neg logit contributions
poke-1.797
horse-1.730
plate-1.662
 Trafford-1.568
 Hawth-1.566
Token Brune
Token ID46070
Feature activation+8.07e+00

Pos logit contributions
 tremend+0.013
 streng+0.011
aughs+0.011
utical+0.011
 Libre+0.010
Neg logit contributions
poke-0.010
horse-0.009
plate-0.009
 Hawth-0.009
 Trafford-0.008
Tokeni
Token ID72
Feature activation+1.06e+00

Pos logit contributions
 tremend+4.919
 streng+4.222
utical+4.221
aughs+4.207
 Libre+3.898
Neg logit contributions
poke-8.044
horse-7.891
plate-7.684
 Trafford-7.451
fleet-7.287
Token celebrated
Token ID13943
Feature activation+1.70e+00

Pos logit contributions
 tremend+1.031
 streng+0.899
aughs+0.875
utical+0.854
 Libre+0.812
Neg logit contributions
poke-0.802
horse-0.768
plate-0.746
 Hawth-0.698
 Trafford-0.697
Token the
Token ID262
Feature activation-2.31e-02

Pos logit contributions
 tremend+1.630
 streng+1.434
aughs+1.390
utical+1.364
 Libre+1.307
Neg logit contributions
poke-1.283
horse-1.235
plate-1.184
 Trafford-1.119
 Hawth-1.117
Token 40
Token ID2319
Feature activation+1.76e+00

Pos logit contributions
poke+0.017
horse+0.017
plate+0.016
 Hawth+0.015
 Trafford+0.015
Neg logit contributions
 tremend-0.022
 streng-0.020
aughs-0.019
utical-0.019
 Libre-0.018
Tokenth
Token ID400
Feature activation-2.12e-01

Pos logit contributions
 tremend+1.824
 streng+1.622
aughs+1.575
utical+1.550
 Libre+1.493
Neg logit contributions
poke-1.197
horse-1.148
plate-1.094
 Trafford-1.027
 Hawth-1.023
Token immune
Token ID10900
Feature activation+3.60e+00

Pos logit contributions
 tremend+1.178
 streng+1.019
aughs+0.989
utical+0.964
 Libre+0.920
Neg logit contributions
poke-1.102
horse-1.062
plate-1.028
 Hawth-0.972
 Trafford-0.966
Token system
Token ID1080
Feature activation+1.81e+00

Pos logit contributions
 tremend+2.543
 streng+2.151
aughs+2.037
utical+1.992
 Libre+1.892
Neg logit contributions
poke-3.572
horse-3.486
plate-3.348
 Trafford-3.243
 Hawth-3.226
Token attacks
Token ID3434
Feature activation-1.28e+00

Pos logit contributions
 tremend+1.793
 streng+1.582
aughs+1.534
utical+1.511
 Libre+1.449
Neg logit contributions
poke-1.318
horse-1.266
plate-1.213
 Trafford-1.140
 Hawth-1.138
Token the
Token ID262
Feature activation+6.01e-01

Pos logit contributions
poke+0.911
horse+0.872
plate+0.847
 Hawth+0.788
 Trafford+0.782
Neg logit contributions
 tremend-1.292
 streng-1.143
aughs-1.118
utical-1.096
 Libre-1.032
Token new
Token ID649
Feature activation+1.38e+00

Pos logit contributions
 tremend+0.537
 streng+0.464
aughs+0.455
utical+0.442
 Libre+0.417
Neg logit contributions
poke-0.496
horse-0.479
plate-0.465
 Hawth-0.440
 Trafford-0.438
Token organ
Token ID1618
Feature activation+7.98e+00

Pos logit contributions
 tremend+1.208
 streng+1.042
aughs+1.016
utical+0.989
 Libre+0.936
Neg logit contributions
poke-1.164
horse-1.128
plate-1.093
 Hawth-1.031
 Trafford-1.028
Token,
Token ID11
Feature activation+3.03e-01

Pos logit contributions
 tremend+7.904
 streng+6.996
aughs+6.717
utical+6.692
 Libre+6.487
Neg logit contributions
poke-5.392
horse-5.143
plate-4.747
 Trafford-4.687
 Hawth-4.636
Token with
Token ID351
Feature activation+2.89e+00

Pos logit contributions
 tremend+0.308
 streng+0.272
aughs+0.265
utical+0.260
 Libre+0.249
Neg logit contributions
poke-0.213
horse-0.204
plate-0.196
 Hawth-0.184
 Trafford-0.183
Token graft
Token ID38455
Feature activation+5.09e+00

Pos logit contributions
 tremend+2.744
 streng+2.414
aughs+2.336
utical+2.295
 Libre+2.208
Neg logit contributions
poke-2.195
horse-2.114
plate-2.022
 Trafford-1.917
 Hawth-1.905
Token-
Token ID12
Feature activation+1.44e+00

Pos logit contributions
 tremend+4.823
 streng+4.257
aughs+4.083
utical+4.036
 Libre+3.888
Neg logit contributions
poke-3.823
horse-3.680
plate-3.487
 Trafford-3.357
 Hawth-3.329
Tokenvers
Token ID690
Feature activation-1.27e+00

Pos logit contributions
 tremend+1.378
 streng+1.225
aughs+1.186
utical+1.169
 Libre+1.119
Neg logit contributions
poke-1.052
horse-1.011
plate-0.957
 Hawth-0.935
 Trafford-0.928
Token Ast
Token ID8304
Feature activation-1.26e-01

Pos logit contributions
poke+0.126
horse+0.122
plate+0.116
 Hawth+0.112
 Trafford+0.111
Neg logit contributions
 tremend-0.157
 streng-0.137
aughs-0.134
utical-0.130
 toget-0.122
Tokenur
Token ID333
Feature activation+1.12e+00

Pos logit contributions
poke+0.066
horse+0.063
plate+0.059
 Trafford+0.054
 Hawth+0.054
Neg logit contributions
 tremend-0.149
 streng-0.135
aughs-0.131
utical-0.130
 Libre-0.126
Tokenias
Token ID4448
Feature activation+8.42e-01

Pos logit contributions
 tremend+0.891
 streng+0.763
aughs+0.733
utical+0.717
 Libre+0.680
Neg logit contributions
poke-1.027
horse-0.996
plate-0.961
 Trafford-0.919
 Hawth-0.917
Token,
Token ID11
Feature activation-9.11e-02

Pos logit contributions
 tremend+0.867
 streng+0.767
aughs+0.742
utical+0.738
 Libre+0.718
Neg logit contributions
poke-0.573
horse-0.549
plate-0.524
 Trafford-0.493
 Hawth-0.489
Token the
Token ID262
Feature activation+6.35e-01

Pos logit contributions
poke+0.070
horse+0.068
plate+0.065
 Hawth+0.062
 Trafford+0.062
Neg logit contributions
 tremend-0.087
 streng-0.076
aughs-0.074
utical-0.072
 toget-0.068
Token Bas
Token ID6455
Feature activation+7.96e+00

Pos logit contributions
 tremend+0.613
 streng+0.541
aughs+0.526
utical+0.513
 toget+0.485
Neg logit contributions
poke-0.473
horse-0.457
plate-0.437
 Hawth-0.417
 Trafford-0.416
Tokenque
Token ID4188
Feature activation+2.69e+00

Pos logit contributions
 tremend+5.805
 streng+4.986
aughs+4.974
 Libre+4.779
utical+4.732
Neg logit contributions
poke-7.086
horse-7.052
plate-6.613
 Hawth-6.484
 Trafford-6.395
Token Country
Token ID12946
Feature activation+7.28e-01

Pos logit contributions
 tremend+2.484
 streng+2.177
aughs+2.099
utical+2.063
 Libre+1.956
Neg logit contributions
poke-2.133
horse-2.061
plate-1.975
 Trafford-1.873
 Hawth-1.866
Token,
Token ID11
Feature activation+1.57e-01

Pos logit contributions
 tremend+0.799
 streng+0.717
aughs+0.697
utical+0.686
 Libre+0.661
Neg logit contributions
poke-0.448
horse-0.429
plate-0.406
 Trafford-0.378
 Hawth-0.376
Token the
Token ID262
Feature activation+7.62e-01

Pos logit contributions
 tremend+0.151
 streng+0.132
aughs+0.129
utical+0.126
 Libre+0.118
Neg logit contributions
poke-0.119
horse-0.115
plate-0.110
 Trafford-0.105
 Hawth-0.104
Token Canary
Token ID50206
Feature activation+2.41e+00

Pos logit contributions
 tremend+0.732
 streng+0.642
aughs+0.626
utical+0.612
 toget+0.575
Neg logit contributions
poke-0.575
horse-0.556
plate-0.533
 Trafford-0.509
 Hawth-0.509
Token has
Token ID468
Feature activation+5.90e-01

Pos logit contributions
 tremend+0.644
 streng+0.570
aughs+0.554
utical+0.544
 Libre+0.521
Neg logit contributions
poke-0.434
horse-0.418
plate-0.400
 Hawth-0.374
 Trafford-0.373
Token the
Token ID262
Feature activation+6.96e-01

Pos logit contributions
 tremend+0.555
 streng+0.486
aughs+0.472
utical+0.463
 Libre+0.441
Neg logit contributions
poke-0.456
horse-0.440
plate-0.423
 Hawth-0.400
 Trafford-0.399
Token state
Token ID1181
Feature activation+1.80e+00

Pos logit contributions
 tremend+0.644
 streng+0.561
aughs+0.548
utical+0.535
 Libre+0.508
Neg logit contributions
poke-0.550
horse-0.532
plate-0.513
 Hawth-0.486
 Trafford-0.485
Token title
Token ID3670
Feature activation-4.71e-02

Pos logit contributions
 tremend+1.763
 streng+1.558
aughs+1.502
utical+1.489
 Libre+1.435
Neg logit contributions
poke-1.319
horse-1.258
plate-1.198
 Trafford-1.146
 Hawth-1.138
Token of
Token ID286
Feature activation+1.43e-01

Pos logit contributions
poke+0.033
horse+0.032
plate+0.031
 Trafford+0.029
 Hawth+0.029
Neg logit contributions
 tremend-0.048
 streng-0.042
aughs-0.041
utical-0.040
 Libre-0.038
Token Brune
Token ID46070
Feature activation+7.76e+00

Pos logit contributions
 tremend+0.138
 streng+0.121
aughs+0.118
utical+0.115
 Libre+0.109
Neg logit contributions
poke-0.108
horse-0.104
plate-0.100
 Trafford-0.095
 Hawth-0.095
Tokeni
Token ID72
Feature activation+1.11e+00

Pos logit contributions
 tremend+5.243
 streng+4.441
utical+4.377
aughs+4.254
 Libre+4.142
Neg logit contributions
poke-7.371
horse-7.249
plate-6.960
 Trafford-6.758
grid-6.670
Token in
Token ID287
Feature activation+1.99e-01

Pos logit contributions
 tremend+1.075
 streng+0.946
aughs+0.920
utical+0.901
 Libre+0.853
Neg logit contributions
poke-0.839
horse-0.810
plate-0.779
 Hawth-0.731
 Trafford-0.731
Token Latin
Token ID9133
Feature activation+2.21e+00

Pos logit contributions
 tremend+0.192
 streng+0.169
aughs+0.165
utical+0.162
 Libre+0.153
Neg logit contributions
poke-0.148
horse-0.143
plate-0.137
 Hawth-0.130
 Trafford-0.130
Token script
Token ID4226
Feature activation+1.24e+00

Pos logit contributions
 tremend+2.018
 streng+1.764
aughs+1.702
utical+1.672
 Libre+1.607
Neg logit contributions
poke-1.772
horse-1.711
plate-1.638
 Trafford-1.560
 Hawth-1.552
Token.[
Token ID3693
Feature activation+1.10e+00

Pos logit contributions
 tremend+1.139
 streng+0.998
aughs+0.962
utical+0.948
 Libre+0.917
Neg logit contributions
poke-0.982
horse-0.945
plate-0.902
 Trafford-0.863
 Hawth-0.859
Token
Token ID198
Feature activation-1.23e-01

Pos logit contributions
poke+0.147
horse+0.142
plate+0.136
 Hawth+0.129
 Trafford+0.128
Neg logit contributions
 tremend-0.185
 streng-0.160
aughs-0.152
utical-0.149
 Libre-0.141
TokenF
Token ID37
Feature activation-6.02e-01

Pos logit contributions
poke+0.098
horse+0.094
plate+0.090
 Hawth+0.085
 Trafford+0.085
Neg logit contributions
 tremend-0.116
 streng-0.101
aughs-0.097
utical-0.095
 Libre-0.091
TokenDA
Token ID5631
Feature activation+2.29e+00

Pos logit contributions
poke+0.538
horse+0.526
plate+0.509
 Hawth+0.482
 Trafford+0.479
Neg logit contributions
 tremend-0.495
 streng-0.427
aughs-0.401
utical-0.388
 Libre-0.374
Token Commissioner
Token ID13270
Feature activation+9.98e-01

Pos logit contributions
 tremend+2.257
 streng+2.003
aughs+1.935
utical+1.905
 Libre+1.834
Neg logit contributions
poke-1.659
horse-1.594
plate-1.522
 Trafford-1.436
 Hawth-1.432
Token Scott
Token ID4746
Feature activation-6.52e-01

Pos logit contributions
 tremend+1.082
 streng+0.969
aughs+0.943
utical+0.929
 Libre+0.898
Neg logit contributions
poke-0.624
horse-0.596
plate-0.565
 Trafford-0.527
 Hawth-0.525
Token Gott
Token ID39451
Feature activation+7.67e+00

Pos logit contributions
poke+0.597
horse+0.578
plate+0.558
 Trafford+0.537
 Hawth+0.535
Neg logit contributions
 tremend-0.529
 streng-0.453
aughs-0.429
utical-0.421
 Libre-0.394
Tokenlie
Token ID14485
Feature activation+1.86e-01

Pos logit contributions
 tremend+3.842
 streng+3.104
aughs+2.902
utical+2.797
 Libre+2.540
Neg logit contributions
poke-8.895
horse-8.690
plate-8.472
 Trafford-8.282
 Hawth-8.205
Tokenb
Token ID65
Feature activation+1.10e+00

Pos logit contributions
 tremend+0.169
 streng+0.149
aughs+0.144
utical+0.141
 Libre+0.135
Neg logit contributions
poke-0.148
horse-0.143
plate-0.138
 Trafford-0.131
 Hawth-0.130
Token called
Token ID1444
Feature activation-1.49e+00

Pos logit contributions
 tremend+1.125
 streng+1.003
aughs+0.972
utical+0.957
 Libre+0.922
Neg logit contributions
poke-0.752
horse-0.721
plate-0.686
 Trafford-0.645
 Hawth-0.643
Token the
Token ID262
Feature activation-2.20e-01

Pos logit contributions
poke+1.076
horse+1.035
plate+0.992
 Trafford+0.932
 Hawth+0.932
Neg logit contributions
 tremend-1.485
 streng-1.311
aughs-1.274
utical-1.249
 Libre-1.197
Token amount
Token ID2033
Feature activation+1.82e+00

Pos logit contributions
poke+0.155
horse+0.149
plate+0.143
 Hawth+0.135
 Trafford+0.134
Neg logit contributions
 tremend-0.223
 streng-0.196
aughs-0.192
utical-0.188
 Libre-0.179
Token the
Token ID262
Feature activation+6.81e-01

Pos logit contributions
poke+0.114
horse+0.110
plate+0.105
 Trafford+0.099
 Hawth+0.099
Neg logit contributions
 tremend-0.149
 streng-0.131
aughs-0.127
utical-0.125
 Libre-0.120
Token ob
Token ID909
Feature activation+8.50e-01

Pos logit contributions
 tremend+0.647
 streng+0.567
aughs+0.552
utical+0.541
 Libre+0.516
Neg logit contributions
poke-0.520
horse-0.501
plate-0.483
 Trafford-0.456
 Hawth-0.456
Tokenverse
Token ID4399
Feature activation+1.40e+00

Pos logit contributions
 tremend+1.000
 streng+0.896
aughs+0.859
utical+0.840
 Libre+0.813
Neg logit contributions
poke-0.484
horse-0.471
plate-0.439
grid-0.404
 Hawth-0.401
Token of
Token ID286
Feature activation+1.11e-01

Pos logit contributions
 tremend+1.320
 streng+1.165
aughs+1.123
utical+1.107
 Libre+1.073
Neg logit contributions
poke-1.061
horse-1.012
plate-0.960
 Trafford-0.930
 Hawth-0.917
Token the
Token ID262
Feature activation+4.61e-01

Pos logit contributions
 tremend+0.105
 streng+0.092
aughs+0.089
utical+0.088
 Libre+0.085
Neg logit contributions
poke-0.084
horse-0.081
plate-0.078
 Trafford-0.074
 Hawth-0.073
Token Brune
Token ID46070
Feature activation+7.65e+00

Pos logit contributions
 tremend+0.453
 streng+0.399
aughs+0.388
utical+0.380
 Libre+0.363
Neg logit contributions
poke-0.338
horse-0.326
plate-0.313
 Trafford-0.295
 Hawth-0.295
Tokeni
Token ID72
Feature activation+9.14e-01

Pos logit contributions
 tremend+4.764
utical+4.092
aughs+4.048
 streng+4.041
 Libre+3.810
Neg logit contributions
poke-7.634
horse-7.471
plate-7.179
 Trafford-7.004
 Hawth-6.913
Token version
Token ID2196
Feature activation+3.47e-01

Pos logit contributions
 tremend+0.589
 streng+0.483
aughs+0.460
utical+0.446
 Libre+0.414
Neg logit contributions
poke-0.978
horse-0.952
plate-0.927
 Trafford-0.889
 Hawth-0.888
Token is
Token ID318
Feature activation+7.17e-01

Pos logit contributions
 tremend+0.357
 streng+0.317
aughs+0.308
utical+0.303
 Libre+0.291
Neg logit contributions
poke-0.237
horse-0.228
plate-0.218
 Trafford-0.204
 Hawth-0.203
Token similar
Token ID2092
Feature activation-1.30e-01

Pos logit contributions
 tremend+0.678
 streng+0.595
aughs+0.578
utical+0.567
 Libre+0.542
Neg logit contributions
poke-0.550
horse-0.530
plate-0.510
 Trafford-0.481
 Hawth-0.480
Token to
Token ID284
Feature activation+1.51e-01

Pos logit contributions
poke+0.094
horse+0.089
plate+0.085
 Trafford+0.082
fleet+0.081
Neg logit contributions
 tremend-0.130
 streng-0.115
aughs-0.110
utical-0.109
 Libre-0.106
Token He
Token ID679
Feature activation-4.71e-01

Pos logit contributions
poke+0.326
horse+0.315
plate+0.301
 Trafford+0.285
 Hawth+0.285
Neg logit contributions
 tremend-0.427
 streng-0.376
aughs-0.362
utical-0.357
 Libre-0.342
Tokenyn
Token ID2047
Feature activation+1.01e+00

Pos logit contributions
poke+0.360
horse+0.347
plate+0.332
 Trafford+0.314
 Hawth+0.313
Neg logit contributions
 tremend-0.447
 streng-0.393
aughs-0.379
utical-0.373
 Libre-0.358
Token went
Token ID1816
Feature activation+1.53e-01

Pos logit contributions
 tremend+0.962
 streng+0.842
aughs+0.811
utical+0.800
 Libre+0.769
Neg logit contributions
poke-0.778
horse-0.750
plate-0.719
 Trafford-0.678
 Hawth-0.677
Token to
Token ID284
Feature activation-9.72e-01

Pos logit contributions
 tremend+0.159
 streng+0.142
aughs+0.138
utical+0.135
 Libre+0.130
Neg logit contributions
poke-0.103
horse-0.099
plate-0.094
 Hawth-0.088
 Trafford-0.088
Token a
Token ID257
Feature activation-3.01e-01

Pos logit contributions
poke+0.684
horse+0.652
plate+0.619
 Hawth+0.594
 Trafford+0.589
Neg logit contributions
 tremend-0.982
 streng-0.879
aughs-0.845
utical-0.836
 Libre-0.790
Token Jud
Token ID4794
Feature activation+7.62e+00

Pos logit contributions
poke+0.233
horse+0.224
plate+0.216
 Hawth+0.206
 Trafford+0.205
Neg logit contributions
 tremend-0.284
 streng-0.249
aughs-0.241
utical-0.239
 Libre-0.224
Tokenas
Token ID292
Feature activation+1.67e-01

Pos logit contributions
 tremend+8.209
 streng+7.434
aughs+7.263
utical+7.152
 Libre+6.920
Neg logit contributions
poke-4.364
horse-4.235
plate-4.029
 Trafford-3.772
fleet-3.748
Token Priest
Token ID20876
Feature activation+3.12e+00

Pos logit contributions
 tremend+0.154
 streng+0.135
aughs+0.131
utical+0.129
 Libre+0.122
Neg logit contributions
poke-0.132
horse-0.128
plate-0.122
 Hawth-0.116
 Trafford-0.116
Token concert
Token ID10010
Feature activation+2.61e+00

Pos logit contributions
 tremend+2.791
 streng+2.436
aughs+2.352
utical+2.306
 Libre+2.213
Neg logit contributions
poke-2.545
horse-2.456
plate-2.359
 Trafford-2.241
 Hawth-2.229
Token in
Token ID287
Feature activation-4.88e-01

Pos logit contributions
 tremend+2.728
 streng+2.429
aughs+2.360
utical+2.323
 Libre+2.243
Neg logit contributions
poke-1.740
horse-1.665
plate-1.585
 Trafford-1.486
 Hawth-1.480
Token Land
Token ID6379
Feature activation-1.24e+00

Pos logit contributions
poke+0.332
horse+0.319
plate+0.302
 Hawth+0.290
 Trafford+0.288
Neg logit contributions
 tremend-0.508
 streng-0.451
aughs-0.436
utical-0.431
 Libre-0.409
Token.
Token ID13
Feature activation-8.23e-02

Pos logit contributions
 tremend+2.785
 streng+2.452
aughs+2.393
utical+2.360
 Libre+2.268
Neg logit contributions
poke-2.127
horse-2.030
plate-1.942
 Trafford-1.849
 Hawth-1.827
Token Sac
Token ID9295
Feature activation+3.38e+00

Pos logit contributions
poke+0.063
horse+0.061
plate+0.059
 Hawth+0.056
 Trafford+0.056
Neg logit contributions
 tremend-0.078
 streng-0.069
aughs-0.066
utical-0.065
 Libre-0.062
Tokenram
Token ID859
Feature activation+2.94e+00

Pos logit contributions
 tremend+2.692
 streng+2.286
aughs+2.224
utical+2.209
 Libre+2.081
Neg logit contributions
poke-3.058
horse-2.961
plate-2.842
 Trafford-2.739
 Hawth-2.724
Tokenents
Token ID658
Feature activation+1.85e+00

Pos logit contributions
 tremend+2.511
 streng+2.186
aughs+2.131
utical+2.120
 Libre+2.000
Neg logit contributions
poke-2.472
horse-2.402
plate-2.279
 Trafford-2.198
 Hawth-2.187
Token.
Token ID13
Feature activation+5.75e-02

Pos logit contributions
 tremend+1.806
 streng+1.593
aughs+1.543
utical+1.538
 Libre+1.473
Neg logit contributions
poke-1.366
horse-1.297
plate-1.235
 Trafford-1.183
 Hawth-1.168
Token Bapt
Token ID18226
Feature activation+7.60e+00

Pos logit contributions
 tremend+0.054
 streng+0.047
aughs+0.046
utical+0.045
 Libre+0.043
Neg logit contributions
poke-0.045
horse-0.043
plate-0.041
 Trafford-0.039
 Hawth-0.039
Tokenism
Token ID1042
Feature activation+1.92e+00

Pos logit contributions
 tremend+6.985
utical+6.324
 streng+6.252
aughs+6.244
 Libre+5.888
Neg logit contributions
poke-5.420
horse-5.230
plate-4.972
 Trafford-4.791
 Hawth-4.737
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
 tremend+1.845
 streng+1.627
aughs+1.590
utical+1.583
 Libre+1.519
Neg logit contributions
poke-1.416
horse-1.346
plate-1.282
 Trafford-1.229
 Hawth-1.225
Token Conf
Token ID7326
Feature activation+5.13e+00

Pos logit contributions
 tremend+0.096
 streng+0.083
aughs+0.080
utical+0.079
 Libre+0.075
Neg logit contributions
poke-0.080
horse-0.077
plate-0.074
 Trafford-0.070
 Hawth-0.070
Tokenirmation
Token ID36241
Feature activation+2.76e+00

Pos logit contributions
 tremend+4.370
 streng+3.822
aughs+3.719
utical+3.692
 Libre+3.520
Neg logit contributions
poke-4.255
horse-4.148
plate-3.965
 Hawth-3.800
 Trafford-3.784
Token.
Token ID13
Feature activation+1.11e-01

Pos logit contributions
 tremend+2.585
 streng+2.266
aughs+2.227
utical+2.203
 Libre+2.119
Neg logit contributions
poke-2.096
horse-1.990
plate-1.888
 Trafford-1.816
 Hawth-1.798
Token Cuban
Token ID18147
Feature activation+7.08e+00

Pos logit contributions
poke+1.173
horse+1.126
plate+1.095
 Hawth+1.048
 Trafford+1.047
Neg logit contributions
 tremend-1.504
 streng-1.304
aughs-1.280
utical-1.263
 toget-1.167
Token President
Token ID1992
Feature activation+1.65e+00

Pos logit contributions
 tremend+5.968
 streng+5.247
aughs+5.011
 Libre+4.892
utical+4.858
Neg logit contributions
poke-5.877
horse-5.702
plate-5.435
fleet-5.175
 Hawth-5.125
Token Fidel
Token ID42320
Feature activation+4.21e+00

Pos logit contributions
 tremend+1.587
 streng+1.392
aughs+1.352
utical+1.317
 Libre+1.251
Neg logit contributions
poke-1.247
horse-1.207
plate-1.158
 Trafford-1.101
 Hawth-1.098
Token Castro
Token ID21193
Feature activation+5.36e+00

Pos logit contributions
 tremend+3.679
 streng+3.214
aughs+3.140
utical+3.066
 Libre+3.008
Neg logit contributions
poke-3.437
horse-3.319
plate-3.185
 Trafford-3.002
fleet-2.996
Token,
Token ID11
Feature activation-7.36e-02

Pos logit contributions
 tremend+5.082
 streng+4.550
aughs+4.402
utical+4.324
 Libre+4.262
Neg logit contributions
poke-3.894
horse-3.685
plate-3.484
fleet-3.325
 Trafford-3.319
Token Cuban
Token ID18147
Feature activation+7.52e+00

Pos logit contributions
poke+0.053
horse+0.051
plate+0.050
 Hawth+0.047
 Trafford+0.047
Neg logit contributions
 tremend-0.073
 streng-0.064
aughs-0.062
utical-0.061
 Libre-0.058
Token dissidents
Token ID49913
Feature activation+3.55e+00

Pos logit contributions
 tremend+6.726
 streng+5.966
aughs+5.772
 Libre+5.607
utical+5.597
Neg logit contributions
poke-5.868
horse-5.633
plate-5.320
fleet-5.076
 Trafford-5.049
Token who
Token ID508
Feature activation+4.66e-01

Pos logit contributions
 tremend+3.512
 streng+3.140
aughs+3.016
utical+2.972
 Libre+2.886
Neg logit contributions
poke-2.518
horse-2.416
plate-2.300
 Trafford-2.177
fleet-2.165
Token advocate
Token ID12811
Feature activation-1.29e-01

Pos logit contributions
 tremend+0.446
 streng+0.388
aughs+0.379
utical+0.372
 Libre+0.354
Neg logit contributions
poke-0.355
horse-0.342
plate-0.328
 Hawth-0.311
 Trafford-0.309
Token greater
Token ID3744
Feature activation-5.68e-02

Pos logit contributions
poke+0.099
horse+0.095
plate+0.092
 Hawth+0.087
 Trafford+0.086
Neg logit contributions
 tremend-0.123
 streng-0.106
aughs-0.105
utical-0.102
 Libre-0.096
Token human
Token ID1692
Feature activation-1.15e+00

Pos logit contributions
poke+0.048
horse+0.046
plate+0.045
 Hawth+0.043
 Trafford+0.043
Neg logit contributions
 tremend-0.050
 streng-0.042
aughs-0.042
utical-0.041
 toget-0.038
Token almost
Token ID2048
Feature activation+6.78e-01

Pos logit contributions
poke+0.137
horse+0.133
plate+0.128
 Hawth+0.119
 Trafford+0.119
Neg logit contributions
 tremend-0.190
 streng-0.166
aughs-0.164
utical-0.161
 Libre-0.152
Token identical
Token ID10411
Feature activation-5.66e-01

Pos logit contributions
 tremend+0.666
 streng+0.586
aughs+0.571
utical+0.562
 Libre+0.534
Neg logit contributions
poke-0.497
horse-0.480
plate-0.462
 Trafford-0.433
 Hawth-0.433
Token except
Token ID2845
Feature activation-1.61e+00

Pos logit contributions
poke+0.374
horse+0.359
plate+0.343
 Trafford+0.320
 Hawth+0.319
Neg logit contributions
 tremend-0.595
 streng-0.529
aughs-0.516
utical-0.507
 Libre-0.487
Token that
Token ID326
Feature activation+6.36e-01

Pos logit contributions
poke+1.067
horse+1.023
plate+0.984
 Trafford+0.912
 Hawth+0.910
Neg logit contributions
 tremend-1.700
 streng-1.512
aughs-1.474
utical-1.439
 Libre-1.385
Token the
Token ID262
Feature activation+6.08e-01

Pos logit contributions
 tremend+0.629
 streng+0.554
aughs+0.539
utical+0.529
 Libre+0.506
Neg logit contributions
poke-0.463
horse-0.446
plate-0.429
 Trafford-0.402
 Hawth-0.402
Token Brune
Token ID46070
Feature activation+7.51e+00

Pos logit contributions
 tremend+0.575
 streng+0.501
aughs+0.490
utical+0.480
 Libre+0.456
Neg logit contributions
poke-0.470
horse-0.453
plate-0.437
 Trafford-0.412
 Hawth-0.412
Tokeni
Token ID72
Feature activation+1.17e+00

Pos logit contributions
 tremend+4.834
 streng+4.015
utical+4.006
aughs+3.979
 Libre+3.620
Neg logit contributions
poke-7.443
horse-7.346
plate-6.979
 Trafford-6.936
 Hawth-6.768
Token version
Token ID2196
Feature activation+5.05e-01

Pos logit contributions
 tremend+1.075
 streng+0.934
aughs+0.907
utical+0.886
 Libre+0.842
Neg logit contributions
poke-0.935
horse-0.902
plate-0.872
 Trafford-0.821
 Hawth-0.821
Token has
Token ID468
Feature activation+6.66e-01

Pos logit contributions
 tremend+0.520
 streng+0.460
aughs+0.447
utical+0.439
 Libre+0.421
Neg logit contributions
poke-0.347
horse-0.336
plate-0.322
 Hawth-0.299
 Trafford-0.298
Token their
Token ID511
Feature activation+2.28e+00

Pos logit contributions
 tremend+0.664
 streng+0.587
aughs+0.572
utical+0.561
 Libre+0.537
Neg logit contributions
poke-0.477
horse-0.460
plate-0.441
 Hawth-0.413
 Trafford-0.413
Token state
Token ID1181
Feature activation+1.62e+00

Pos logit contributions
 tremend+2.100
 streng+1.836
aughs+1.780
utical+1.747
 Libre+1.669
Neg logit contributions
poke-1.802
horse-1.739
plate-1.672
 Trafford-1.584
 Hawth-1.581
Token of
Token ID286
Feature activation-6.59e-01

Pos logit contributions
poke+0.782
horse+0.748
plate+0.716
 Trafford+0.687
 Hawth+0.680
Neg logit contributions
 tremend-0.928
 streng-0.801
aughs-0.787
utical-0.766
 Libre-0.733
Token life
Token ID1204
Feature activation-1.10e+00

Pos logit contributions
poke+0.469
horse+0.449
plate+0.431
 Hawth+0.413
 Trafford+0.411
Neg logit contributions
 tremend-0.658
 streng-0.583
aughs-0.569
utical-0.563
 Libre-0.528
Token
Token ID784
Feature activation+2.81e-01

Pos logit contributions
poke+0.767
horse+0.741
plate+0.707
 Hawth+0.662
 Trafford+0.661
Neg logit contributions
 tremend-1.116
 streng-0.989
aughs-0.958
utical-0.948
 Libre-0.907
Token beyond
Token ID3675
Feature activation-1.12e+00

Pos logit contributions
 tremend+0.304
 streng+0.271
aughs+0.264
utical+0.260
 Libre+0.250
Neg logit contributions
poke-0.178
horse-0.171
plate-0.163
 Hawth-0.152
 Trafford-0.152
Token the
Token ID262
Feature activation+1.19e-01

Pos logit contributions
poke+0.809
horse+0.779
plate+0.744
 Hawth+0.711
 Trafford+0.699
Neg logit contributions
 tremend-1.122
 streng-0.984
aughs-0.957
utical-0.945
 Libre-0.899
Token plat
Token ID40315
Feature activation-8.96e+00

Pos logit contributions
 tremend+0.110
 streng+0.096
aughs+0.093
utical+0.092
 Libre+0.087
Neg logit contributions
poke-0.095
horse-0.091
plate-0.088
 Hawth-0.084
 Trafford-0.083
Tokenitudes
Token ID10455
Feature activation-5.93e+00

Pos logit contributions
poke+2.614
horse+2.475
plate+2.403
fleet+1.920
 Hawth+1.870
Neg logit contributions
 tremend-11.855
 streng-10.892
utical-10.619
aughs-10.618
 Libre-10.374
Token?
Token ID30
Feature activation+2.07e+00

Pos logit contributions
poke+3.788
horse+3.675
plate+3.515
 Hawth+3.275
 Trafford+3.212
Neg logit contributions
 tremend-6.282
 streng-5.598
aughs-5.453
utical-5.339
 Libre-5.092
Token I
Token ID314
Feature activation+5.92e-01

Pos logit contributions
 tremend+1.960
 streng+1.720
aughs+1.661
utical+1.633
 Libre+1.564
Neg logit contributions
poke-1.593
horse-1.536
plate-1.472
 Trafford-1.395
 Hawth-1.391
Token am
Token ID716
Feature activation-2.33e+00

Pos logit contributions
 tremend+0.600
 streng+0.527
aughs+0.516
utical+0.509
 Libre+0.484
Neg logit contributions
poke-0.419
horse-0.402
plate-0.384
 Hawth-0.360
 Trafford-0.358
Token certain
Token ID1728
Feature activation+2.00e+00

Pos logit contributions
poke+1.552
horse+1.491
plate+1.434
 Hawth+1.349
 Trafford+1.324
Neg logit contributions
 tremend-2.443
 streng-2.161
aughs-2.137
utical-2.095
 Libre-1.983
Token of
Token ID286
Feature activation-9.92e-01

Pos logit contributions
poke+0.801
horse+0.778
plate+0.746
 Hawth+0.697
 Trafford+0.689
Neg logit contributions
 tremend-1.281
 streng-1.128
aughs-1.058
utical-1.034
 toget-1.001
Token 15
Token ID1315
Feature activation+8.29e-01

Pos logit contributions
poke+0.686
horse+0.663
plate+0.633
 Hawth+0.617
 Trafford+0.606
Neg logit contributions
 tremend-1.059
 streng-0.930
aughs-0.877
utical-0.862
 toget-0.827
Token Photos
Token ID9434
Feature activation+4.82e-01

Pos logit contributions
 tremend+0.803
 streng+0.712
aughs+0.700
utical+0.683
 Libre+0.666
Neg logit contributions
poke-0.605
horse-0.578
plate-0.551
 Trafford-0.518
 Hawth-0.513
Token:
Token ID25
Feature activation-1.19e+00

Pos logit contributions
 tremend+0.534
 streng+0.478
aughs+0.463
utical+0.456
 Libre+0.439
Neg logit contributions
poke-0.296
horse-0.283
plate-0.268
 Trafford-0.249
 Hawth-0.249
Token Carly
Token ID35982
Feature activation-3.31e+00

Pos logit contributions
poke+0.832
horse+0.801
plate+0.763
 Trafford+0.723
 Hawth+0.723
Neg logit contributions
 tremend-1.219
 streng-1.079
aughs-1.041
utical-1.024
 Libre-0.980
Token Fiorina
Token ID49028
Feature activation-8.77e+00

Pos logit contributions
poke+1.195
horse+1.096
plate+1.026
 Hawth+0.897
 Trafford+0.879
Neg logit contributions
 tremend-4.470
 streng-4.091
aughs-3.996
utical-3.912
 Libre-3.832
Token's
Token ID338
Feature activation-3.75e-01

Pos logit contributions
poke+5.760
horse+5.603
plate+5.571
 Hawth+5.225
 Trafford+4.951
Neg logit contributions
 tremend-8.553
 streng-7.559
aughs-7.421
utical-7.308
sembly-7.000
Token political
Token ID1964
Feature activation-2.37e+00

Pos logit contributions
poke+0.277
horse+0.267
plate+0.256
 Hawth+0.242
 Trafford+0.241
Neg logit contributions
 tremend-0.365
 streng-0.322
aughs-0.313
utical-0.307
 Libre-0.294
Token career
Token ID3451
Feature activation-3.90e+00

Pos logit contributions
poke+1.799
horse+1.737
plate+1.661
 Hawth+1.571
 Trafford+1.569
Neg logit contributions
 tremend-2.257
 streng-1.981
aughs-1.922
utical-1.888
 Libre-1.807
Token Fiorina
Token ID49028
Feature activation-7.88e+00

Pos logit contributions
poke+2.192
horse+2.124
plate+2.010
 Hawth+1.872
 Trafford+1.833
Neg logit contributions
 tremend-4.461
 streng-4.000
aughs-3.871
utical-3.852
 Libre-3.650
Token,
Token ID11
Feature activation-1.03e+00

Pos logit contributions
poke+5.077
horse+4.969
plate+4.921
 Hawth+4.558
 Dover+4.325
Neg logit contributions
 tremend-8.021
 streng-7.030
utical-6.819
aughs-6.803
sembly-6.484
Token to
Token ID284
Feature activation-1.47e-01

Pos logit contributions
 tremend+0.219
 streng+0.195
aughs+0.190
utical+0.187
 Libre+0.180
Neg logit contributions
poke-0.138
horse-0.132
plate-0.126
 Hawth-0.118
 Trafford-0.117
Token this
Token ID428
Feature activation-3.20e+00

Pos logit contributions
poke+0.100
horse+0.096
plate+0.091
 Hawth+0.087
 Trafford+0.086
Neg logit contributions
 tremend-0.151
 streng-0.134
aughs-0.131
utical-0.129
 Libre-0.123
Token woman
Token ID2415
Feature activation-1.40e+00

Pos logit contributions
poke+2.360
horse+2.296
plate+2.195
 Hawth+2.109
 Trafford+2.066
Neg logit contributions
 tremend-3.038
aughs-2.667
 streng-2.652
utical-2.614
 Libre-2.439
Token with
Token ID351
Feature activation+1.69e+00

Pos logit contributions
poke+1.010
horse+0.977
plate+0.938
 Hawth+0.878
 Trafford+0.870
Neg logit contributions
 tremend-1.380
 streng-1.221
aughs-1.194
utical-1.165
 Libre-1.122
Token sentimental
Token ID46908
Feature activation-7.13e-01

Pos logit contributions
 tremend+1.687
 streng+1.494
aughs+1.448
utical+1.423
 Libre+1.372
Neg logit contributions
poke-1.206
horse-1.158
plate-1.107
 Trafford-1.043
 Hawth-1.037
Token plat
Token ID40315
Feature activation-8.71e+00

Pos logit contributions
poke+0.533
horse+0.517
plate+0.494
 Hawth+0.468
 Trafford+0.466
Neg logit contributions
 tremend-0.686
 streng-0.602
aughs-0.585
utical-0.574
 Libre-0.551
Tokenitudes
Token ID10455
Feature activation-6.34e+00

Pos logit contributions
poke+2.971
horse+2.781
plate+2.630
fleet+2.257
 Trafford+2.178
Neg logit contributions
 tremend-11.459
 streng-10.461
aughs-10.250
utical-10.087
 Libre-9.876
Token,
Token ID11
Feature activation-2.85e-01

Pos logit contributions
poke+3.701
horse+3.593
plate+3.425
 Hawth+3.137
 Trafford+3.045
Neg logit contributions
 tremend-7.001
 streng-6.247
aughs-6.212
utical-5.960
 Libre-5.766
Token Lac
Token ID23115
Feature activation-2.16e+00

Pos logit contributions
poke+0.190
horse+0.183
plate+0.174
 Hawth+0.165
 Trafford+0.164
Neg logit contributions
 tremend-0.298
 streng-0.265
aughs-0.259
utical-0.254
 Libre-0.241
Tokenan
Token ID272
Feature activation-1.87e+00

Pos logit contributions
poke+1.931
horse+1.866
plate+1.826
fleet+1.708
grid+1.697
Neg logit contributions
 tremend-1.893
 streng-1.626
aughs-1.464
utical-1.420
 toget-1.402
Token
Token ID447
Feature activation+7.67e-01

Pos logit contributions
poke+1.322
horse+1.279
plate+1.226
 Hawth+1.162
 Trafford+1.146
Neg logit contributions
 tremend-1.884
 streng-1.637
aughs-1.595
utical-1.576
 Libre-1.493
Token respects
Token ID19410
Feature activation-2.01e+00

Pos logit contributions
poke+0.115
horse+0.110
plate+0.105
 Hawth+0.098
 Trafford+0.098
Neg logit contributions
 tremend-0.169
 streng-0.150
aughs-0.145
utical-0.143
 Libre-0.138
Token these
Token ID777
Feature activation-3.09e+00

Pos logit contributions
poke+1.486
horse+1.419
plate+1.366
 Hawth+1.315
 Trafford+1.291
Neg logit contributions
 tremend-1.955
 streng-1.724
aughs-1.673
utical-1.668
 Libre-1.575
Token people
Token ID661
Feature activation-3.43e-01

Pos logit contributions
poke+2.222
horse+2.138
plate+2.068
 Hawth+1.951
 Trafford+1.924
Neg logit contributions
 tremend-3.039
 streng-2.651
aughs-2.605
utical-2.599
 Libre-2.459
Token and
Token ID290
Feature activation-1.26e-01

Pos logit contributions
poke+0.230
horse+0.221
plate+0.211
 Hawth+0.197
 Trafford+0.196
Neg logit contributions
 tremend-0.357
 streng-0.318
aughs-0.310
utical-0.304
 Libre-0.294
Token never
Token ID1239
Feature activation-3.06e-01

Pos logit contributions
poke+0.088
horse+0.084
plate+0.081
 Hawth+0.076
 Trafford+0.075
Neg logit contributions
 tremend-0.128
 streng-0.113
aughs-0.110
utical-0.109
 Libre-0.104
Token condesc
Token ID41466
Feature activation-8.51e+00

Pos logit contributions
poke+0.215
horse+0.206
plate+0.197
 Hawth+0.185
 Trafford+0.182
Neg logit contributions
 tremend-0.311
 streng-0.273
aughs-0.267
utical-0.264
 Libre-0.253
Tokenends
Token ID2412
Feature activation-2.55e+00

Pos logit contributions
poke+4.596
horse+4.258
plate+4.201
antis+3.776
 Trafford+3.754
Neg logit contributions
 tremend-9.808
 streng-8.820
utical-8.288
 Libre-8.148
aughs-8.106
Token to
Token ID284
Feature activation-2.86e-01

Pos logit contributions
poke+1.665
horse+1.591
plate+1.523
 Hawth+1.421
 Trafford+1.406
Neg logit contributions
 tremend-2.685
 streng-2.405
aughs-2.334
utical-2.314
 Libre-2.228
Token them
Token ID606
Feature activation-2.13e-01

Pos logit contributions
poke+0.232
horse+0.222
plate+0.213
 Hawth+0.204
 Trafford+0.202
Neg logit contributions
 tremend-0.261
 streng-0.227
aughs-0.220
utical-0.219
 Libre-0.207
Token,
Token ID11
Feature activation-2.15e-01

Pos logit contributions
poke+0.145
horse+0.139
plate+0.133
 Hawth+0.125
 Trafford+0.124
Neg logit contributions
 tremend-0.220
 streng-0.195
aughs-0.190
utical-0.187
 Libre-0.180
Token evidenced
Token ID30204
Feature activation+4.71e+00

Pos logit contributions
poke+0.143
horse+0.136
plate+0.130
 Hawth+0.122
 Trafford+0.121
Neg logit contributions
 tremend-0.225
 streng-0.200
aughs-0.195
utical-0.192
 Libre-0.185
Token Times
Token ID3782
Feature activation-1.29e+00

Pos logit contributions
 tremend+0.709
 streng+0.625
aughs+0.609
utical+0.601
 Libre+0.566
Neg logit contributions
poke-0.544
horse-0.524
plate-0.500
 Hawth-0.479
 Trafford-0.477
Token Square
Token ID9276
Feature activation-1.93e+00

Pos logit contributions
poke+0.900
horse+0.864
plate+0.824
 Trafford+0.776
 Hawth+0.773
Neg logit contributions
 tremend-1.310
 streng-1.169
utical-1.136
aughs-1.136
 Libre-1.052
Token in
Token ID287
Feature activation-6.80e-01

Pos logit contributions
poke+1.244
horse+1.200
plate+1.141
 Hawth+1.068
 Trafford+1.066
Neg logit contributions
 tremend-2.040
 streng-1.831
aughs-1.805
utical-1.775
 Libre-1.671
Token the
Token ID262
Feature activation-2.09e-01

Pos logit contributions
poke+0.510
horse+0.493
plate+0.473
 Hawth+0.454
 Trafford+0.450
Neg logit contributions
 tremend-0.658
 streng-0.578
aughs-0.559
utical-0.553
 Libre-0.519
Token old
Token ID1468
Feature activation-1.49e+00

Pos logit contributions
poke+0.161
horse+0.156
plate+0.150
 Hawth+0.144
 Trafford+0.144
Neg logit contributions
 tremend-0.197
 streng-0.172
aughs-0.168
utical-0.166
 Libre-0.156
Token Naval
Token ID20818
Feature activation-8.38e+00

Pos logit contributions
poke+1.080
horse+1.033
plate+0.988
 Trafford+0.944
 Hawth+0.937
Neg logit contributions
 tremend-1.474
 streng-1.296
aughs-1.260
utical-1.257
 Libre-1.181
Token Air
Token ID3701
Feature activation-3.44e+00

Pos logit contributions
poke+5.336
horse+5.152
plate+5.034
 Hawth+4.755
 Trafford+4.726
Neg logit contributions
 tremend-8.805
 streng-7.619
aughs-7.457
utical-7.452
 toget-7.066
Token Station
Token ID9327
Feature activation-2.23e+00

Pos logit contributions
poke+1.517
horse+1.464
plate+1.371
fleet+1.231
 Trafford+1.223
Neg logit contributions
 tremend-4.352
 streng-3.944
aughs-3.901
utical-3.814
 toget-3.660
Token in
Token ID287
Feature activation-6.08e-01

Pos logit contributions
poke+1.461
horse+1.407
plate+1.346
 Hawth+1.270
 Trafford+1.270
Neg logit contributions
 tremend-2.352
 streng-2.103
aughs-2.047
utical-2.026
 Libre-1.904
Token South
Token ID2520
Feature activation-1.44e+00

Pos logit contributions
poke+0.423
horse+0.412
plate+0.391
 Hawth+0.378
 Trafford+0.375
Neg logit contributions
 tremend-0.622
 streng-0.548
aughs-0.529
utical-0.522
 Libre-0.492
Token We
Token ID775
Feature activation-2.70e-01

Pos logit contributions
poke+0.910
horse+0.867
plate+0.825
 Hawth+0.779
 Trafford+0.773
Neg logit contributions
 tremend-1.579
 streng-1.411
aughs-1.363
utical-1.345
 Libre-1.287
Token of
Token ID286
Feature activation-1.43e+00

Pos logit contributions
 tremend+0.102
 streng+0.090
aughs+0.085
utical+0.083
 toget+0.079
Neg logit contributions
poke-0.071
horse-0.069
plate-0.066
 Hawth-0.062
 Trafford-0.061
Token 15
Token ID1315
Feature activation+2.96e-01

Pos logit contributions
poke+1.072
horse+1.039
plate+0.989
 Hawth+0.956
 Trafford+0.939
Neg logit contributions
 tremend-1.491
 streng-1.288
aughs-1.193
utical-1.178
 toget-1.130
Token Photos
Token ID9434
Feature activation-2.02e-01

Pos logit contributions
 tremend+0.323
 streng+0.286
aughs+0.271
utical+0.267
 Libre+0.255
Neg logit contributions
poke-0.195
horse-0.188
plate-0.178
 Hawth-0.169
 Trafford-0.167
Token:
Token ID25
Feature activation-1.86e+00

Pos logit contributions
poke+0.126
horse+0.120
plate+0.114
 Trafford+0.106
 Hawth+0.106
Neg logit contributions
 tremend-0.222
 streng-0.198
aughs-0.193
utical-0.190
 Libre-0.183
Token Carly
Token ID35982
Feature activation-5.34e+00

Pos logit contributions
poke+1.072
horse+1.037
plate+0.979
 Hawth+0.937
 Trafford+0.904
Neg logit contributions
 tremend-2.227
 streng-1.972
aughs-1.862
utical-1.823
 toget-1.767
Token Fiorina
Token ID49028
Feature activation-8.36e+00

Pos logit contributions
poke+1.118
horse+1.046
plate+0.966
 Hawth+0.780
 Trafford+0.623
Neg logit contributions
 tremend-8.235
 streng-7.513
aughs-7.194
utical-7.026
sembly-7.006
Token's
Token ID338
Feature activation-3.96e-01

Pos logit contributions
poke+5.097
horse+4.931
plate+4.824
 Hawth+4.440
grid+4.112
Neg logit contributions
 tremend-9.850
 streng-8.451
aughs-7.759
sembly-7.740
 newcom-7.574
Token political
Token ID1964
Feature activation-2.40e+00

Pos logit contributions
poke+0.354
horse+0.343
plate+0.333
 Hawth+0.319
 Trafford+0.316
Neg logit contributions
 tremend-0.334
 streng-0.282
aughs-0.272
utical-0.265
 Libre-0.248
Token career
Token ID3451
Feature activation-4.32e+00

Pos logit contributions
poke+1.494
horse+1.433
plate+1.351
 Hawth+1.297
 Trafford+1.266
Neg logit contributions
 tremend-2.700
 streng-2.361
aughs-2.285
utical-2.248
 Libre-2.144
Token Fiorina
Token ID49028
Feature activation-7.74e+00

Pos logit contributions
poke+1.468
horse+1.389
plate+1.255
 Hawth+1.119
 Trafford+1.072
Neg logit contributions
 tremend-6.005
 streng-5.484
aughs-5.222
utical-5.220
 toget-5.061
Token speaks
Token ID9209
Feature activation-2.31e+00

Pos logit contributions
poke+4.635
horse+4.475
plate+4.437
 Hawth+4.044
 Trafford+3.852
Neg logit contributions
 tremend-8.346
 streng-7.354
utical-7.131
aughs-7.066
sembly-6.734
Token of
Token ID286
Feature activation-1.20e+00

Pos logit contributions
 tremend+0.087
 streng+0.076
aughs+0.072
utical+0.071
 Libre+0.067
Neg logit contributions
poke-0.061
horse-0.059
plate-0.056
 Hawth-0.053
 Trafford-0.052
Token 15
Token ID1315
Feature activation-1.57e-01

Pos logit contributions
poke+0.927
horse+0.896
plate+0.857
 Hawth+0.821
 Trafford+0.809
Neg logit contributions
 tremend-1.202
 streng-1.037
aughs-0.974
utical-0.955
 toget-0.912
Token Photos
Token ID9434
Feature activation-4.17e-01

Pos logit contributions
poke+0.103
horse+0.099
plate+0.095
 Hawth+0.090
 Trafford+0.088
Neg logit contributions
 tremend-0.172
 streng-0.152
aughs-0.144
utical-0.142
 toget-0.135
Token:
Token ID25
Feature activation-1.67e+00

Pos logit contributions
poke+0.258
horse+0.246
plate+0.233
 Trafford+0.217
 Hawth+0.217
Neg logit contributions
 tremend-0.461
 streng-0.412
aughs-0.399
utical-0.393
 Libre-0.379
Token Carly
Token ID35982
Feature activation-5.02e+00

Pos logit contributions
poke+0.984
horse+0.943
plate+0.894
 Hawth+0.848
 Trafford+0.823
Neg logit contributions
 tremend-1.961
 streng-1.742
aughs-1.646
utical-1.605
 toget-1.557
Token Fiorina
Token ID49028
Feature activation-8.31e+00

Pos logit contributions
poke+1.140
horse+1.073
plate+0.970
 Hawth+0.818
 Trafford+0.686
Neg logit contributions
 tremend-7.788
 streng-7.093
aughs-6.702
utical-6.556
sembly-6.517
Token's
Token ID338
Feature activation-2.20e-01

Pos logit contributions
poke+5.034
horse+4.929
plate+4.707
 Hawth+4.363
 Trafford+4.033
Neg logit contributions
 tremend-10.459
 streng-8.951
sembly-8.151
 newcom-8.146
aughs-7.940
Token political
Token ID1964
Feature activation-2.50e+00

Pos logit contributions
poke+0.201
horse+0.195
plate+0.188
 Hawth+0.180
 Trafford+0.179
Neg logit contributions
 tremend-0.180
 streng-0.152
aughs-0.146
utical-0.142
 Libre-0.134
Token career
Token ID3451
Feature activation-4.58e+00

Pos logit contributions
poke+1.540
horse+1.480
plate+1.395
 Hawth+1.341
 Trafford+1.309
Neg logit contributions
 tremend-2.831
 streng-2.471
aughs-2.390
utical-2.349
 toget-2.244
Token Fiorina
Token ID49028
Feature activation-7.70e+00

Pos logit contributions
poke+1.577
horse+1.485
plate+1.354
 Hawth+1.202
 Trafford+1.155
Neg logit contributions
 tremend-6.305
 streng-5.758
aughs-5.500
utical-5.496
 toget-5.303
Token arrives
Token ID14443
Feature activation-1.16e+00

Pos logit contributions
poke+4.819
horse+4.621
plate+4.620
 Hawth+4.234
 Trafford+4.076
Neg logit contributions
 tremend-8.082
 streng-7.031
utical-6.841
aughs-6.797
sembly-6.502
Token controversial
Token ID8381
Feature activation-1.12e-01

Pos logit contributions
 tremend+1.189
 streng+1.048
aughs+1.018
utical+1.006
 Libre+0.956
Neg logit contributions
poke-0.874
horse-0.842
plate-0.803
 Hawth-0.761
 Trafford-0.759
Token editor
Token ID5464
Feature activation-9.29e-01

Pos logit contributions
poke+0.079
horse+0.076
plate+0.073
 Hawth+0.069
 Trafford+0.068
Neg logit contributions
 tremend-0.114
 streng-0.101
aughs-0.098
utical-0.098
 Libre-0.091
Token.
Token ID13
Feature activation-4.20e-01

Pos logit contributions
poke+0.599
horse+0.577
plate+0.550
 Hawth+0.514
 Trafford+0.510
Neg logit contributions
 tremend-0.995
 streng-0.884
aughs-0.861
utical-0.849
 Libre-0.812
Token Some
Token ID2773
Feature activation+1.37e+00

Pos logit contributions
poke+0.307
horse+0.297
plate+0.283
 Hawth+0.269
 Trafford+0.269
Neg logit contributions
 tremend-0.420
 streng-0.368
aughs-0.352
utical-0.348
 Libre-0.329
Token of
Token ID286
Feature activation-5.25e-01

Pos logit contributions
 tremend+1.320
 streng+1.155
aughs+1.120
utical+1.107
 Libre+1.050
Neg logit contributions
poke-1.041
horse-1.005
plate-0.961
 Hawth-0.911
 Trafford-0.906
Token Milo
Token ID32662
Feature activation-8.24e+00

Pos logit contributions
poke+0.353
horse+0.338
plate+0.322
 Hawth+0.303
 Trafford+0.302
Neg logit contributions
 tremend-0.548
 streng-0.487
aughs-0.472
utical-0.466
 Libre-0.446
Token's
Token ID338
Feature activation+5.38e-01

Pos logit contributions
poke+5.526
horse+5.430
plate+5.176
 Hawth+4.878
 Trafford+4.741
Neg logit contributions
 tremend-8.316
 streng-7.317
utical-6.798
aughs-6.769
 toget-6.542
Token colleagues
Token ID7810
Feature activation-1.53e+00

Pos logit contributions
 tremend+0.514
 streng+0.450
aughs+0.433
utical+0.430
 Libre+0.408
Neg logit contributions
poke-0.409
horse-0.396
plate-0.380
 Hawth-0.362
 Trafford-0.357
Token at
Token ID379
Feature activation-1.07e+00

Pos logit contributions
poke+1.074
horse+1.032
plate+0.986
 Hawth+0.929
 Trafford+0.919
Neg logit contributions
 tremend-1.557
 streng-1.364
aughs-1.328
utical-1.311
 Libre-1.250
Token Breitbart
Token ID19923
Feature activation-3.88e+00

Pos logit contributions
poke+0.648
horse+0.622
plate+0.586
 Hawth+0.554
 Trafford+0.546
Neg logit contributions
 tremend-1.190
 streng-1.062
aughs-1.028
utical-1.019
 Libre-0.973
Token reportedly
Token ID7478
Feature activation+2.13e-01

Pos logit contributions
poke+2.733
horse+2.639
plate+2.525
 Hawth+2.395
 Trafford+2.356
Neg logit contributions
 tremend-3.904
 streng-3.406
aughs-3.296
utical-3.291
 Libre-3.052
Token of
Token ID286
Feature activation-1.29e+00

Pos logit contributions
poke+0.427
horse+0.413
plate+0.395
 Hawth+0.369
 Trafford+0.365
Neg logit contributions
 tremend-0.618
 streng-0.543
aughs-0.513
utical-0.501
 toget-0.480
Token 15
Token ID1315
Feature activation+1.05e-01

Pos logit contributions
poke+0.978
horse+0.947
plate+0.902
 Hawth+0.870
 Trafford+0.854
Neg logit contributions
 tremend-1.318
 streng-1.136
aughs-1.061
utical-1.042
 toget-0.998
Token Photos
Token ID9434
Feature activation-2.45e-01

Pos logit contributions
 tremend+0.114
 streng+0.101
aughs+0.096
utical+0.094
 Libre+0.090
Neg logit contributions
poke-0.070
horse-0.067
plate-0.064
 Hawth-0.060
 Trafford-0.060
Token:
Token ID25
Feature activation-1.79e+00

Pos logit contributions
poke+0.153
horse+0.146
plate+0.138
 Trafford+0.129
 Hawth+0.128
Neg logit contributions
 tremend-0.267
 streng-0.239
aughs-0.232
utical-0.229
 Libre-0.221
Token Carly
Token ID35982
Feature activation-5.03e+00

Pos logit contributions
poke+1.043
horse+1.004
plate+0.950
 Hawth+0.902
 Trafford+0.873
Neg logit contributions
 tremend-2.131
 streng-1.891
aughs-1.785
utical-1.740
 toget-1.691
Token Fiorina
Token ID49028
Feature activation-8.13e+00

Pos logit contributions
poke+1.111
horse+1.043
plate+0.942
 Hawth+0.781
 Trafford+0.650
Neg logit contributions
 tremend-7.808
 streng-7.117
aughs-6.738
utical-6.578
 toget-6.548
Token's
Token ID338
Feature activation-3.79e-01

Pos logit contributions
poke+4.938
horse+4.813
plate+4.611
 Hawth+4.275
 Trafford+4.000
Neg logit contributions
 tremend-10.135
 streng-8.696
sembly-7.861
 newcom-7.836
aughs-7.757
Token political
Token ID1964
Feature activation-2.19e+00

Pos logit contributions
poke+0.344
horse+0.334
plate+0.323
 Hawth+0.309
 Trafford+0.307
Neg logit contributions
 tremend-0.314
 streng-0.266
aughs-0.256
utical-0.249
 Libre-0.233
Token career
Token ID3451
Feature activation-4.34e+00

Pos logit contributions
poke+1.366
horse+1.311
plate+1.236
 Hawth+1.188
 Trafford+1.162
Neg logit contributions
 tremend-2.472
 streng-2.160
aughs-2.090
utical-2.054
 toget-1.960
Token Fiorina
Token ID49028
Feature activation-7.58e+00

Pos logit contributions
poke+1.551
horse+1.468
plate+1.347
 Hawth+1.209
 Trafford+1.161
Neg logit contributions
 tremend-5.946
 streng-5.426
utical-5.160
aughs-5.145
 toget-4.998
Token speaks
Token ID9209
Feature activation-2.51e+00

Pos logit contributions
poke+4.732
horse+4.539
plate+4.529
 Hawth+4.140
 Trafford+3.976
Neg logit contributions
 tremend-8.013
 streng-6.997
utical-6.774
aughs-6.737
sembly-6.428
Token documented
Token ID12395
Feature activation+2.49e-01

Pos logit contributions
 tremend+0.199
 streng+0.176
aughs+0.171
utical+0.169
 Libre+0.161
Neg logit contributions
poke-0.140
horse-0.135
plate-0.129
 Hawth-0.121
 Trafford-0.120
Token about
Token ID546
Feature activation-3.76e-01

Pos logit contributions
 tremend+0.264
 streng+0.235
aughs+0.229
utical+0.225
 Libre+0.217
Neg logit contributions
poke-0.163
horse-0.156
plate-0.148
 Trafford-0.138
 Hawth-0.138
Token so
Token ID523
Feature activation-1.28e+00

Pos logit contributions
poke+0.273
horse+0.261
plate+0.249
 Hawth+0.236
 Trafford+0.235
Neg logit contributions
 tremend-0.374
 streng-0.330
aughs-0.322
utical-0.316
 Libre-0.300
Token-
Token ID12
Feature activation+6.89e-01

Pos logit contributions
poke+0.929
horse+0.893
plate+0.853
 Trafford+0.805
 Hawth+0.802
Neg logit contributions
 tremend-1.269
 streng-1.122
aughs-1.088
utical-1.070
 Libre-1.028
Tokencalled
Token ID7174
Feature activation-2.48e+00

Pos logit contributions
 tremend+0.708
 streng+0.628
aughs+0.608
utical+0.594
 Libre+0.571
Neg logit contributions
poke-0.482
horse-0.464
plate-0.445
 Trafford-0.413
fleet-0.412
Token sexism
Token ID24953
Feature activation-8.11e+00

Pos logit contributions
poke+1.844
horse+1.772
plate+1.696
 Hawth+1.605
 Trafford+1.603
Neg logit contributions
 tremend-2.404
 streng-2.118
aughs-2.065
utical-2.029
 Libre-1.913
Token and
Token ID290
Feature activation-3.36e-01

Pos logit contributions
poke+4.807
horse+4.683
plate+4.431
 Hawth+4.029
 Trafford+3.924
Neg logit contributions
 tremend-8.676
 streng-7.751
aughs-7.591
utical-7.467
 Libre-7.119
Token racism
Token ID10713
Feature activation-5.80e+00

Pos logit contributions
poke+0.250
horse+0.241
plate+0.230
 Hawth+0.217
 Trafford+0.217
Neg logit contributions
 tremend-0.326
 streng-0.288
aughs-0.280
utical-0.275
 Libre-0.263
Token on
Token ID319
Feature activation+5.92e-01

Pos logit contributions
poke+3.543
horse+3.464
plate+3.264
 Hawth+3.033
 Trafford+2.936
Neg logit contributions
 tremend-6.240
 streng-5.562
aughs-5.405
utical-5.339
 Libre-5.104
Token the
Token ID262
Feature activation-8.19e-02

Pos logit contributions
 tremend+0.573
 streng+0.505
aughs+0.489
utical+0.481
 Libre+0.462
Neg logit contributions
poke-0.441
horse-0.425
plate-0.406
 Trafford-0.384
 Hawth-0.383
Token left
Token ID1364
Feature activation-1.14e+00

Pos logit contributions
poke+0.062
horse+0.060
plate+0.057
 Hawth+0.054
 Trafford+0.054
Neg logit contributions
 tremend-0.078
 streng-0.069
aughs-0.067
utical-0.066
 Libre-0.063
Token
Token ID198
Feature activation-2.62e-01

Pos logit contributions
poke+0.039
horse+0.037
plate+0.036
 Trafford+0.034
 Hawth+0.034
Neg logit contributions
 tremend-0.049
 streng-0.043
aughs-0.042
utical-0.041
 Libre-0.039
Token
Token ID198
Feature activation-1.91e-01

Pos logit contributions
poke+0.200
horse+0.193
plate+0.185
 Hawth+0.174
 Trafford+0.173
Neg logit contributions
 tremend-0.265
 streng-0.228
aughs-0.215
utical-0.211
 toget-0.201
Tokenthank
Token ID40716
Feature activation-1.54e+00

Pos logit contributions
poke+0.158
horse+0.153
plate+0.147
 Trafford+0.138
 Hawth+0.138
Neg logit contributions
 tremend-0.171
 streng-0.149
aughs-0.143
utical-0.140
 Libre-0.134
Token you
Token ID345
Feature activation+3.52e-01

Pos logit contributions
poke+1.082
horse+1.033
plate+0.976
 Trafford+0.922
fleet+0.914
Neg logit contributions
 tremend-1.573
 streng-1.394
aughs-1.361
utical-1.338
 Libre-1.279
Token @
Token ID2488
Feature activation-2.28e+00

Pos logit contributions
 tremend+0.351
 streng+0.311
aughs+0.303
utical+0.298
 Libre+0.285
Neg logit contributions
poke-0.251
horse-0.241
plate-0.230
 Trafford-0.218
 Hawth-0.217
Tokenmr
Token ID43395
Feature activation-8.07e+00

Pos logit contributions
poke+1.780
horse+1.715
plate+1.632
 Trafford+1.544
fleet+1.540
Neg logit contributions
 tremend-2.140
 streng-1.876
aughs-1.813
utical-1.785
 Libre-1.699
Token_
Token ID62
Feature activation-2.11e+00

Pos logit contributions
poke+6.182
horse+6.006
plate+5.677
fleet+5.350
grid+5.325
Neg logit contributions
 tremend-7.488
 streng-6.555
aughs-6.229
utical-6.148
 Libre-5.974
Tokense
Token ID325
Feature activation+7.81e-02

Pos logit contributions
poke+1.559
horse+1.506
plate+1.429
fleet+1.338
 Trafford+1.333
Neg logit contributions
 tremend-2.083
 streng-1.839
aughs-1.768
utical-1.740
 Libre-1.679
Tokenan
Token ID272
Feature activation-1.46e+00

Pos logit contributions
 tremend+0.075
 streng+0.066
aughs+0.064
utical+0.063
 Libre+0.060
Neg logit contributions
poke-0.059
horse-0.057
plate-0.054
 Trafford-0.051
 Hawth-0.051
Tokenh
Token ID71
Feature activation+1.79e-01

Pos logit contributions
poke+1.040
horse+1.005
plate+0.959
 Trafford+0.899
fleet+0.896
Neg logit contributions
 tremend-1.461
 streng-1.287
aughs-1.244
utical-1.223
 Libre-1.180
Tokenug
Token ID1018
Feature activation-1.30e+00

Pos logit contributions
 tremend+0.172
 streng+0.151
aughs+0.145
utical+0.143
 Libre+0.137
Neg logit contributions
poke-0.135
horse-0.130
plate-0.125
 Trafford-0.118
 Hawth-0.117
Token of
Token ID286
Feature activation-7.64e-01

Pos logit contributions
poke+0.226
horse+0.218
plate+0.209
 Hawth+0.195
 Trafford+0.193
Neg logit contributions
 tremend-0.321
 streng-0.281
aughs-0.268
utical-0.261
 Libre-0.249
Token 15
Token ID1315
Feature activation+2.93e-02

Pos logit contributions
poke+0.594
horse+0.574
plate+0.549
 Hawth+0.526
 Trafford+0.519
Neg logit contributions
 tremend-0.759
 streng-0.655
aughs-0.617
utical-0.605
 toget-0.576
Token Photos
Token ID9434
Feature activation-1.64e-01

Pos logit contributions
 tremend+0.032
 streng+0.028
aughs+0.027
utical+0.026
 Libre+0.025
Neg logit contributions
poke-0.019
horse-0.019
plate-0.018
 Hawth-0.017
 Trafford-0.017
Token:
Token ID25
Feature activation-1.42e+00

Pos logit contributions
poke+0.102
horse+0.097
plate+0.092
 Trafford+0.086
 Hawth+0.086
Neg logit contributions
 tremend-0.179
 streng-0.160
aughs-0.156
utical-0.154
 Libre-0.148
Token Carly
Token ID35982
Feature activation-4.81e+00

Pos logit contributions
poke+0.844
horse+0.811
plate+0.768
 Hawth+0.726
 Trafford+0.707
Neg logit contributions
 tremend-1.662
 streng-1.477
aughs-1.400
utical-1.366
 toget-1.321
Token Fiorina
Token ID49028
Feature activation-8.06e+00

Pos logit contributions
poke+1.090
horse+1.027
plate+0.930
 Hawth+0.775
 Trafford+0.657
Neg logit contributions
 tremend-7.435
 streng-6.777
aughs-6.415
utical-6.277
 toget-6.231
Token's
Token ID338
Feature activation-1.36e-01

Pos logit contributions
poke+4.887
horse+4.789
plate+4.578
 Hawth+4.242
 Trafford+3.961
Neg logit contributions
 tremend-10.023
 streng-8.605
sembly-7.794
 newcom-7.787
aughs-7.676
Token political
Token ID1964
Feature activation-2.28e+00

Pos logit contributions
poke+0.124
horse+0.120
plate+0.117
 Hawth+0.111
 Trafford+0.111
Neg logit contributions
 tremend-0.112
 streng-0.095
aughs-0.091
utical-0.088
 Libre-0.083
Token career
Token ID3451
Feature activation-4.36e+00

Pos logit contributions
poke+1.415
horse+1.359
plate+1.281
 Hawth+1.229
 Trafford+1.203
Neg logit contributions
 tremend-2.586
 streng-2.257
aughs-2.185
utical-2.148
 toget-2.051
Token Fiorina
Token ID49028
Feature activation-7.54e+00

Pos logit contributions
poke+1.533
horse+1.444
plate+1.316
 Hawth+1.168
 Trafford+1.131
Neg logit contributions
 tremend-5.974
 streng-5.463
aughs-5.217
utical-5.210
 toget-5.034
Token concedes
Token ID49867
Feature activation-2.21e+00

Pos logit contributions
poke+4.681
plate+4.480
horse+4.475
 Hawth+4.100
 Trafford+3.935
Neg logit contributions
 tremend-7.984
 streng-6.945
utical-6.742
aughs-6.726
sembly-6.432
Token Morgan
Token ID10805
Feature activation-1.84e+00

Pos logit contributions
poke+0.049
horse+0.047
plate+0.045
 Hawth+0.042
 Trafford+0.042
Neg logit contributions
 tremend-0.070
 streng-0.062
aughs-0.060
utical-0.060
 Libre-0.057
Token have
Token ID423
Feature activation-9.08e-01

Pos logit contributions
poke+1.361
horse+1.308
plate+1.249
 Hawth+1.190
 Trafford+1.184
Neg logit contributions
 tremend-1.798
 streng-1.570
aughs-1.515
utical-1.503
 Libre-1.433
Token clashed
Token ID37003
Feature activation-1.44e+00

Pos logit contributions
poke+0.681
horse+0.660
plate+0.636
 Hawth+0.601
 Trafford+0.598
Neg logit contributions
 tremend-0.875
 streng-0.757
aughs-0.742
utical-0.738
 Libre-0.697
Token in
Token ID287
Feature activation-4.99e-01

Pos logit contributions
poke+0.957
horse+0.921
plate+0.879
 Hawth+0.821
 Trafford+0.819
Neg logit contributions
 tremend-1.511
 streng-1.342
aughs-1.309
utical-1.291
 Libre-1.235
Token a
Token ID257
Feature activation+1.14e-01

Pos logit contributions
poke+0.354
horse+0.341
plate+0.324
 Trafford+0.308
 Hawth+0.307
Neg logit contributions
 tremend-0.501
 streng-0.443
aughs-0.431
utical-0.424
 Libre-0.405
Token sexism
Token ID24953
Feature activation-8.02e+00

Pos logit contributions
 tremend+0.120
 streng+0.107
aughs+0.105
utical+0.103
 Libre+0.098
Neg logit contributions
poke-0.076
horse-0.073
plate-0.069
 Trafford-0.065
 Hawth-0.065
Token row
Token ID5752
Feature activation-1.71e+00

Pos logit contributions
poke+5.094
horse+4.923
plate+4.647
grid+4.253
 Trafford+4.210
Neg logit contributions
 tremend-8.424
 streng-7.415
aughs-7.395
utical-7.245
 Libre-6.823
Token.
Token ID13
Feature activation-4.01e-01

Pos logit contributions
poke+1.154
horse+1.118
plate+1.062
 Trafford+0.995
 Hawth+0.992
Neg logit contributions
 tremend-1.769
 streng-1.571
aughs-1.529
utical-1.510
 Libre-1.438
Token
Token ID198
Feature activation-7.23e-01

Pos logit contributions
poke+0.310
horse+0.300
plate+0.286
 Trafford+0.274
 Hawth+0.273
Neg logit contributions
 tremend-0.383
 streng-0.333
aughs-0.319
utical-0.316
 Libre-0.299
Token
Token ID198
Feature activation-6.40e-01

Pos logit contributions
poke+0.553
horse+0.535
plate+0.513
 Hawth+0.483
 Trafford+0.478
Neg logit contributions
 tremend-0.736
 streng-0.635
aughs-0.596
utical-0.582
 toget-0.559
TokenSus
Token ID30746
Feature activation+4.48e+00

Pos logit contributions
poke+0.519
horse+0.502
plate+0.479
 Trafford+0.449
fleet+0.448
Neg logit contributions
 tremend-0.604
 streng-0.522
aughs-0.494
utical-0.489
 Libre-0.464
Token of
Token ID286
Feature activation-1.07e+00

Pos logit contributions
 tremend+0.079
 streng+0.070
aughs+0.066
utical+0.065
 Libre+0.062
Neg logit contributions
poke-0.058
horse-0.056
plate-0.053
 Hawth-0.050
 Trafford-0.050
Token 15
Token ID1315
Feature activation-1.29e-01

Pos logit contributions
poke+0.830
horse+0.802
plate+0.767
 Hawth+0.735
 Trafford+0.724
Neg logit contributions
 tremend-1.063
 streng-0.918
aughs-0.865
utical-0.848
 toget-0.808
Token Photos
Token ID9434
Feature activation-5.06e-01

Pos logit contributions
poke+0.085
horse+0.082
plate+0.078
 Hawth+0.074
 Trafford+0.073
Neg logit contributions
 tremend-0.141
 streng-0.125
aughs-0.118
utical-0.116
 toget-0.111
Token:
Token ID25
Feature activation-1.68e+00

Pos logit contributions
poke+0.312
horse+0.298
plate+0.282
 Trafford+0.262
 Hawth+0.262
Neg logit contributions
 tremend-0.560
 streng-0.500
aughs-0.484
utical-0.477
 Libre-0.459
Token Carly
Token ID35982
Feature activation-4.96e+00

Pos logit contributions
poke+0.989
horse+0.948
plate+0.899
 Hawth+0.852
 Trafford+0.827
Neg logit contributions
 tremend-1.975
 streng-1.754
aughs-1.657
utical-1.615
 toget-1.568
Token Fiorina
Token ID49028
Feature activation-7.97e+00

Pos logit contributions
poke+1.128
horse+1.057
plate+0.959
 Hawth+0.808
 Trafford+0.678
Neg logit contributions
 tremend-7.682
 streng-6.997
aughs-6.612
utical-6.467
 toget-6.428
Token's
Token ID338
Feature activation-2.26e-01

Pos logit contributions
poke+4.880
horse+4.778
plate+4.560
 Hawth+4.227
 Trafford+3.941
Neg logit contributions
 tremend-9.928
 streng-8.495
sembly-7.741
 newcom-7.729
aughs-7.553
Token political
Token ID1964
Feature activation-2.49e+00

Pos logit contributions
poke+0.207
horse+0.201
plate+0.195
 Hawth+0.186
 Trafford+0.185
Neg logit contributions
 tremend-0.184
 streng-0.156
aughs-0.150
utical-0.146
 Libre-0.138
Token career
Token ID3451
Feature activation-4.56e+00

Pos logit contributions
poke+1.536
horse+1.476
plate+1.393
 Hawth+1.339
 Trafford+1.306
Neg logit contributions
 tremend-2.819
 streng-2.459
aughs-2.380
utical-2.339
 toget-2.233
Token Box
Token ID8315
Feature activation+6.96e-01

Pos logit contributions
poke+1.625
horse+1.530
plate+1.410
 Hawth+1.259
 Trafford+1.206
Neg logit contributions
 tremend-6.226
 streng-5.679
utical-5.415
aughs-5.412
 toget-5.221
Tokener
Token ID263
Feature activation+4.11e-01

Pos logit contributions
 tremend+0.484
 streng+0.400
aughs+0.373
utical+0.366
 Libre+0.339
Neg logit contributions
poke-0.724
horse-0.705
plate-0.685
 Trafford-0.654
 Hawth-0.652
Token threatened
Token ID8556
Feature activation-1.67e+00

Pos logit contributions
 tremend+0.210
 streng+0.183
aughs+0.179
utical+0.176
 Libre+0.168
Neg logit contributions
poke-0.157
horse-0.151
plate-0.145
 Hawth-0.137
 Trafford-0.136
Token to
Token ID284
Feature activation-3.14e-01

Pos logit contributions
poke+1.129
horse+1.079
plate+1.023
 Hawth+0.966
 Trafford+0.961
Neg logit contributions
 tremend-1.732
 streng-1.537
aughs-1.484
utical-1.481
 Libre-1.410
Token walk
Token ID2513
Feature activation-1.20e+00

Pos logit contributions
poke+0.246
horse+0.235
plate+0.225
 Hawth+0.217
 Trafford+0.212
Neg logit contributions
 tremend-0.294
 streng-0.255
aughs-0.253
utical-0.251
 Libre-0.231
Token out
Token ID503
Feature activation+3.87e-01

Pos logit contributions
poke+0.776
horse+0.748
plate+0.705
 Hawth+0.664
grid+0.647
Neg logit contributions
 tremend-1.303
 streng-1.155
aughs-1.108
utical-1.106
 Libre-1.054
Token if
Token ID611
Feature activation-4.91e-01

Pos logit contributions
 tremend+0.385
 streng+0.339
aughs+0.329
utical+0.324
 Libre+0.310
Neg logit contributions
poke-0.280
horse-0.269
plate-0.257
 Hawth-0.243
 Trafford-0.242
Token Milo
Token ID32662
Feature activation-7.91e+00

Pos logit contributions
poke+0.326
horse+0.313
plate+0.298
 Hawth+0.279
 Trafford+0.279
Neg logit contributions
 tremend-0.516
 streng-0.458
aughs-0.444
utical-0.439
 Libre-0.420
Token was
Token ID373
Feature activation-3.53e-01

Pos logit contributions
poke+5.020
horse+4.795
plate+4.663
 Hawth+4.478
 Trafford+4.236
Neg logit contributions
 tremend-8.442
 streng-7.201
utical-7.026
aughs-6.868
sembly-6.729
Token not
Token ID407
Feature activation-1.81e+00

Pos logit contributions
poke+0.227
horse+0.218
plate+0.207
 Hawth+0.196
 Trafford+0.193
Neg logit contributions
 tremend-0.380
 streng-0.336
aughs-0.329
utical-0.325
 Libre-0.309
Token let
Token ID1309
Feature activation-6.30e-01

Pos logit contributions
poke+1.205
horse+1.164
plate+1.099
 Hawth+1.051
 Trafford+1.035
Neg logit contributions
 tremend-1.902
 streng-1.661
aughs-1.640
utical-1.619
 Libre-1.529
Token go
Token ID467
Feature activation+2.94e-01

Pos logit contributions
poke+0.426
horse+0.406
plate+0.386
 Hawth+0.364
 Trafford+0.363
Neg logit contributions
 tremend-0.659
 streng-0.581
aughs-0.566
utical-0.558
 Libre-0.534
Token.
Token ID13
Feature activation-3.21e-01

Pos logit contributions
 tremend+0.297
 streng+0.263
aughs+0.255
utical+0.251
 Libre+0.241
Neg logit contributions
poke-0.207
horse-0.199
plate-0.190
 Trafford-0.179
 Hawth-0.178
Tokening
Token ID278
Feature activation+2.98e-01

Pos logit contributions
poke+0.057
horse+0.054
plate+0.053
 Trafford+0.049
fleet+0.049
Neg logit contributions
 tremend-0.072
 streng-0.063
aughs-0.061
utical-0.060
 Libre-0.057
Token |
Token ID930
Feature activation+5.00e-01

Pos logit contributions
 tremend+0.290
 streng+0.255
aughs+0.247
utical+0.243
 Libre+0.231
Neg logit contributions
poke-0.222
horse-0.214
plate-0.205
 Trafford-0.194
 Hawth-0.193
Token Create
Token ID13610
Feature activation+5.03e-01

Pos logit contributions
 tremend+0.481
 streng+0.422
aughs+0.409
utical+0.401
 Libre+0.382
Neg logit contributions
poke-0.378
horse-0.364
plate-0.349
 Trafford-0.331
 Hawth-0.331
Token your
Token ID534
Feature activation+1.78e+00

Pos logit contributions
 tremend+0.490
 streng+0.431
aughs+0.417
utical+0.411
 Libre+0.391
Neg logit contributions
poke-0.374
horse-0.360
plate-0.345
 Trafford-0.327
 Hawth-0.326
Token own
Token ID898
Feature activation-1.70e+00

Pos logit contributions
 tremend+1.371
 streng+1.166
aughs+1.121
utical+1.095
 Libre+1.034
Neg logit contributions
poke-1.677
horse-1.626
plate-1.573
 Trafford-1.506
 Hawth-1.503
Token warp
Token ID25825
Feature activation-7.88e+00

Pos logit contributions
poke+1.244
horse+1.187
plate+1.147
 Trafford+1.087
 Hawth+1.085
Neg logit contributions
 tremend-1.671
 streng-1.466
aughs-1.428
utical-1.406
 Libre-1.320
Token drive
Token ID3708
Feature activation-5.05e+00

Pos logit contributions
poke+5.915
horse+5.797
plate+5.594
fleet+5.291
grid+5.237
Neg logit contributions
 tremend-7.286
 streng-6.294
utical-6.198
aughs-6.195
 Libre-5.758
Token website
Token ID3052
Feature activation-1.23e+00

Pos logit contributions
poke+3.678
horse+3.546
plate+3.448
fleet+3.275
 Hawth+3.233
Neg logit contributions
 tremend-4.917
 streng-4.253
aughs-4.209
utical-4.128
 Libre-3.831
Token for
Token ID329
Feature activation+1.17e+00

Pos logit contributions
poke+0.872
horse+0.837
plate+0.806
 Hawth+0.755
 Trafford+0.755
Neg logit contributions
 tremend-1.244
 streng-1.097
aughs-1.070
utical-1.047
 Libre-0.995
Token your
Token ID534
Feature activation+1.68e+00

Pos logit contributions
 tremend+1.074
 streng+0.938
aughs+0.910
utical+0.893
 Libre+0.849
Neg logit contributions
poke-0.929
horse-0.895
plate-0.859
 Trafford-0.817
 Hawth-0.817
Token business
Token ID1597
Feature activation-8.24e-01

Pos logit contributions
 tremend+1.564
 streng+1.370
aughs+1.327
utical+1.303
 Libre+1.245
Neg logit contributions
poke-1.319
horse-1.271
plate-1.219
 Trafford-1.156
 Hawth-1.153
Token Carly
Token ID35982
Feature activation-3.31e+00

Pos logit contributions
poke+0.832
horse+0.801
plate+0.763
 Trafford+0.723
 Hawth+0.723
Neg logit contributions
 tremend-1.219
 streng-1.079
aughs-1.041
utical-1.024
 Libre-0.980
Token Fiorina
Token ID49028
Feature activation-8.77e+00

Pos logit contributions
poke+1.195
horse+1.096
plate+1.026
 Hawth+0.897
 Trafford+0.879
Neg logit contributions
 tremend-4.470
 streng-4.091
aughs-3.996
utical-3.912
 Libre-3.832
Token's
Token ID338
Feature activation-3.75e-01

Pos logit contributions
poke+5.760
horse+5.603
plate+5.571
 Hawth+5.225
 Trafford+4.951
Neg logit contributions
 tremend-8.553
 streng-7.559
aughs-7.421
utical-7.308
sembly-7.000
Token political
Token ID1964
Feature activation-2.37e+00

Pos logit contributions
poke+0.277
horse+0.267
plate+0.256
 Hawth+0.242
 Trafford+0.241
Neg logit contributions
 tremend-0.365
 streng-0.322
aughs-0.313
utical-0.307
 Libre-0.294
Token career
Token ID3451
Feature activation-3.90e+00

Pos logit contributions
poke+1.799
horse+1.737
plate+1.661
 Hawth+1.571
 Trafford+1.569
Neg logit contributions
 tremend-2.257
 streng-1.981
aughs-1.922
utical-1.888
 Libre-1.807
Token Fiorina
Token ID49028
Feature activation-7.88e+00

Pos logit contributions
poke+2.192
horse+2.124
plate+2.010
 Hawth+1.872
 Trafford+1.833
Neg logit contributions
 tremend-4.461
 streng-4.000
aughs-3.871
utical-3.852
 Libre-3.650
Token,
Token ID11
Feature activation-1.03e+00

Pos logit contributions
poke+5.077
horse+4.969
plate+4.921
 Hawth+4.558
 Dover+4.325
Neg logit contributions
 tremend-8.021
 streng-7.030
utical-6.819
aughs-6.803
sembly-6.484
Token right
Token ID826
Feature activation-8.70e-01

Pos logit contributions
poke+0.766
horse+0.742
plate+0.712
 Hawth+0.679
 Trafford+0.671
Neg logit contributions
 tremend-1.004
 streng-0.882
aughs-0.859
utical-0.841
 Libre-0.800
Token,
Token ID11
Feature activation-6.44e-01

Pos logit contributions
poke+0.589
horse+0.562
plate+0.536
 Trafford+0.505
 Hawth+0.501
Neg logit contributions
 tremend-0.897
 streng-0.798
aughs-0.778
utical-0.765
 Libre-0.740
Token poses
Token ID17313
Feature activation-1.04e+00

Pos logit contributions
poke+0.440
horse+0.422
plate+0.404
 Hawth+0.379
 Trafford+0.377
Neg logit contributions
 tremend-0.663
 streng-0.588
aughs-0.571
utical-0.563
 Libre-0.541
Token for
Token ID329
Feature activation+1.20e+00

Pos logit contributions
poke+0.689
horse+0.660
plate+0.630
 Hawth+0.588
 Trafford+0.587
Neg logit contributions
 tremend-1.093
 streng-0.972
aughs-0.945
utical-0.929
 Libre-0.894
Token that
Token ID326
Feature activation-2.96e-01

Pos logit contributions
poke+0.395
horse+0.377
plate+0.361
 Hawth+0.338
 Trafford+0.337
Neg logit contributions
 tremend-0.618
 streng-0.550
aughs-0.535
utical-0.526
 Libre-0.501
Token because
Token ID780
Feature activation-1.06e+00

Pos logit contributions
poke+0.208
horse+0.200
plate+0.191
 Hawth+0.180
 Trafford+0.180
Neg logit contributions
 tremend-0.300
 streng-0.266
aughs-0.259
utical-0.255
 Libre-0.242
Token one
Token ID530
Feature activation-5.04e-01

Pos logit contributions
poke+0.727
horse+0.700
plate+0.671
 Hawth+0.631
 Trafford+0.628
Neg logit contributions
 tremend-1.088
 streng-0.963
aughs-0.942
utical-0.919
 Libre-0.873
Token of
Token ID286
Feature activation-7.40e-01

Pos logit contributions
poke+0.354
horse+0.342
plate+0.326
 Hawth+0.307
 Trafford+0.305
Neg logit contributions
 tremend-0.511
 streng-0.451
aughs-0.440
utical-0.431
 Libre-0.412
Token my
Token ID616
Feature activation+1.05e+00

Pos logit contributions
poke+0.585
horse+0.564
plate+0.539
 Hawth+0.514
 Trafford+0.513
Neg logit contributions
 tremend-0.686
 streng-0.600
aughs-0.580
utical-0.569
 Libre-0.541
Token tweets
Token ID12665
Feature activation-7.85e+00

Pos logit contributions
 tremend+0.934
 streng+0.809
aughs+0.782
utical+0.769
 Libre+0.728
Neg logit contributions
poke-0.872
horse-0.845
plate-0.812
 Trafford-0.776
 Hawth-0.775
Token asking
Token ID4737
Feature activation-2.80e+00

Pos logit contributions
poke+5.202
horse+4.958
plate+4.689
 Hawth+4.356
fleet+4.287
Neg logit contributions
 tremend-8.063
aughs-7.035
utical-6.967
 streng-6.938
 Libre-6.488
Token "
Token ID366
Feature activation-1.26e-01

Pos logit contributions
poke+1.935
horse+1.838
plate+1.739
 Trafford+1.659
 Hawth+1.649
Neg logit contributions
 tremend-2.897
 streng-2.557
aughs-2.496
utical-2.449
 Libre-2.314
Tokenwhen
Token ID12518
Feature activation-1.25e+00

Pos logit contributions
poke+0.103
horse+0.100
plate+0.095
fleet+0.090
 Trafford+0.089
Neg logit contributions
 tremend-0.115
 streng-0.099
aughs-0.096
utical-0.094
 Libre-0.090
Token Sam
Token ID3409
Feature activation+1.62e+00

Pos logit contributions
poke+0.849
horse+0.810
plate+0.769
 Trafford+0.730
 Hawth+0.725
Neg logit contributions
 tremend-1.304
 streng-1.145
aughs-1.119
utical-1.100
 Libre-1.038
Token Bac
Token ID35583
Feature activation+2.92e+00

Pos logit contributions
 tremend+1.635
 streng+1.455
aughs+1.415
utical+1.389
 Libre+1.339
Neg logit contributions
poke-1.131
horse-1.091
plate-1.044
 Trafford-0.972
 Hawth-0.970
Token a
Token ID257
Feature activation-6.48e-01

Pos logit contributions
poke+0.800
horse+0.770
plate+0.732
 Hawth+0.693
 Trafford+0.690
Neg logit contributions
 tremend-1.092
 streng-0.963
utical-0.926
aughs-0.925
 Libre-0.875
Token Rolling
Token ID21567
Feature activation+1.39e+00

Pos logit contributions
poke+0.487
horse+0.468
plate+0.449
 Hawth+0.429
 Trafford+0.422
Neg logit contributions
 tremend-0.626
 streng-0.549
utical-0.535
aughs-0.532
 Libre-0.497
Token Stone
Token ID8026
Feature activation-1.78e+00

Pos logit contributions
 tremend+1.612
 streng+1.430
aughs+1.367
utical+1.362
 toget+1.293
Neg logit contributions
poke-0.836
horse-0.806
plate-0.756
 Trafford-0.708
 Hawth-0.705
Token reporter
Token ID9095
Feature activation+1.76e-01

Pos logit contributions
poke+1.380
horse+1.345
plate+1.284
 Hawth+1.217
 Trafford+1.196
Neg logit contributions
 tremend-1.664
 streng-1.443
utical-1.423
aughs-1.388
 Libre-1.290
Token as
Token ID355
Feature activation-1.38e+00

Pos logit contributions
 tremend+0.180
 streng+0.160
aughs+0.155
utical+0.153
 Libre+0.147
Neg logit contributions
poke-0.121
horse-0.117
plate-0.111
 Trafford-0.104
 Hawth-0.104
Token Fiorina
Token ID49028
Feature activation-7.84e+00

Pos logit contributions
poke+0.893
horse+0.845
plate+0.811
 Hawth+0.758
 Trafford+0.751
Neg logit contributions
 tremend-1.482
 streng-1.314
utical-1.274
aughs-1.269
 Libre-1.201
Token appeared
Token ID4120
Feature activation+6.34e-01

Pos logit contributions
poke+5.229
plate+5.025
horse+4.975
 Hawth+4.566
 Trafford+4.370
Neg logit contributions
 tremend-8.051
utical-6.907
 streng-6.809
aughs-6.777
sembly-6.338
Token on
Token ID319
Feature activation+3.63e-01

Pos logit contributions
 tremend+0.661
 streng+0.589
aughs+0.572
utical+0.562
 Libre+0.543
Neg logit contributions
poke-0.425
horse-0.406
plate-0.385
 Trafford-0.364
 Hawth-0.361
Token TV
Token ID3195
Feature activation+2.62e+00

Pos logit contributions
 tremend+0.361
 streng+0.319
aughs+0.308
utical+0.305
 Libre+0.291
Neg logit contributions
poke-0.262
horse-0.252
plate-0.240
 Hawth-0.227
 Trafford-0.226
Token.
Token ID13
Feature activation-4.20e-01

Pos logit contributions
 tremend+2.656
 streng+2.360
aughs+2.284
utical+2.234
 Libre+2.179
Neg logit contributions
poke-1.809
horse-1.723
plate-1.647
 Trafford-1.563
 Hawth-1.549
Token "
Token ID366
Feature activation+1.36e+00

Pos logit contributions
poke+0.295
horse+0.284
plate+0.271
 Trafford+0.255
 Hawth+0.253
Neg logit contributions
 tremend-0.420
 streng-0.373
aughs-0.365
utical-0.358
 Libre-0.345
Token35
Token ID2327
Feature activation+1.22e+00

Pos logit contributions
poke+0.147
horse+0.143
plate+0.138
 Hawth+0.133
 Trafford+0.131
Neg logit contributions
 tremend-0.166
 streng-0.140
aughs-0.130
utical-0.128
 toget-0.121
Token p
Token ID279
Feature activation-2.56e+00

Pos logit contributions
 tremend+1.214
 streng+1.076
aughs+1.047
utical+1.025
 Libre+0.994
Neg logit contributions
poke-0.856
horse-0.822
plate-0.786
 Trafford-0.743
 Hawth-0.735
Token.
Token ID13
Feature activation-5.77e-01

Pos logit contributions
poke+1.673
horse+1.606
plate+1.523
 Hawth+1.423
 Trafford+1.389
Neg logit contributions
 tremend-2.943
 streng-2.584
aughs-2.410
utical-2.348
 toget-2.293
Tokenm
Token ID76
Feature activation-3.18e+00

Pos logit contributions
poke+0.393
horse+0.378
plate+0.359
 Trafford+0.334
 Hawth+0.334
Neg logit contributions
 tremend-0.621
 streng-0.548
aughs-0.521
utical-0.512
 toget-0.490
Token.:
Token ID11207
Feature activation-7.59e-01

Pos logit contributions
poke+2.355
horse+2.257
plate+2.167
 Trafford+2.049
 Hawth+2.036
Neg logit contributions
 tremend-3.090
 streng-2.721
aughs-2.656
utical-2.603
 Libre-2.502
Token Milo
Token ID32662
Feature activation-7.83e+00

Pos logit contributions
poke+0.528
horse+0.507
plate+0.485
 Hawth+0.460
 Trafford+0.457
Neg logit contributions
 tremend-0.786
 streng-0.693
aughs-0.662
utical-0.657
 Libre-0.623
Token has
Token ID468
Feature activation-7.54e-01

Pos logit contributions
poke+5.058
horse+4.897
plate+4.785
 Hawth+4.550
 Trafford+4.398
Neg logit contributions
 tremend-7.904
 streng-6.874
utical-6.623
aughs-6.563
sembly-6.256
Token resigned
Token ID16542
Feature activation-1.47e+00

Pos logit contributions
poke+0.549
horse+0.531
plate+0.516
 Hawth+0.484
 Trafford+0.478
Neg logit contributions
 tremend-0.745
 streng-0.645
aughs-0.632
utical-0.629
 Libre-0.592
Token.
Token ID13
Feature activation-4.56e-01

Pos logit contributions
poke+0.841
horse+0.801
plate+0.758
 Hawth+0.705
 Trafford+0.699
Neg logit contributions
 tremend-1.687
 streng-1.513
aughs-1.476
utical-1.457
 Libre-1.397
Token
Token ID198
Feature activation-1.94e-01

Pos logit contributions
poke+0.333
horse+0.320
plate+0.306
 Hawth+0.291
 Trafford+0.291
Neg logit contributions
 tremend-0.458
 streng-0.401
aughs-0.382
utical-0.378
 Libre-0.358
Token
Token ID198
Feature activation-4.36e-02

Pos logit contributions
poke+0.150
horse+0.144
plate+0.139
 Hawth+0.130
 Trafford+0.129
Neg logit contributions
 tremend-0.193
 streng-0.167
aughs-0.157
utical-0.154
 toget-0.147
Token Jamaica
Token ID31620
Feature activation+4.83e+00

Pos logit contributions
poke+0.251
horse+0.242
plate+0.231
 Trafford+0.219
 Hawth+0.218
Neg logit contributions
 tremend-0.321
 streng-0.282
aughs-0.274
utical-0.269
 Libre-0.258
Token.
Token ID13
Feature activation-1.52e-01

Pos logit contributions
 tremend+4.482
 streng+4.047
aughs+3.893
utical+3.828
 Libre+3.733
Neg logit contributions
poke-3.572
horse-3.358
plate-3.230
 Trafford-3.053
fleet-3.048
Token Credit
Token ID10504
Feature activation-5.65e-01

Pos logit contributions
poke+0.110
horse+0.105
plate+0.101
 Trafford+0.095
 Hawth+0.095
Neg logit contributions
 tremend-0.152
 streng-0.134
aughs-0.129
utical-0.127
 Libre-0.122
Token:
Token ID25
Feature activation-4.29e-01

Pos logit contributions
poke+0.334
horse+0.322
plate+0.303
 Hawth+0.283
 Trafford+0.280
Neg logit contributions
 tremend-0.656
 streng-0.582
aughs-0.558
utical-0.549
 toget-0.525
TokenAP
Token ID2969
Feature activation-6.01e-02

Pos logit contributions
poke+0.316
horse+0.304
plate+0.291
 Trafford+0.275
 Hawth+0.274
Neg logit contributions
 tremend-0.419
 streng-0.369
aughs-0.358
utical-0.352
 Libre-0.337
Token Cuban
Token ID18147
Feature activation+5.37e+00

Pos logit contributions
poke+0.043
horse+0.042
plate+0.040
 Hawth+0.038
 Trafford+0.038
Neg logit contributions
 tremend-0.060
 streng-0.053
aughs-0.051
utical-0.050
 Libre-0.048
Token authorities
Token ID4773
Feature activation+8.46e-01

Pos logit contributions
 tremend+5.128
 streng+4.563
aughs+4.401
utical+4.293
 Libre+4.237
Neg logit contributions
poke-3.980
horse-3.825
plate-3.646
 Hawth-3.440
 Trafford-3.433
Token organised
Token ID20325
Feature activation+1.42e+00

Pos logit contributions
 tremend+0.841
 streng+0.735
aughs+0.720
utical+0.706
 Libre+0.674
Neg logit contributions
poke-0.616
horse-0.592
plate-0.567
 Hawth-0.533
 Trafford-0.533
Token a
Token ID257
Feature activation+3.44e-01

Pos logit contributions
 tremend+1.390
 streng+1.231
aughs+1.188
utical+1.169
 Libre+1.130
Neg logit contributions
poke-1.036
horse-0.993
plate-0.949
 Trafford-0.897
 Hawth-0.893
Token mass
Token ID2347
Feature activation+1.03e+00

Pos logit contributions
 tremend+0.333
 streng+0.292
aughs+0.286
utical+0.280
 Libre+0.266
Neg logit contributions
poke-0.257
horse-0.248
plate-0.237
 Trafford-0.224
 Hawth-0.224
Token exodus
Token ID39524
Feature activation-3.14e+00

Pos logit contributions
 tremend+0.773
 streng+0.654
aughs+0.630
utical+0.613
 Libre+0.577
Neg logit contributions
poke-0.997
horse-0.969
plate-0.937
 Trafford-0.897
 Hawth-0.895
Token co
Token ID763
Feature activation-7.76e-01

Pos logit contributions
 tremend+0.605
 streng+0.524
aughs+0.511
utical+0.503
 Libre+0.476
Neg logit contributions
poke-0.532
horse-0.515
plate-0.496
 Hawth-0.473
 Trafford-0.470
Token-
Token ID12
Feature activation+1.09e+00

Pos logit contributions
poke+0.622
horse+0.604
plate+0.581
 Trafford+0.546
fleet+0.544
Neg logit contributions
 tremend-0.707
 streng-0.617
aughs-0.594
utical-0.584
 Libre-0.559
Tokenop
Token ID404
Feature activation+1.19e-01

Pos logit contributions
 tremend+1.074
 streng+0.948
aughs+0.919
utical+0.903
 Libre+0.868
Neg logit contributions
poke-0.799
horse-0.770
plate-0.736
 Trafford-0.693
 Hawth-0.690
Tokenting
Token ID889
Feature activation-5.43e-01

Pos logit contributions
 tremend+0.126
 streng+0.112
aughs+0.109
utical+0.107
 Libre+0.103
Neg logit contributions
poke-0.078
horse-0.074
plate-0.071
 Hawth-0.066
 Trafford-0.066
Token of
Token ID286
Feature activation+6.25e-02

Pos logit contributions
poke+0.418
horse+0.401
plate+0.384
 Trafford+0.366
 Hawth+0.363
Neg logit contributions
 tremend-0.515
 streng-0.451
aughs-0.438
utical-0.431
 Libre-0.412
Token punk
Token ID22782
Feature activation+4.38e+00

Pos logit contributions
 tremend+0.058
 streng+0.051
aughs+0.049
utical+0.048
 Libre+0.046
Neg logit contributions
poke-0.049
horse-0.047
plate-0.046
 Hawth-0.044
 Trafford-0.043
Token fashion
Token ID6977
Feature activation+4.72e-01

Pos logit contributions
 tremend+4.226
 streng+3.735
aughs+3.621
utical+3.563
 Libre+3.424
Neg logit contributions
poke-3.237
horse-3.100
plate-2.957
 Trafford-2.819
 Hawth-2.795
Token by
Token ID416
Feature activation+1.15e+00

Pos logit contributions
 tremend+0.492
 streng+0.438
aughs+0.426
utical+0.419
 Libre+0.402
Neg logit contributions
poke-0.316
horse-0.304
plate-0.290
 Trafford-0.271
 Hawth-0.270
Token popular
Token ID2968
Feature activation+2.79e+00

Pos logit contributions
 tremend+1.075
 streng+0.940
aughs+0.913
utical+0.895
 Libre+0.853
Neg logit contributions
poke-0.893
horse-0.861
plate-0.827
 Hawth-0.788
 Trafford-0.786
Token designers
Token ID15441
Feature activation-1.49e+00

Pos logit contributions
 tremend+2.502
 streng+2.179
aughs+2.105
utical+2.067
 Libre+1.975
Neg logit contributions
poke-2.281
horse-2.205
plate-2.120
 Trafford-2.012
 Hawth-2.008
Token and
Token ID290
Feature activation+4.33e-02

Pos logit contributions
poke+0.973
horse+0.938
plate+0.893
 Trafford+0.837
 Hawth+0.835
Neg logit contributions
 tremend-1.571
 streng-1.398
aughs-1.369
utical-1.338
 Libre-1.284
Token down
Token ID866
Feature activation+8.06e-01

Pos logit contributions
poke+0.230
horse+0.220
plate+0.211
 Hawth+0.196
 Trafford+0.196
Neg logit contributions
 tremend-0.352
 streng-0.312
aughs-0.302
utical-0.299
 Libre-0.286
Token the
Token ID262
Feature activation+5.02e-01

Pos logit contributions
 tremend+0.780
 streng+0.685
aughs+0.664
utical+0.653
 Libre+0.623
Neg logit contributions
poke-0.604
horse-0.583
plate-0.560
 Hawth-0.525
 Trafford-0.525
Token momentum
Token ID12858
Feature activation-3.03e-01

Pos logit contributions
 tremend+0.454
 streng+0.395
aughs+0.384
utical+0.377
 Libre+0.355
Neg logit contributions
poke-0.407
horse-0.393
plate-0.379
 Hawth-0.360
 Trafford-0.358
Token of
Token ID286
Feature activation+4.70e-01

Pos logit contributions
poke+0.225
horse+0.216
plate+0.207
 Trafford+0.196
 Hawth+0.195
Neg logit contributions
 tremend-0.294
 streng-0.259
aughs-0.251
utical-0.247
 Libre-0.238
Token popular
Token ID2968
Feature activation+3.63e+00

Pos logit contributions
 tremend+0.437
 streng+0.381
aughs+0.370
utical+0.364
 Libre+0.344
Neg logit contributions
poke-0.368
horse-0.356
plate-0.343
 Hawth-0.324
 Trafford-0.324
Token reform
Token ID4975
Feature activation+4.28e+00

Pos logit contributions
 tremend+2.839
 streng+2.448
aughs+2.341
utical+2.293
 Libre+2.202
Neg logit contributions
poke-3.346
horse-3.226
plate-3.115
 Trafford-2.986
 Hawth-2.972
Token movements
Token ID8650
Feature activation+8.62e-01

Pos logit contributions
 tremend+4.081
 streng+3.611
aughs+3.495
utical+3.428
 Libre+3.320
Neg logit contributions
poke-3.201
horse-3.056
plate-2.934
 Trafford-2.799
 Hawth-2.779
Token.
Token ID13
Feature activation+8.55e-01

Pos logit contributions
 tremend+0.896
 streng+0.798
aughs+0.775
utical+0.763
 Libre+0.735
Neg logit contributions
poke-0.579
horse-0.555
plate-0.529
 Trafford-0.496
 Hawth-0.494
Token Israel
Token ID2692
Feature activation+1.72e+00

Pos logit contributions
 tremend+0.825
 streng+0.715
aughs+0.682
utical+0.668
 toget+0.631
Neg logit contributions
poke-0.663
horse-0.645
plate-0.617
 Hawth-0.590
 Trafford-0.590
Token found
Token ID1043
Feature activation+2.36e+00

Pos logit contributions
 tremend+1.726
 streng+1.529
aughs+1.484
utical+1.459
 Libre+1.404
Neg logit contributions
poke-1.219
horse-1.171
plate-1.117
 Trafford-1.053
 Hawth-1.049
Token the
Token ID262
Feature activation+8.58e-01

Pos logit contributions
 tremend+2.236
 streng+1.967
aughs+1.903
utical+1.870
 Libre+1.795
Neg logit contributions
poke-1.808
horse-1.741
plate-1.667
 Trafford-1.579
 Hawth-1.573
Token his
Token ID465
Feature activation+8.09e-01

Pos logit contributions
 tremend+1.940
 streng+1.715
aughs+1.661
utical+1.633
 Libre+1.571
Neg logit contributions
poke-1.449
horse-1.395
plate-1.333
 Trafford-1.257
 Hawth-1.252
Token two
Token ID734
Feature activation-1.51e+00

Pos logit contributions
 tremend+0.752
 streng+0.652
aughs+0.637
utical+0.625
 Libre+0.592
Neg logit contributions
poke-0.639
horse-0.617
plate-0.594
 Trafford-0.566
 Hawth-0.566
Token half
Token ID2063
Feature activation+4.86e-01

Pos logit contributions
poke+1.205
horse+1.160
plate+1.129
 Hawth+1.073
 Trafford+1.069
Neg logit contributions
 tremend-1.385
 streng-1.204
aughs-1.172
utical-1.139
 Libre-1.084
Token centuries
Token ID10675
Feature activation-1.08e+00

Pos logit contributions
 tremend+0.484
 streng+0.428
aughs+0.414
utical+0.407
 Libre+0.390
Neg logit contributions
poke-0.352
horse-0.338
plate-0.324
 Trafford-0.304
 Hawth-0.303
Token in
Token ID287
Feature activation-3.86e-01

Pos logit contributions
poke+0.716
horse+0.692
plate+0.664
 Hawth+0.620
 Trafford+0.618
Neg logit contributions
 tremend-1.139
 streng-1.002
aughs-0.983
utical-0.962
 Libre-0.921
Token Kingston
Token ID34612
Feature activation+4.94e+00

Pos logit contributions
poke+0.288
horse+0.276
plate+0.265
 Hawth+0.254
 Trafford+0.253
Neg logit contributions
 tremend-0.376
 streng-0.330
aughs-0.320
utical-0.315
 Libre-0.299
Token,
Token ID11
Feature activation-3.06e-02

Pos logit contributions
 tremend+5.005
 streng+4.472
aughs+4.336
utical+4.271
 Libre+4.129
Neg logit contributions
poke-3.358
horse-3.215
plate-3.041
 Hawth-2.849
 Trafford-2.848
Token Jamaica
Token ID31620
Feature activation+6.23e+00

Pos logit contributions
poke+0.022
horse+0.021
plate+0.020
 Hawth+0.019
 Trafford+0.019
Neg logit contributions
 tremend-0.031
 streng-0.027
aughs-0.027
utical-0.026
 Libre-0.025
Token in
Token ID287
Feature activation-9.38e-02

Pos logit contributions
 tremend+5.967
 streng+5.368
aughs+5.195
utical+5.148
 Libre+4.993
Neg logit contributions
poke-4.412
horse-4.192
plate-3.962
fleet-3.770
 Trafford-3.755
Token the
Token ID262
Feature activation+3.31e-01

Pos logit contributions
poke+0.072
horse+0.069
plate+0.067
 Hawth+0.064
 Trafford+0.064
Neg logit contributions
 tremend-0.090
 streng-0.078
aughs-0.076
utical-0.075
 Libre-0.071
Token 2006
Token ID4793
Feature activation+9.52e-01

Pos logit contributions
 tremend+0.319
 streng+0.278
aughs+0.271
utical+0.265
 Libre+0.251
Neg logit contributions
poke-0.251
horse-0.241
plate-0.232
 Hawth-0.223
 Trafford-0.223
Token rejected
Token ID8606
Feature activation+2.42e+00

Pos logit contributions
 tremend+0.278
 streng+0.243
aughs+0.238
utical+0.236
 Libre+0.223
Neg logit contributions
poke-0.200
horse-0.193
plate-0.185
 Hawth-0.175
 Trafford-0.172
Token his
Token ID465
Feature activation+3.72e-01

Pos logit contributions
 tremend+2.378
 streng+2.106
aughs+2.044
utical+2.004
 Libre+1.938
Neg logit contributions
poke-1.746
horse-1.673
plate-1.602
 Trafford-1.511
fleet-1.499
Token book
Token ID1492
Feature activation-4.95e-01

Pos logit contributions
 tremend+0.348
 streng+0.305
aughs+0.296
utical+0.292
 Libre+0.277
Neg logit contributions
poke-0.289
horse-0.280
plate-0.268
 Hawth-0.256
 Trafford-0.253
Token The
Token ID383
Feature activation-9.82e-01

Pos logit contributions
poke+0.326
horse+0.316
plate+0.302
 Hawth+0.284
 Trafford+0.280
Neg logit contributions
 tremend-0.522
 streng-0.464
aughs-0.450
utical-0.444
 Libre-0.425
Token Magic
Token ID6139
Feature activation-7.17e-01

Pos logit contributions
poke+0.739
horse+0.716
plate+0.683
 Hawth+0.653
 Trafford+0.651
Neg logit contributions
 tremend-0.949
 streng-0.833
aughs-0.800
utical-0.788
 Libre-0.750
Token Finger
Token ID39454
Feature activation+7.02e+00

Pos logit contributions
poke+0.569
horse+0.555
plate+0.531
 Hawth+0.503
 Trafford+0.501
Neg logit contributions
 tremend-0.669
 streng-0.584
aughs-0.555
utical-0.545
 Libre-0.519
Token,
Token ID11
Feature activation-1.19e-01

Pos logit contributions
 tremend+6.774
 streng+5.988
aughs+5.924
utical+5.765
 Libre+5.599
Neg logit contributions
poke-4.894
horse-4.628
plate-4.400
 Trafford-4.272
fleet-4.200
Token he
Token ID339
Feature activation-1.17e-01

Pos logit contributions
poke+0.085
horse+0.082
plate+0.078
 Hawth+0.075
 Trafford+0.074
Neg logit contributions
 tremend-0.119
 streng-0.105
aughs-0.102
utical-0.101
 Libre-0.096
Token would
Token ID561
Feature activation+1.23e+00

Pos logit contributions
poke+0.077
horse+0.074
plate+0.071
 Hawth+0.066
 Trafford+0.066
Neg logit contributions
 tremend-0.124
 streng-0.110
aughs-0.108
utical-0.106
 Libre-0.102
Token leave
Token ID2666
Feature activation-2.33e+00

Pos logit contributions
 tremend+1.176
 streng+1.031
aughs+1.006
utical+0.988
 Libre+0.940
Neg logit contributions
poke-0.935
horse-0.901
plate-0.864
 Hawth-0.818
 Trafford-0.814
Token them
Token ID606
Feature activation-2.67e-01

Pos logit contributions
poke+1.657
horse+1.605
plate+1.527
 Hawth+1.479
 Trafford+1.445
Neg logit contributions
 tremend-2.346
 streng-2.060
aughs-2.001
utical-1.969
 Libre-1.871
Token.
Token ID13
Feature activation-6.24e-01

Pos logit contributions
 tremend+0.896
 streng+0.795
aughs+0.772
utical+0.758
 Libre+0.731
Neg logit contributions
poke-0.613
horse-0.588
plate-0.561
 Trafford-0.528
 Hawth-0.526
Token
Token ID447
Feature activation+4.09e-01

Pos logit contributions
poke+0.485
horse+0.469
plate+0.448
 Hawth+0.429
 Trafford+0.427
Neg logit contributions
 tremend-0.597
 streng-0.520
aughs-0.497
utical-0.488
 Libre-0.460
Token
Token ID251
Feature activation-1.34e+00

Pos logit contributions
 tremend+0.368
 streng+0.322
aughs+0.311
utical+0.305
 Libre+0.292
Neg logit contributions
poke-0.331
horse-0.320
plate-0.307
 Trafford-0.292
 Hawth-0.291
Token V
Token ID569
Feature activation-1.16e+00

Pos logit contributions
poke+1.027
horse+0.986
plate+0.946
 Hawth+0.913
 Trafford+0.904
Neg logit contributions
 tremend-1.307
 streng-1.139
aughs-1.082
utical-1.066
 toget-1.004
Tokenini
Token ID5362
Feature activation-1.49e+00

Pos logit contributions
poke+1.087
horse+1.056
plate+1.022
fleet+0.975
grid+0.973
Neg logit contributions
 tremend-0.913
 streng-0.769
aughs-0.723
utical-0.718
 Libre-0.680
Tokenar
Token ID283
Feature activation+4.60e-01

Pos logit contributions
poke+1.598
horse+1.564
plate+1.519
 Hawth+1.450
grid+1.447
Neg logit contributions
 tremend-1.072
 streng-0.866
aughs-0.759
utical-0.735
 toget-0.709
Token summoned
Token ID20056
Feature activation-5.40e-01

Pos logit contributions
 tremend+0.477
 streng+0.424
aughs+0.412
utical+0.405
 Libre+0.390
Neg logit contributions
poke-0.311
horse-0.299
plate-0.284
 Trafford-0.267
 Hawth-0.266
Token around
Token ID1088
Feature activation+6.50e-01

Pos logit contributions
poke+0.409
horse+0.395
plate+0.379
 Hawth+0.363
 Trafford+0.360
Neg logit contributions
 tremend-0.516
 streng-0.452
aughs-0.439
utical-0.433
 Libre-0.410
Token 20
Token ID1160
Feature activation+4.66e-01

Pos logit contributions
 tremend+0.623
 streng+0.548
aughs+0.531
utical+0.522
 Libre+0.500
Neg logit contributions
poke-0.490
horse-0.472
plate-0.452
 Hawth-0.428
 Trafford-0.427
Token traders
Token ID21703
Feature activation-2.58e+00

Pos logit contributions
 tremend+0.440
 streng+0.385
aughs+0.374
utical+0.367
 Libre+0.351
Neg logit contributions
poke-0.360
horse-0.347
plate-0.333
 Hawth-0.316
 Trafford-0.315
Token and
Token ID290
Feature activation-6.21e-01

Pos logit contributions
poke+1.551
horse+1.497
plate+1.417
 Hawth+1.319
 Trafford+1.308
Neg logit contributions
 tremend-2.859
 streng-2.553
aughs-2.503
utical-2.465
 Libre-2.359
Tokenlu
Token ID2290
Feature activation+6.62e-01

Pos logit contributions
poke+0.419
horse+0.407
plate+0.394
 Trafford+0.376
 Hawth+0.374
Neg logit contributions
 tremend-0.357
 streng-0.303
aughs-0.290
utical-0.282
 Libre-0.268
Token.
Token ID13
Feature activation+1.16e-01

Pos logit contributions
 tremend+0.687
 streng+0.607
aughs+0.590
utical+0.578
 Libre+0.557
Neg logit contributions
poke-0.451
horse-0.433
plate-0.417
 Trafford-0.387
 Hawth-0.386
Token Using
Token ID8554
Feature activation-2.11e-01

Pos logit contributions
 tremend+0.115
 streng+0.100
aughs+0.097
utical+0.095
 Libre+0.090
Neg logit contributions
poke-0.087
horse-0.084
plate-0.080
 Hawth-0.076
 Trafford-0.076
Token it
Token ID340
Feature activation+4.39e-01

Pos logit contributions
poke+0.159
horse+0.154
plate+0.147
 Hawth+0.140
 Trafford+0.139
Neg logit contributions
 tremend-0.204
 streng-0.178
aughs-0.174
utical-0.170
 Libre-0.162
Token on
Token ID319
Feature activation+1.63e+00

Pos logit contributions
 tremend+0.455
 streng+0.401
aughs+0.394
utical+0.385
 Libre+0.370
Neg logit contributions
poke-0.298
horse-0.289
plate-0.275
 Hawth-0.258
 Trafford-0.256
Token a
Token ID257
Feature activation+5.99e-01

Pos logit contributions
 tremend+1.605
 streng+1.416
aughs+1.377
utical+1.351
 Libre+1.295
Neg logit contributions
poke-1.186
horse-1.141
plate-1.091
 Trafford-1.029
 Hawth-1.028
Token widespread
Token ID10095
Feature activation+2.40e+00

Pos logit contributions
 tremend+0.566
 streng+0.497
aughs+0.483
utical+0.473
 Libre+0.452
Neg logit contributions
poke-0.461
horse-0.445
plate-0.427
 Trafford-0.404
 Hawth-0.403
Token prevent
Token ID2948
Feature activation+8.76e-01

Pos logit contributions
 tremend+1.910
 streng+1.643
aughs+1.568
utical+1.546
 Libre+1.478
Neg logit contributions
poke-2.179
horse-2.112
plate-2.034
 Trafford-1.946
 Hawth-1.934
Tokenative
Token ID876
Feature activation+2.40e+00

Pos logit contributions
 tremend+0.824
 streng+0.723
aughs+0.700
utical+0.689
 Libre+0.660
Neg logit contributions
poke-0.675
horse-0.651
plate-0.624
 Trafford-0.592
 Hawth-0.589
Token scale
Token ID5046
Feature activation+1.42e+00

Pos logit contributions
 tremend+1.856
 streng+1.582
aughs+1.517
utical+1.485
 Libre+1.408
Neg logit contributions
poke-2.251
horse-2.184
plate-2.110
 Trafford-2.020
 Hawth-2.014
Token could
Token ID714
Feature activation+1.47e+00

Pos logit contributions
 tremend+1.473
 streng+1.306
aughs+1.272
utical+1.249
 Libre+1.201
Neg logit contributions
poke-0.965
horse-0.927
plate-0.884
 Trafford-0.829
 Hawth-0.827
Token the
Token ID262
Feature activation+2.26e-01

Pos logit contributions
poke+0.466
horse+0.448
plate+0.427
 Hawth+0.406
 Trafford+0.404
Neg logit contributions
 tremend-0.659
 streng-0.583
aughs-0.567
utical-0.556
 Libre-0.533
Token name
Token ID1438
Feature activation-7.82e-01

Pos logit contributions
 tremend+0.216
 streng+0.190
aughs+0.184
utical+0.182
 Libre+0.173
Neg logit contributions
poke-0.171
horse-0.165
plate-0.158
 Hawth-0.150
 Trafford-0.150
Token a
Token ID257
Feature activation+4.22e-01

Pos logit contributions
poke+0.568
horse+0.549
plate+0.529
 Hawth+0.496
 Trafford+0.494
Neg logit contributions
 tremend-0.775
 streng-0.685
aughs-0.665
utical-0.650
 Libre-0.621
Token teenage
Token ID16330
Feature activation-6.38e-01

Pos logit contributions
 tremend+0.395
 streng+0.347
aughs+0.336
utical+0.331
 Libre+0.315
Neg logit contributions
poke-0.331
horse-0.317
plate-0.305
 Hawth-0.289
 Trafford-0.288
Token boy
Token ID2933
Feature activation+1.35e+00

Pos logit contributions
poke+0.493
horse+0.473
plate+0.452
 Hawth+0.432
 Trafford+0.430
Neg logit contributions
 tremend-0.607
 streng-0.530
aughs-0.517
utical-0.513
 Libre-0.479
Token memor
Token ID16181
Feature activation+1.64e+00

Pos logit contributions
 tremend+1.348
 streng+1.191
aughs+1.156
utical+1.137
 Libre+1.092
Neg logit contributions
poke-0.973
horse-0.935
plate-0.894
 Trafford-0.842
 Hawth-0.840
Tokenably
Token ID1346
Feature activation+5.06e-01

Pos logit contributions
 tremend+1.369
 streng+1.179
aughs+1.135
utical+1.113
 Libre+1.059
Neg logit contributions
poke-1.450
horse-1.405
plate-1.354
 Trafford-1.290
 Hawth-1.287
Token gives
Token ID3607
Feature activation-8.07e-01

Pos logit contributions
 tremend+0.514
 streng+0.453
aughs+0.441
utical+0.435
 Libre+0.416
Neg logit contributions
poke-0.357
horse-0.343
plate-0.327
 Hawth-0.308
 Trafford-0.307
Token his
Token ID465
Feature activation+5.47e-01

Pos logit contributions
poke+0.578
horse+0.558
plate+0.532
 Hawth+0.505
 Trafford+0.502
Neg logit contributions
 tremend-0.807
 streng-0.716
aughs-0.691
utical-0.682
 Libre-0.651
Token penis
Token ID16360
Feature activation-1.29e-01

Pos logit contributions
 tremend+0.507
 streng+0.444
aughs+0.429
utical+0.424
 Libre+0.402
Neg logit contributions
poke-0.431
horse-0.417
plate-0.400
 Hawth-0.380
 Trafford-0.379
Token in
Token ID287
Feature activation-3.80e-01

Pos logit contributions
poke+0.088
horse+0.085
plate+0.081
 Hawth+0.075
 Trafford+0.075
Neg logit contributions
 tremend-0.133
 streng-0.118
aughs-0.114
utical-0.113
 Libre-0.108
Token
Token ID198
Feature activation+1.11e-01

Pos logit contributions
 tremend+0.053
 streng+0.046
aughs+0.043
utical+0.042
 toget+0.040
Neg logit contributions
poke-0.040
horse-0.039
plate-0.037
 Hawth-0.035
 Trafford-0.035
Token
Token ID447
Feature activation+6.54e-01

Pos logit contributions
 tremend+0.105
 streng+0.092
aughs+0.088
utical+0.086
 Libre+0.083
Neg logit contributions
poke-0.087
horse-0.084
plate-0.081
 Hawth-0.076
 Trafford-0.076
Token
Token ID246
Feature activation+1.04e+00

Pos logit contributions
 tremend+0.527
 streng+0.452
aughs+0.435
utical+0.425
 Libre+0.404
Neg logit contributions
poke-0.593
horse-0.575
plate-0.555
 Trafford-0.530
 Hawth-0.529
TokenAn
Token ID2025
Feature activation-2.52e+00

Pos logit contributions
 tremend+1.001
 streng+0.881
aughs+0.851
utical+0.837
 Libre+0.801
Neg logit contributions
poke-0.790
horse-0.761
plate-0.728
 Trafford-0.690
 Hawth-0.689
Tokennie
Token ID11952
Feature activation+4.34e-01

Pos logit contributions
poke+1.644
horse+1.593
plate+1.494
 Hawth+1.412
 Trafford+1.409
Neg logit contributions
 tremend-2.654
 streng-2.365
aughs-2.307
utical-2.281
 Libre-2.180
Token Hall
Token ID4789
Feature activation+9.12e-01

Pos logit contributions
 tremend+0.389
 streng+0.338
aughs+0.327
utical+0.321
 Libre+0.308
Neg logit contributions
poke-0.355
horse-0.342
plate-0.329
 Trafford-0.312
fleet-0.310
Token
Token ID447
Feature activation+7.03e-01

Pos logit contributions
 tremend+0.924
 streng+0.819
aughs+0.795
utical+0.783
 Libre+0.751
Neg logit contributions
poke-0.639
horse-0.615
plate-0.588
 Trafford-0.553
 Hawth-0.551
Token
Token ID247
Feature activation-3.62e-01

Pos logit contributions
 tremend+0.599
 streng+0.514
aughs+0.491
utical+0.474
 Libre+0.453
Neg logit contributions
poke-0.621
horse-0.602
plate-0.579
 Hawth-0.553
 Trafford-0.553
Token (
Token ID357
Feature activation-7.79e-01

Pos logit contributions
poke+0.259
horse+0.250
plate+0.238
 Hawth+0.225
 Trafford+0.225
Neg logit contributions
 tremend-0.361
 streng-0.319
aughs-0.310
utical-0.304
 Libre-0.292
Token1977
Token ID37781
Feature activation+2.19e+00

Pos logit contributions
poke+0.659
horse+0.639
plate+0.615
 Hawth+0.582
 Trafford+0.580
Neg logit contributions
 tremend-0.684
 streng-0.592
aughs-0.569
utical-0.559
 Libre-0.532
Token)
Token ID8
Feature activation+1.48e+00

Pos logit contributions
 tremend+2.226
 streng+1.979
aughs+1.928
utical+1.893
 Libre+1.831
Neg logit contributions
poke-1.501
horse-1.439
plate-1.367
 Trafford-1.291
 Hawth-1.281
Token Department
Token ID2732
Feature activation+7.38e-01

Pos logit contributions
poke+2.585
horse+2.516
plate+2.369
 Trafford+2.252
 Hawth+2.250
Neg logit contributions
 tremend-4.644
 streng-4.154
aughs-4.078
utical-3.964
 Libre-3.815
Token.
Token ID13
Feature activation+7.42e-01

Pos logit contributions
 tremend+0.779
 streng+0.695
aughs+0.674
utical+0.666
 Libre+0.642
Neg logit contributions
poke-0.485
horse-0.463
plate-0.440
 Trafford-0.412
 Hawth-0.411
Token Stre
Token ID9737
Feature activation+2.52e+00

Pos logit contributions
 tremend+0.697
 streng+0.607
aughs+0.586
utical+0.575
 Libre+0.548
Neg logit contributions
poke-0.581
horse-0.563
plate-0.539
 Trafford-0.512
 Hawth-0.511
Tokenng
Token ID782
Feature activation+2.83e+00

Pos logit contributions
 tremend+2.297
 streng+2.057
aughs+1.966
utical+1.943
 Libre+1.885
Neg logit contributions
poke-1.940
horse-1.880
plate-1.808
 Trafford-1.721
 Hawth-1.712
Tokenthening
Token ID20563
Feature activation+2.40e+00

Pos logit contributions
 tremend+1.868
 streng+1.569
aughs+1.480
utical+1.455
 Libre+1.355
Neg logit contributions
poke-2.944
horse-2.863
plate-2.776
 Trafford-2.680
 Hawth-2.672
Token rural
Token ID10016
Feature activation+1.32e-01

Pos logit contributions
 tremend+2.401
 streng+2.125
aughs+2.062
utical+2.028
 Libre+1.950
Neg logit contributions
poke-1.712
horse-1.645
plate-1.572
 Trafford-1.481
 Hawth-1.476
Token transport
Token ID4839
Feature activation-2.70e+00

Pos logit contributions
 tremend+0.133
 streng+0.117
aughs+0.115
utical+0.113
 Libre+0.107
Neg logit contributions
poke-0.094
horse-0.091
plate-0.087
 Trafford-0.082
 Hawth-0.081
Token,
Token ID11
Feature activation+6.74e-01

Pos logit contributions
poke+1.969
horse+1.928
plate+1.842
fleet+1.748
 Trafford+1.744
Neg logit contributions
 tremend-2.603
 streng-2.263
aughs-2.258
utical-2.186
 Libre-2.087
Token last
Token ID938
Feature activation+1.69e-01

Pos logit contributions
 tremend+0.660
 streng+0.577
aughs+0.567
utical+0.554
 Libre+0.531
Neg logit contributions
poke-0.495
horse-0.477
plate-0.457
 Trafford-0.432
 Hawth-0.431
Token mile
Token ID10591
Feature activation-2.84e+00

Pos logit contributions
 tremend+0.165
 streng+0.144
aughs+0.141
utical+0.138
 Libre+0.132
Neg logit contributions
poke-0.126
horse-0.122
plate-0.116
 Trafford-0.110
 Hawth-0.109
Token connectivity
Token ID19843
Feature activation-2.30e+00

Pos logit contributions
poke+2.068
horse+1.990
plate+1.921
 Trafford+1.808
 Hawth+1.798
Neg logit contributions
 tremend-2.793
 streng-2.422
aughs-2.417
utical-2.354
 Libre-2.226
Token
Token ID447
Feature activation-3.77e-01

Pos logit contributions
 tremend+3.084
 streng+2.695
aughs+2.605
utical+2.558
 Libre+2.447
Neg logit contributions
poke-2.725
horse-2.631
plate-2.527
 Trafford-2.398
 Hawth-2.391
Token
Token ID247
Feature activation-4.15e-01

Pos logit contributions
poke+0.334
horse+0.323
plate+0.311
 Hawth+0.296
 Trafford+0.295
Neg logit contributions
 tremend-0.321
 streng-0.274
aughs-0.263
utical-0.254
 Libre-0.242
Tokens
Token ID82
Feature activation+9.10e-01

Pos logit contributions
poke+0.284
horse+0.272
plate+0.260
 Trafford+0.243
fleet+0.241
Neg logit contributions
 tremend-0.432
 streng-0.383
aughs-0.372
utical-0.364
 Libre-0.348
Token supreme
Token ID17700
Feature activation+1.73e+00

Pos logit contributions
 tremend+0.847
 streng+0.728
aughs+0.718
utical+0.710
 Libre+0.655
Neg logit contributions
poke-0.713
horse-0.702
plate-0.671
 Trafford-0.640
 Hawth-0.639
Token leader
Token ID3554
Feature activation-9.39e-02

Pos logit contributions
 tremend+1.420
 streng+1.220
aughs+1.176
utical+1.152
 Libre+1.093
Neg logit contributions
poke-1.540
horse-1.494
plate-1.441
 Trafford-1.373
 Hawth-1.370
Token,
Token ID11
Feature activation-3.36e-01

Pos logit contributions
poke+0.065
horse+0.063
plate+0.060
 Trafford+0.056
 Hawth+0.056
Neg logit contributions
 tremend-0.096
 streng-0.084
aughs-0.082
utical-0.081
 Libre-0.077
Token Ay
Token ID13709
Feature activation+4.75e+00

Pos logit contributions
poke+0.276
horse+0.272
plate+0.261
 Trafford+0.246
 Hawth+0.245
Neg logit contributions
 tremend-0.298
 streng-0.254
aughs-0.249
utical-0.245
 Libre-0.231
Tokenat
Token ID265
Feature activation+9.94e-03

Pos logit contributions
 tremend+4.022
 streng+3.587
aughs+3.520
utical+3.440
 Libre+3.340
Neg logit contributions
poke-3.829
horse-3.632
plate-3.560
 Hawth-3.423
 Trafford-3.415
Tokenollah
Token ID17999
Feature activation+6.72e+00

Pos logit contributions
 tremend+0.008
 streng+0.006
aughs+0.006
utical+0.006
 Libre+0.006
Neg logit contributions
poke-0.009
horse-0.009
plate-0.009
 Trafford-0.009
 Hawth-0.008
Token Ali
Token ID12104
Feature activation+1.05e+00

Pos logit contributions
 tremend+5.898
 streng+5.274
aughs+5.104
utical+5.004
 Libre+4.922
Neg logit contributions
poke-5.308
horse-5.090
plate-4.833
 Hawth-4.644
fleet-4.601
Token Kham
Token ID45159
Feature activation+2.92e+00

Pos logit contributions
 tremend+0.926
 streng+0.804
aughs+0.774
utical+0.761
 Libre+0.723
Neg logit contributions
poke-0.882
horse-0.852
plate-0.820
 Trafford-0.781
 Hawth-0.779
Token I
Token ID314
Feature activation+8.07e-01

Pos logit contributions
 tremend+0.297
 streng+0.256
aughs+0.245
utical+0.239
 toget+0.225
Neg logit contributions
poke-0.230
horse-0.223
plate-0.213
 Hawth-0.205
 Trafford-0.203
Token see
Token ID766
Feature activation+7.20e-01

Pos logit contributions
 tremend+0.818
 streng+0.722
aughs+0.707
utical+0.694
 Libre+0.661
Neg logit contributions
poke-0.572
horse-0.548
plate-0.524
 Hawth-0.490
 Trafford-0.489
Token no
Token ID645
Feature activation-5.33e-01

Pos logit contributions
 tremend+0.724
 streng+0.642
aughs+0.630
utical+0.616
 Libre+0.586
Neg logit contributions
poke-0.511
horse-0.491
plate-0.470
 Hawth-0.443
 Trafford-0.442
Token other
Token ID584
Feature activation-5.85e-01

Pos logit contributions
poke+0.425
horse+0.411
plate+0.396
 Hawth+0.378
 Trafford+0.372
Neg logit contributions
 tremend-0.486
 streng-0.419
aughs-0.418
utical-0.404
 Libre-0.380
Token alternative
Token ID5559
Feature activation+1.10e+00

Pos logit contributions
poke+0.478
horse+0.464
plate+0.447
 Hawth+0.425
 Trafford+0.421
Neg logit contributions
 tremend-0.525
 streng-0.452
aughs-0.447
utical-0.432
 Libre-0.407
Token too
Token ID1165
Feature activation-8.40e-01

Pos logit contributions
 tremend+1.133
 streng+1.006
aughs+0.979
utical+0.962
 Libre+0.925
Neg logit contributions
poke-0.745
horse-0.715
plate-0.682
 Trafford-0.639
 Hawth-0.638
Token,
Token ID11
Feature activation-6.54e-02

Pos logit contributions
poke+0.580
horse+0.559
plate+0.534
 Hawth+0.502
 Trafford+0.498
Neg logit contributions
 tremend-0.856
 streng-0.758
aughs-0.743
utical-0.728
 Libre-0.697
Token but
Token ID475
Feature activation-1.61e+00

Pos logit contributions
poke+0.042
horse+0.041
plate+0.039
 Hawth+0.036
 Trafford+0.036
Neg logit contributions
 tremend-0.070
 streng-0.062
aughs-0.061
utical-0.060
 Libre-0.057
Token I
Token ID314
Feature activation+9.39e-01

Pos logit contributions
poke+1.066
horse+1.029
plate+0.988
 Hawth+0.932
 Trafford+0.910
Neg logit contributions
 tremend-1.693
 streng-1.485
aughs-1.481
utical-1.440
 Libre-1.359
Token have
Token ID423
Feature activation-1.15e+00

Pos logit contributions
 tremend+0.949
 streng+0.835
aughs+0.819
utical+0.804
 Libre+0.765
Neg logit contributions
poke-0.669
horse-0.640
plate-0.613
 Hawth-0.574
 Trafford-0.572
Token no
Token ID645
Feature activation-4.43e-01

Pos logit contributions
poke+0.809
horse+0.778
plate+0.745
 Hawth+0.704
 Trafford+0.697
Neg logit contributions
 tremend-1.158
 streng-1.023
aughs-1.015
utical-0.987
 Libre-0.938
Token those
Token ID883
Feature activation-1.26e+00

Pos logit contributions
poke+0.400
horse+0.389
plate+0.370
 Hawth+0.356
 Trafford+0.348
Neg logit contributions
 tremend-0.598
 streng-0.525
aughs-0.517
utical-0.509
 Libre-0.479
Token living
Token ID2877
Feature activation-9.84e-01

Pos logit contributions
poke+0.837
horse+0.806
plate+0.767
 Hawth+0.725
 Trafford+0.719
Neg logit contributions
 tremend-1.311
 streng-1.155
aughs-1.141
utical-1.117
 Libre-1.066
Token in
Token ID287
Feature activation-7.66e-01

Pos logit contributions
poke+0.621
horse+0.596
plate+0.569
 Hawth+0.528
 Trafford+0.523
Neg logit contributions
 tremend-1.065
 streng-0.946
aughs-0.929
utical-0.912
 Libre-0.874
Token Wa
Token ID15329
Feature activation+2.83e+00

Pos logit contributions
poke+0.575
horse+0.553
plate+0.527
 Hawth+0.511
 Trafford+0.501
Neg logit contributions
 tremend-0.738
 streng-0.645
aughs-0.636
utical-0.620
 Libre-0.586
Tokenik
Token ID1134
Feature activation-1.74e+00

Pos logit contributions
 tremend+2.165
 streng+1.838
aughs+1.754
utical+1.715
 Libre+1.624
Neg logit contributions
poke-2.691
horse-2.612
plate-2.524
 Trafford-2.414
 Hawth-2.410
Tokeniki
Token ID5580
Feature activation-2.27e+00

Pos logit contributions
poke+0.714
horse+0.667
plate+0.611
 Hawth+0.537
fleet+0.536
Neg logit contributions
 tremend-2.366
 streng-2.140
aughs-2.027
utical-2.001
 Libre-1.962
Token where
Token ID810
Feature activation-4.30e-01

Pos logit contributions
poke+1.457
horse+1.397
plate+1.328
 Hawth+1.250
 Trafford+1.248
Neg logit contributions
 tremend-2.430
 streng-2.169
aughs-2.113
utical-2.075
 Libre-1.989
Token the
Token ID262
Feature activation-4.44e-01

Pos logit contributions
poke+0.314
horse+0.303
plate+0.290
 Hawth+0.275
 Trafford+0.274
Neg logit contributions
 tremend-0.423
 streng-0.371
aughs-0.364
utical-0.357
 Libre-0.339
Token tourism
Token ID19277
Feature activation-1.40e-02

Pos logit contributions
poke+0.328
horse+0.316
plate+0.303
 Hawth+0.290
 Trafford+0.286
Neg logit contributions
 tremend-0.432
 streng-0.378
aughs-0.371
utical-0.365
 Libre-0.344
Token industry
Token ID2831
Feature activation+5.44e-01

Pos logit contributions
poke+0.013
horse+0.012
plate+0.012
 Hawth+0.011
fleet+0.011
Neg logit contributions
 tremend-0.011
 streng-0.010
aughs-0.009
utical-0.009
 Libre-0.008
Token has
Token ID468
Feature activation-4.90e-01

Pos logit contributions
 tremend+0.563
 streng+0.501
aughs+0.487
utical+0.479
 Libre+0.461
Neg logit contributions
poke-0.368
horse-0.354
plate-0.336
 Trafford-0.315
 Hawth-0.314
Token and
Token ID290
Feature activation-6.60e-01

Pos logit contributions
poke+0.185
horse+0.177
plate+0.169
 Hawth+0.157
 Trafford+0.157
Neg logit contributions
 tremend-0.304
 streng-0.271
aughs-0.264
utical-0.260
 Libre-0.251
Token said
Token ID531
Feature activation-1.41e+00

Pos logit contributions
poke+0.444
horse+0.423
plate+0.403
 Hawth+0.380
 Trafford+0.373
Neg logit contributions
 tremend-0.695
 streng-0.612
aughs-0.602
utical-0.598
 Libre-0.563
Token,
Token ID11
Feature activation-7.21e-01

Pos logit contributions
poke+0.925
horse+0.886
plate+0.844
 Hawth+0.787
 Trafford+0.785
Neg logit contributions
 tremend-1.494
 streng-1.331
aughs-1.298
utical-1.277
 Libre-1.227
Token
Token ID564
Feature activation+2.01e-01

Pos logit contributions
poke+0.483
horse+0.463
plate+0.441
 Trafford+0.420
 Hawth+0.414
Neg logit contributions
 tremend-0.754
 streng-0.671
aughs-0.651
utical-0.640
 Libre-0.615
Token
Token ID250
Feature activation+1.25e+00

Pos logit contributions
 tremend+0.176
 streng+0.153
aughs+0.148
utical+0.144
 Libre+0.138
Neg logit contributions
poke-0.169
horse-0.164
plate-0.157
 Trafford-0.149
 Hawth-0.149
TokenIt
Token ID1026
Feature activation-8.03e-01

Pos logit contributions
 tremend+1.163
 streng+1.018
aughs+0.984
utical+0.966
 Libre+0.926
Neg logit contributions
poke-0.991
horse-0.954
plate-0.917
 Trafford-0.865
 Hawth-0.862
Token
Token ID447
Feature activation+4.69e-01

Pos logit contributions
poke+0.597
horse+0.581
plate+0.554
 Hawth+0.516
 Trafford+0.515
Neg logit contributions
 tremend-0.777
 streng-0.684
aughs-0.663
utical-0.656
 Libre-0.627
Token
Token ID247
Feature activation-1.05e-02

Pos logit contributions
 tremend+0.368
 streng+0.310
aughs+0.295
utical+0.285
 Libre+0.272
Neg logit contributions
poke-0.444
horse-0.432
plate-0.417
 Hawth-0.398
 Trafford-0.398
Tokens
Token ID82
Feature activation+1.19e+00

Pos logit contributions
poke+0.007
horse+0.007
plate+0.007
 Hawth+0.006
 Trafford+0.006
Neg logit contributions
 tremend-0.011
 streng-0.009
aughs-0.009
utical-0.009
 Libre-0.009
Token not
Token ID407
Feature activation-1.56e+00

Pos logit contributions
 tremend+1.184
 streng+1.048
aughs+1.022
utical+1.003
 Libre+0.960
Neg logit contributions
poke-0.861
horse-0.829
plate-0.794
 Hawth-0.743
 Trafford-0.740
Token easy
Token ID2562
Feature activation+1.10e+00

Pos logit contributions
poke+1.098
horse+1.059
plate+1.012
 Hawth+0.953
 Trafford+0.934
Neg logit contributions
 tremend-1.575
aughs-1.384
 streng-1.383
utical-1.355
 Libre-1.273
Token voter
Token ID10765
Feature activation+8.69e-02

Pos logit contributions
poke+0.538
horse+0.518
plate+0.496
 Hawth+0.472
 Trafford+0.469
Neg logit contributions
 tremend-0.679
 streng-0.591
aughs-0.579
utical-0.569
 Libre-0.533
Token file
Token ID2393
Feature activation-8.27e-01

Pos logit contributions
 tremend+0.083
 streng+0.073
aughs+0.071
utical+0.070
 Libre+0.066
Neg logit contributions
poke-0.066
horse-0.064
plate-0.061
 Trafford-0.058
 Hawth-0.058
Token the
Token ID262
Feature activation-1.31e-01

Pos logit contributions
poke+0.565
horse+0.547
plate+0.523
 Trafford+0.486
 Hawth+0.485
Neg logit contributions
 tremend-0.857
 streng-0.758
aughs-0.742
utical-0.726
 Libre-0.694
Token Democratic
Token ID4390
Feature activation-1.91e+00

Pos logit contributions
poke+0.106
horse+0.103
plate+0.099
 Hawth+0.094
 Trafford+0.094
Neg logit contributions
 tremend-0.118
 streng-0.102
aughs-0.099
utical-0.098
 Libre-0.092
Token National
Token ID2351
Feature activation-3.25e+00

Pos logit contributions
poke+1.455
horse+1.407
plate+1.353
 Hawth+1.279
 Trafford+1.277
Neg logit contributions
 tremend-1.810
 streng-1.581
aughs-1.546
utical-1.521
 Libre-1.428
Token Committee
Token ID4606
Feature activation-6.46e-01

Pos logit contributions
poke+2.510
horse+2.472
plate+2.397
 Hawth+2.261
 Trafford+2.245
Neg logit contributions
 tremend-2.990
 streng-2.613
utical-2.551
aughs-2.535
 toget-2.341
Token makes
Token ID1838
Feature activation-1.61e+00

Pos logit contributions
poke+0.455
horse+0.440
plate+0.420
 Hawth+0.394
 Trafford+0.393
Neg logit contributions
 tremend-0.655
 streng-0.575
aughs-0.561
utical-0.552
 Libre-0.524
Token available
Token ID1695
Feature activation-1.10e+00

Pos logit contributions
poke+1.221
horse+1.198
plate+1.147
 Trafford+1.081
 Hawth+1.080
Neg logit contributions
 tremend-1.545
 streng-1.345
aughs-1.326
utical-1.301
 Libre-1.205
Token to
Token ID284
Feature activation-6.50e-01

Pos logit contributions
poke+0.714
horse+0.693
plate+0.659
 Hawth+0.611
 Trafford+0.610
Neg logit contributions
 tremend-1.180
 streng-1.047
aughs-1.030
utical-1.009
 Libre-0.961
Token candidates
Token ID5871
Feature activation-3.19e+00

Pos logit contributions
poke+0.491
horse+0.474
plate+0.454
 Hawth+0.432
 Trafford+0.425
Neg logit contributions
 tremend-0.631
 streng-0.547
aughs-0.535
utical-0.533
 Libre-0.491
Token to
Token ID284
Feature activation-6.33e-01

Pos logit contributions
poke+2.032
horse+1.968
plate+1.893
 Hawth+1.743
 Trafford+1.733
Neg logit contributions
 tremend-3.441
 streng-3.034
aughs-3.020
utical-2.956
 Libre-2.793
Token of
Token ID286
Feature activation-5.28e-01

Pos logit contributions
 tremend+1.182
 streng+1.046
aughs+1.016
utical+0.996
 Libre+0.964
Neg logit contributions
poke-0.995
horse-0.954
plate-0.912
 Trafford-0.876
 Hawth-0.865
Token the
Token ID262
Feature activation-2.54e-01

Pos logit contributions
poke+0.370
horse+0.358
plate+0.341
 Hawth+0.325
 Trafford+0.322
Neg logit contributions
 tremend-0.564
 streng-0.494
aughs-0.464
utical-0.455
 toget-0.441
Token Year
Token ID6280
Feature activation+4.07e-01

Pos logit contributions
poke+0.193
horse+0.186
plate+0.178
 Trafford+0.168
 Hawth+0.167
Neg logit contributions
 tremend-0.242
 streng-0.213
aughs-0.207
utical-0.203
 Libre-0.195
Token voting
Token ID6709
Feature activation+3.83e-02

Pos logit contributions
 tremend+0.414
 streng+0.366
aughs+0.354
utical+0.351
 Libre+0.335
Neg logit contributions
poke-0.284
horse-0.275
plate-0.262
 Trafford-0.246
 Hawth-0.246
Token to
Token ID284
Feature activation+7.71e-03

Pos logit contributions
 tremend+0.040
 streng+0.035
aughs+0.034
utical+0.034
 Libre+0.032
Neg logit contributions
poke-0.026
horse-0.025
plate-0.024
 Trafford-0.022
 Hawth-0.022
Token Marcus
Token ID17068
Feature activation-6.51e+00

Pos logit contributions
 tremend+0.008
 streng+0.007
aughs+0.007
utical+0.007
 Libre+0.006
Neg logit contributions
poke-0.005
horse-0.005
plate-0.005
 Hawth-0.005
 Trafford-0.004
Token Paige
Token ID42847
Feature activation+4.80e+00

Pos logit contributions
poke+4.519
horse+4.289
 Hawth+4.115
 Trafford+4.092
plate+3.966
Neg logit contributions
 tremend-6.686
 streng-5.894
utical-5.695
aughs-5.609
 toget-5.232
Token.[
Token ID3693
Feature activation+7.00e-01

Pos logit contributions
 tremend+4.638
 streng+4.114
aughs+3.992
utical+3.924
 Libre+3.805
Neg logit contributions
poke-3.476
horse-3.290
plate-3.148
fleet-2.958
 Trafford-2.954
Token103
Token ID15197
Feature activation+3.67e-01

Pos logit contributions
 tremend+0.743
 streng+0.664
aughs+0.648
utical+0.639
 Libre+0.619
Neg logit contributions
poke-0.447
horse-0.429
plate-0.407
 Trafford-0.382
 Hawth-0.381
Token]
Token ID60
Feature activation+1.38e+00

Pos logit contributions
 tremend+0.336
 streng+0.292
aughs+0.287
utical+0.281
 Libre+0.271
Neg logit contributions
poke-0.290
horse-0.280
plate-0.267
 Trafford-0.256
 Hawth-0.255
Token He
Token ID679
Feature activation-1.69e-01

Pos logit contributions
 tremend+1.301
 streng+1.143
aughs+1.108
utical+1.088
 Libre+1.044
Neg logit contributions
poke-1.068
horse-1.029
plate-0.987
 Trafford-0.934
 Hawth-0.931
Token block
Token ID2512
Feature activation+1.74e+00

Pos logit contributions
poke+0.448
horse+0.427
plate+0.411
 Hawth+0.390
 Trafford+0.386
Neg logit contributions
 tremend-0.563
 streng-0.489
aughs-0.485
utical-0.481
 Libre-0.450
Token the
Token ID262
Feature activation-3.26e-01

Pos logit contributions
 tremend+1.757
 streng+1.560
aughs+1.512
utical+1.487
 Libre+1.435
Neg logit contributions
poke-1.212
horse-1.164
plate-1.111
 Trafford-1.047
 Hawth-1.038
Token Milwaukee
Token ID16629
Feature activation-2.28e+00

Pos logit contributions
poke+0.253
horse+0.244
plate+0.235
 Hawth+0.223
 Trafford+0.221
Neg logit contributions
 tremend-0.307
 streng-0.269
aughs-0.263
utical-0.259
 Libre-0.244
Token Bucks
Token ID29751
Feature activation+6.22e-01

Pos logit contributions
poke+1.569
horse+1.525
plate+1.440
 Hawth+1.368
 Trafford+1.337
Neg logit contributions
 tremend-2.332
 streng-2.065
aughs-2.017
utical-2.002
 Libre-1.869
Token'
Token ID6
Feature activation+8.51e-01

Pos logit contributions
 tremend+0.628
 streng+0.557
aughs+0.541
utical+0.534
 Libre+0.510
Neg logit contributions
poke-0.439
horse-0.423
plate-0.404
 Hawth-0.378
 Trafford-0.378
Token Sterling
Token ID23647
Feature activation-4.69e+00

Pos logit contributions
 tremend+0.850
 streng+0.752
aughs+0.736
utical+0.723
 Libre+0.685
Neg logit contributions
poke-0.610
horse-0.588
plate-0.563
 Hawth-0.530
 Trafford-0.527
Token Brown
Token ID4373
Feature activation+2.93e-01

Pos logit contributions
poke+2.965
horse+2.798
 Hawth+2.573
plate+2.565
 Trafford+2.455
Neg logit contributions
 tremend-5.204
 streng-4.627
aughs-4.432
utical-4.400
 toget-4.249
Token,
Token ID11
Feature activation-6.03e-01

Pos logit contributions
 tremend+0.303
 streng+0.269
aughs+0.261
utical+0.258
 Libre+0.248
Neg logit contributions
poke-0.200
horse-0.192
plate-0.183
 Trafford-0.171
 Hawth-0.171
Token who
Token ID508
Feature activation+9.70e-02

Pos logit contributions
poke+0.403
horse+0.388
plate+0.368
 Hawth+0.350
 Trafford+0.347
Neg logit contributions
 tremend-0.631
 streng-0.558
aughs-0.548
utical-0.539
 Libre-0.513
Token powered
Token ID13232
Feature activation-2.86e+00

Pos logit contributions
 tremend+0.098
 streng+0.086
aughs+0.084
utical+0.083
 Libre+0.079
Neg logit contributions
poke-0.069
horse-0.066
plate-0.063
 Hawth-0.060
 Trafford-0.060
Token through
Token ID832
Feature activation+7.29e-01

Pos logit contributions
poke+1.854
horse+1.794
plate+1.690
 Hawth+1.598
 Trafford+1.565
Neg logit contributions
 tremend-3.059
 streng-2.721
aughs-2.687
utical-2.651
 Libre-2.479
Token.
Token ID13
Feature activation+2.28e-01

Pos logit contributions
poke+0.391
horse+0.375
plate+0.357
 Trafford+0.335
 Hawth+0.334
Neg logit contributions
 tremend-0.602
 streng-0.535
aughs-0.521
utical-0.512
 Libre-0.492
Token The
Token ID383
Feature activation-2.88e-02

Pos logit contributions
 tremend+0.218
 streng+0.191
aughs+0.183
utical+0.179
 Libre+0.170
Neg logit contributions
poke-0.175
horse-0.170
plate-0.162
 Hawth-0.155
 Trafford-0.155
Token top
Token ID1353
Feature activation+8.30e-01

Pos logit contributions
poke+0.022
horse+0.021
plate+0.020
 Hawth+0.020
 Trafford+0.019
Neg logit contributions
 tremend-0.028
 streng-0.024
aughs-0.024
utical-0.023
 toget-0.022
Token eight
Token ID3624
Feature activation-6.12e-01

Pos logit contributions
 tremend+0.826
 streng+0.724
aughs+0.706
utical+0.693
 Libre+0.654
Neg logit contributions
poke-0.607
horse-0.592
plate-0.567
 Hawth-0.537
 Trafford-0.534
Token airports
Token ID22600
Feature activation-3.14e+00

Pos logit contributions
poke+0.457
horse+0.447
plate+0.425
 Hawth+0.408
 Trafford+0.404
Neg logit contributions
 tremend-0.597
 streng-0.520
aughs-0.512
utical-0.502
 Libre-0.472
Token commanded
Token ID22419
Feature activation-4.96e+00

Pos logit contributions
poke+2.043
horse+2.001
plate+1.896
 Hawth+1.788
 Trafford+1.740
Neg logit contributions
 tremend-3.309
 streng-2.938
aughs-2.901
utical-2.826
 Libre-2.672
Token about
Token ID546
Feature activation-1.58e-01

Pos logit contributions
poke+3.054
horse+3.023
plate+2.886
 Hawth+2.747
 Trafford+2.718
Neg logit contributions
 tremend-5.195
 streng-4.689
aughs-4.628
utical-4.484
 toget-4.210
Token half
Token ID2063
Feature activation+1.84e-01

Pos logit contributions
poke+0.105
horse+0.102
plate+0.097
 Hawth+0.092
 Trafford+0.091
Neg logit contributions
 tremend-0.167
 streng-0.148
aughs-0.145
utical-0.142
 Libre-0.135
Token of
Token ID286
Feature activation-5.53e-01

Pos logit contributions
 tremend+0.171
 streng+0.149
aughs+0.145
utical+0.143
 Libre+0.138
Neg logit contributions
poke-0.143
horse-0.137
plate-0.131
 Trafford-0.126
 Hawth-0.124
Token all
Token ID477
Feature activation+1.52e+00

Pos logit contributions
poke+0.429
horse+0.414
plate+0.399
 Hawth+0.381
 Trafford+0.376
Neg logit contributions
 tremend-0.520
 streng-0.455
aughs-0.440
utical-0.432
 Libre-0.407
Token passenger
Token ID11849
Feature activation-1.77e+00

Pos logit contributions
 tremend+1.558
 streng+1.384
aughs+1.344
utical+1.322
 Libre+1.271
Neg logit contributions
poke-1.044
horse-1.002
plate-0.956
 Trafford-0.898
 Hawth-0.896
Token were
Token ID547
Feature activation-5.79e-01

Pos logit contributions
poke+1.518
horse+1.458
plate+1.389
 Hawth+1.306
 Trafford+1.304
Neg logit contributions
 tremend-2.249
 streng-1.965
aughs-1.942
utical-1.917
 Libre-1.786
Token being
Token ID852
Feature activation-1.76e+00

Pos logit contributions
poke+0.405
horse+0.390
plate+0.372
 Hawth+0.351
 Trafford+0.350
Neg logit contributions
 tremend-0.595
 streng-0.517
aughs-0.512
utical-0.509
 Libre-0.472
Token rigged
Token ID31043
Feature activation-2.66e+00

Pos logit contributions
poke+1.226
horse+1.185
plate+1.131
 Hawth+1.067
 Trafford+1.065
Neg logit contributions
 tremend-1.806
aughs-1.554
 streng-1.550
utical-1.545
 Libre-1.422
Token to
Token ID284
Feature activation-6.40e-01

Pos logit contributions
poke+1.710
horse+1.651
plate+1.561
 Hawth+1.449
 Trafford+1.449
Neg logit contributions
 tremend-2.863
 streng-2.548
aughs-2.490
utical-2.453
 Libre-2.322
Token change
Token ID1487
Feature activation+5.05e-01

Pos logit contributions
poke+0.477
horse+0.459
plate+0.435
 Hawth+0.416
 Trafford+0.413
Neg logit contributions
 tremend-0.625
 streng-0.545
aughs-0.542
utical-0.534
 Libre-0.495
Token Donald
Token ID3759
Feature activation-5.45e+00

Pos logit contributions
 tremend+0.500
 streng+0.439
aughs+0.430
utical+0.423
 Libre+0.399
Neg logit contributions
poke-0.368
horse-0.356
plate-0.339
 Hawth-0.322
 Trafford-0.320
Token Trump
Token ID1301
Feature activation-4.44e+00

Pos logit contributions
poke+2.922
horse+2.770
plate+2.602
 Trafford+2.396
 Hawth+2.384
Neg logit contributions
 tremend-6.403
 streng-5.779
aughs-5.635
utical-5.558
 Libre-5.382
Token votes
Token ID5690
Feature activation+2.33e-01

Pos logit contributions
poke+3.184
horse+3.093
plate+2.955
 Hawth+2.770
 Trafford+2.766
Neg logit contributions
 tremend-4.358
 streng-3.805
aughs-3.757
utical-3.684
 Libre-3.485
Token to
Token ID284
Feature activation-6.72e-01

Pos logit contributions
 tremend+0.235
 streng+0.209
aughs+0.202
utical+0.199
 Libre+0.192
Neg logit contributions
poke-0.164
horse-0.157
plate-0.150
 Trafford-0.141
 Hawth-0.141
Token Hillary
Token ID5073
Feature activation-4.28e+00

Pos logit contributions
poke+0.422
horse+0.401
plate+0.379
 Hawth+0.358
 Trafford+0.351
Neg logit contributions
 tremend-0.731
 streng-0.648
aughs-0.639
utical-0.633
 Libre-0.599
Token Clinton
Token ID2605
Feature activation-4.58e+00

Pos logit contributions
poke+2.719
horse+2.605
plate+2.468
 Hawth+2.354
 Trafford+2.312
Neg logit contributions
 tremend-4.561
 streng-4.051
aughs-3.960
utical-3.901
 Libre-3.703
Token drones
Token ID15382
Feature activation-2.23e+00

Pos logit contributions
poke+2.614
horse+2.533
plate+2.400
 Hawth+2.301
 Trafford+2.250
Neg logit contributions
 tremend-4.317
 streng-3.791
aughs-3.744
utical-3.686
 Libre-3.474
Token for
Token ID329
Feature activation+7.43e-01

Pos logit contributions
poke+1.441
horse+1.390
plate+1.325
 Hawth+1.236
 Trafford+1.230
Neg logit contributions
 tremend-2.386
 streng-2.109
aughs-2.074
utical-2.040
 Libre-1.950
Token such
Token ID884
Feature activation-4.51e+00

Pos logit contributions
 tremend+0.697
 streng+0.608
aughs+0.592
utical+0.580
 Libre+0.552
Neg logit contributions
poke-0.580
horse-0.560
plate-0.537
 Hawth-0.511
 Trafford-0.509
Token things
Token ID1243
Feature activation-2.05e+00

Pos logit contributions
poke+3.677
horse+3.570
plate+3.454
 Hawth+3.323
 Trafford+3.248
Neg logit contributions
 tremend-3.970
 streng-3.351
aughs-3.350
utical-3.243
 Libre-3.054
Token as
Token ID355
Feature activation-2.05e+00

Pos logit contributions
poke+1.408
horse+1.354
plate+1.290
 Trafford+1.209
 Hawth+1.209
Neg logit contributions
 tremend-2.101
 streng-1.863
aughs-1.809
utical-1.782
 Libre-1.710
Token traffic
Token ID4979
Feature activation-5.99e+00

Pos logit contributions
poke+1.571
horse+1.521
plate+1.453
 Hawth+1.378
 Trafford+1.372
Neg logit contributions
 tremend-1.953
 streng-1.694
aughs-1.678
utical-1.632
 Libre-1.535
Token control
Token ID1630
Feature activation-5.35e-01

Pos logit contributions
poke+3.769
horse+3.661
plate+3.512
 Hawth+3.221
 Trafford+3.144
Neg logit contributions
 tremend-6.408
 streng-5.609
aughs-5.562
utical-5.517
 Libre-5.222
Token and
Token ID290
Feature activation-3.96e-01

Pos logit contributions
poke+0.350
horse+0.335
plate+0.319
 Trafford+0.299
 Hawth+0.298
Neg logit contributions
 tremend-0.565
 streng-0.504
aughs-0.490
utical-0.482
 Libre-0.465
Token surveillance
Token ID8452
Feature activation-8.15e-01

Pos logit contributions
poke+0.287
horse+0.277
plate+0.265
 Hawth+0.250
 Trafford+0.249
Neg logit contributions
 tremend-0.392
 streng-0.345
aughs-0.338
utical-0.331
 Libre-0.316
Token.
Token ID13
Feature activation-1.65e-01

Pos logit contributions
poke+0.570
horse+0.549
plate+0.524
 Hawth+0.491
 Trafford+0.490
Neg logit contributions
 tremend-0.828
 streng-0.732
aughs-0.714
utical-0.701
 Libre-0.672
Token McDonnell
Token ID39441
Feature activation-4.04e+00

Pos logit contributions
poke+0.127
horse+0.122
plate+0.117
 Hawth+0.112
 Trafford+0.111
Neg logit contributions
 tremend-0.159
 streng-0.139
aughs-0.133
utical-0.131
 Libre-0.125