TOP ACTIVATIONS
MAX = 1.781

com / iv xx brand ? f ref = ts <|endoftext|>
Share this story : http :// on . c ps j
at 10 : 02 am PST Do not use
responds , " You are such a tease ."
Share this story : http :// usat . ly / 1
Share this story : http :// cin . ci / 2
Share this story : http :// usat . ly / 1
$ 11 . 25 million contract signed in March 2016
at 9 : 28 am PST Do use social
., where killer whale Til ik um was involved in three
cin . ci / 2 yp d G uf <|endoftext|> A
at 9 : 01 am PDT Do use social
import paths import n umpy as np import arg parse import
import paths import n umpy as np import arg parse import
$ 16 . 25 million contract signed in February 2017
year , $ 72 million contract with $ 37 million guaranteed
: http :// usat . ly / 1 G q FP
names , and the # Never Trump forces have invested a
we must win . <|endoftext|> Mr . Sel z nick was
his current three - year contract . Last year , he

MIN ACTIVATIONS
MIN = -2.063

BR USS ELS ( Reuters ) - The world
HA V ANA ( Reuters ) - Latin American and Caribbean
OT TA WA ( Reuters ) - Canada s
ITED N ATIONS ( Reuters ) - An army battalion in
ONG K ONG ( Reuters ) - One needs to look
a fighter . As they say , nothing is more dangerous
ote ( O mega Pharma - Quick step ) s .
country . Read full story <|endoftext|> Asia Health Correspond
. ( Photo by REUTERS / Car lo Alleg ri )
k ( O mega Pharma - Quick step ) s .
. ( Photo by REUTERS / Gary Cameron / File photo
Ryan , who was em ce e ing the program ,
" As you may have heard , Winter ke wl Games
could name . The g reg arious Massachusetts pol , House
request stamp . <|endoftext|> ED MON TON Omar Kh adr
<|endoftext|> Metro Manila ( CNN Philippines ) A " special
a model ine only for Vim 6 . 0 and later
cameras being defective ( cons ist ently front - f ocusing
. ( Photo by REUTERS / John S omm ers II
an Amber Rose - re min is cent voice actress to

INTERVAL 0.820 - 1.781
CONTAINS 0.478%

em ruining your attempt to tape record the first Western song
s books take the reader beyond falling in love and into
. A ole i
the information containing those allegations ? DEF END AN TS
protect them from the harsh Antarctic winter , incub ate their

INTERVAL -0.141 - 0.820
CONTAINS 68.779%

- ACC Fresh man first team ( along with Jones and
See also [ edit ] <|endoftext|> I ke a
a week to a couple of months , and the pressure
me . I am ready . Then , it
all ? The first proposal , Mandatory In clusion

INTERVAL -1.102 - -0.141
CONTAINS 30.692%

that authorities are questioning a person of interest at Brigham and
the rooft ops to duel to the death in the name
Maybe we have to pray ,
parent since 2016 . She
. A US 5 Robbie M ce wen ( Green Edge

INTERVAL -2.063 - -1.102
CONTAINS 0.051%

upsetting . . . the bottom line is the comments are
minimized . Twitter : @ brand t st rib
G Q ( read the full profile here ). Talking Points
ing to other browsers , Mozilla has said .
it is ). sudo system ctl restart network -
Tokencom
Token ID785
Feature activation+5.01e-01

Pos logit contributions
 leaflets+2.020
 Masquerade+1.905
als+1.880
 Rollins+1.877
 Dent+1.867
Neg logit contributions
uble-1.759
outer-1.707
oro-1.641
olphins-1.579
oster-1.566
Token/
Token ID14
Feature activation-8.01e-02

Pos logit contributions
uble+1.154
outer+1.130
oro+1.074
oster+0.991
olphins+0.951
Neg logit contributions
 leaflets-2.453
senal-2.411
 Masquerade-2.345
 pse-2.334
 Rollins-2.285
Tokeniv
Token ID452
Feature activation+2.80e-01

Pos logit contributions
 leaflets+0.301
senal+0.286
 Masquerade+0.284
 pse+0.279
 Rollins+0.275
Neg logit contributions
uble-0.277
outer-0.273
oro-0.263
oster-0.250
olphins-0.245
Tokenxx
Token ID5324
Feature activation+4.98e-01

Pos logit contributions
uble+0.941
outer+0.930
oro+0.895
oster+0.850
olphins+0.830
Neg logit contributions
 leaflets-1.083
senal-1.033
 Masquerade-1.026
 pse-1.008
 Rollins-0.993
Tokenbrand
Token ID17938
Feature activation+2.65e-01

Pos logit contributions
uble+1.602
outer+1.597
oro+1.528
oster+1.451
olphins+1.405
Neg logit contributions
 leaflets-1.978
senal-1.904
 Masquerade-1.867
 pse-1.854
 Rollins-1.815
Token?
Token ID30
Feature activation+1.78e+00

Pos logit contributions
uble+0.858
outer+0.853
oro+0.821
oster+0.780
olphins+0.752
Neg logit contributions
 leaflets-1.047
senal-1.005
 Masquerade-0.992
 pse-0.981
 Rollins-0.963
Tokenf
Token ID69
Feature activation+9.33e-01

Pos logit contributions
uble+5.043
oro+4.939
outer+4.884
oster+4.489
fashion+4.393
Neg logit contributions
 leaflets-7.431
senal-7.234
 pse-6.885
 Dent-6.866
 Masquerade-6.844
Tokenref
Token ID5420
Feature activation-1.00e-01

Pos logit contributions
uble+2.575
outer+2.525
oro+2.460
oster+2.377
fashion+2.223
Neg logit contributions
 leaflets-4.135
senal-3.973
 pse-3.867
 Masquerade-3.805
 Dent-3.764
Token=
Token ID28
Feature activation+5.86e-01

Pos logit contributions
 leaflets+0.491
 Masquerade+0.472
senal+0.470
 pse+0.462
 Rollins+0.458
Neg logit contributions
uble-0.233
outer-0.229
oro-0.213
oster-0.198
olphins-0.193
Tokents
Token ID912
Feature activation+6.66e-01

Pos logit contributions
uble+1.994
outer+1.988
oro+1.921
oster+1.842
fashion+1.773
Neg logit contributions
 leaflets-2.219
 Masquerade-2.102
senal-2.099
 pse-2.073
 Rollins-2.019
Token<|endoftext|>
Token ID50256
Feature activation-1.48e-01

Pos logit contributions
uble+2.149
outer+2.109
oro+2.050
oster+1.931
olphins+1.867
Neg logit contributions
 leaflets-2.647
senal-2.542
 pse-2.494
 Masquerade-2.486
 Rollins-2.407
Token Share
Token ID8734
Feature activation-4.77e-01

Pos logit contributions
 leaflets+2.124
 Masquerade+1.986
senal+1.910
 pse+1.905
 Dent+1.894
Neg logit contributions
uble-3.093
outer-3.085
oro-2.959
oster-2.842
TEXTURE-2.834
Token this
Token ID428
Feature activation-5.30e-01

Pos logit contributions
 leaflets+1.704
 Masquerade+1.593
senal+1.579
 pse+1.554
 Rollins+1.542
Neg logit contributions
uble-1.750
outer-1.742
oro-1.670
oster-1.596
TEXTURE-1.570
Token story
Token ID1621
Feature activation-3.51e-01

Pos logit contributions
 leaflets+0.886
 Masquerade+0.768
senal+0.765
 pse+0.732
 Rollins+0.709
Neg logit contributions
uble-2.944
outer-2.917
oro-2.856
oster-2.765
olphins-2.737
Token:
Token ID25
Feature activation-4.34e-02

Pos logit contributions
 leaflets+1.130
 Masquerade+1.054
senal+1.038
 pse+1.020
 Rollins+1.013
Neg logit contributions
uble-1.400
outer-1.388
oro-1.345
oster-1.282
olphins-1.269
Token http
Token ID2638
Feature activation+1.04e+00

Pos logit contributions
 leaflets+0.229
senal+0.221
 Masquerade+0.220
 pse+0.217
 Rollins+0.215
Neg logit contributions
uble-0.084
outer-0.082
oro-0.076
oster-0.069
olphins-0.067
Token://
Token ID1378
Feature activation+1.74e+00

Pos logit contributions
uble+1.143
outer+1.117
oro+0.956
oster+0.829
TEXTURE+0.723
Neg logit contributions
senal-6.544
 leaflets-6.322
 pse-6.201
 Masquerade-6.069
cffff-6.002
Tokenon
Token ID261
Feature activation+7.67e-01

Pos logit contributions
outer+4.902
uble+4.813
oro+4.508
oster+4.288
usa+4.168
Neg logit contributions
senal-7.501
 leaflets-7.420
 Masquerade-7.224
 pse-7.164
 Dent-6.947
Token.
Token ID13
Feature activation+5.43e-01

Pos logit contributions
uble+2.011
outer+1.977
oro+1.880
oster+1.777
olphins+1.702
Neg logit contributions
senal-3.622
 leaflets-3.546
 pse-3.444
 Masquerade-3.440
 Dent-3.306
Tokenc
Token ID66
Feature activation+4.74e-04

Pos logit contributions
uble+1.825
outer+1.798
oro+1.743
oster+1.640
obe+1.602
Neg logit contributions
 leaflets-2.126
senal-2.069
 Masquerade-2.043
 pse-2.003
 Dent-1.927
Tokenps
Token ID862
Feature activation+4.29e-01

Pos logit contributions
uble+0.002
outer+0.002
oro+0.001
oster+0.001
TEXTURE+0.001
Neg logit contributions
 leaflets-0.002
 Masquerade-0.002
senal-0.002
 pse-0.002
 Rollins-0.002
Tokenj
Token ID73
Feature activation+2.92e-01

Pos logit contributions
uble+1.158
outer+1.156
oro+1.105
oster+1.018
usa+1.004
Neg logit contributions
 leaflets-1.950
senal-1.882
 Masquerade-1.874
 pse-1.852
 Dent-1.809
Token at
Token ID379
Feature activation+7.70e-02

Pos logit contributions
uble+0.606
outer+0.599
oro+0.581
oster+0.556
olphins+0.546
Neg logit contributions
 leaflets-0.480
senal-0.455
 Masquerade-0.448
 pse-0.441
 Rollins-0.432
Token 10
Token ID838
Feature activation+6.84e-01

Pos logit contributions
uble+0.291
outer+0.287
oro+0.280
oster+0.267
olphins+0.261
Neg logit contributions
 leaflets-0.262
senal-0.257
 pse-0.244
 Masquerade-0.243
cffff-0.238
Token:
Token ID25
Feature activation-1.57e-01

Pos logit contributions
uble+2.456
outer+2.441
oro+2.367
oster+2.222
olphins+2.169
Neg logit contributions
senal-2.516
 leaflets-2.460
 pse-2.356
 Masquerade-2.303
cffff-2.235
Token02
Token ID2999
Feature activation+2.01e-01

Pos logit contributions
 leaflets+0.509
senal+0.486
 Masquerade+0.474
 pse+0.469
 Rollins+0.455
Neg logit contributions
uble-0.624
outer-0.618
oro-0.597
oster-0.572
TEXTURE-0.562
Tokenam
Token ID321
Feature activation+9.52e-01

Pos logit contributions
uble+0.521
outer+0.515
oro+0.489
oster+0.455
olphins+0.442
Neg logit contributions
 leaflets-0.927
senal-0.892
 Masquerade-0.882
 pse-0.873
 Rollins-0.861
Token PST
Token ID28220
Feature activation+1.69e+00

Pos logit contributions
uble+2.338
outer+2.235
oro+2.172
oster+1.989
olphins+1.963
Neg logit contributions
 leaflets-4.453
senal-4.418
 pse-4.354
 Masquerade-4.271
 Rollins-4.147
Token
Token ID198
Feature activation+1.43e-01

Pos logit contributions
uble+4.258
outer+4.165
oro+4.018
oster+3.701
obe+3.696
Neg logit contributions
 leaflets-7.407
 pse-7.290
senal-7.236
 Masquerade-6.970
cffff-6.947
Token
Token ID198
Feature activation+2.99e-02

Pos logit contributions
uble+0.449
outer+0.443
oro+0.424
oster+0.401
olphins+0.393
Neg logit contributions
 leaflets-0.581
senal-0.551
 Masquerade-0.551
 pse-0.541
 Rollins-0.535
TokenDo
Token ID5211
Feature activation-1.88e-01

Pos logit contributions
uble+0.095
outer+0.094
oro+0.090
oster+0.085
TEXTURE+0.083
Neg logit contributions
 leaflets-0.121
senal-0.116
 Masquerade-0.114
 pse-0.113
 Rollins-0.111
Token not
Token ID407
Feature activation+2.60e-01

Pos logit contributions
 leaflets+0.638
senal+0.606
 Masquerade+0.598
 pse+0.588
 Rollins+0.578
Neg logit contributions
uble-0.717
outer-0.708
oro-0.685
oster-0.655
olphins-0.642
Token use
Token ID779
Feature activation+4.19e-01

Pos logit contributions
uble+0.948
outer+0.936
oro+0.902
oster+0.865
olphins+0.838
Neg logit contributions
 leaflets-0.921
senal-0.907
 Masquerade-0.870
 pse-0.857
 Rollins-0.843
Token responds
Token ID20067
Feature activation-6.99e-02

Pos logit contributions
uble+0.328
outer+0.325
oro+0.313
oster+0.298
olphins+0.292
Neg logit contributions
 leaflets-0.327
senal-0.310
 Masquerade-0.308
 pse-0.302
 Rollins-0.298
Token,
Token ID11
Feature activation-1.07e-01

Pos logit contributions
 leaflets+0.249
 Masquerade+0.234
senal+0.232
 pse+0.229
 Rollins+0.226
Neg logit contributions
uble-0.255
outer-0.253
oro-0.243
oster-0.232
olphins-0.228
Token "
Token ID366
Feature activation-7.73e-02

Pos logit contributions
 leaflets+0.317
senal+0.296
 Masquerade+0.294
 pse+0.287
 Rollins+0.283
Neg logit contributions
uble-0.455
outer-0.452
oro-0.438
oster-0.420
olphins-0.413
TokenYou
Token ID1639
Feature activation+1.81e-01

Pos logit contributions
 leaflets+0.333
senal+0.319
 Masquerade+0.317
 pse+0.312
 Rollins+0.308
Neg logit contributions
uble-0.225
outer-0.222
oro-0.212
oster-0.199
olphins-0.194
Token are
Token ID389
Feature activation+1.96e-01

Pos logit contributions
uble+0.587
outer+0.581
oro+0.558
oster+0.529
olphins+0.514
Neg logit contributions
 leaflets-0.717
senal-0.691
 Masquerade-0.678
 pse-0.669
 Rollins-0.658
Token such
Token ID884
Feature activation+1.69e+00

Pos logit contributions
uble+0.698
outer+0.690
oro+0.664
oster+0.632
olphins+0.621
Neg logit contributions
 leaflets-0.715
senal-0.677
 Masquerade-0.673
 pse-0.660
 Rollins-0.652
Token a
Token ID257
Feature activation+8.18e-01

Pos logit contributions
outer+5.630
uble+5.570
oro+5.477
oster+5.293
TEXTURE+5.114
Neg logit contributions
senal-6.130
 leaflets-6.118
 pse-5.772
 Masquerade-5.705
 Dent-5.606
Token tease
Token ID34691
Feature activation+8.11e-01

Pos logit contributions
uble+2.932
outer+2.917
oro+2.801
oster+2.699
TEXTURE+2.623
Neg logit contributions
 leaflets-2.936
senal-2.837
 Masquerade-2.733
 pse-2.720
 Dent-2.660
Token."
Token ID526
Feature activation+1.24e-01

Pos logit contributions
uble+2.545
outer+2.496
oro+2.410
oster+2.305
obe+2.219
Neg logit contributions
 leaflets-3.276
senal-3.215
 pse-3.081
 Masquerade-3.080
cffff-2.986
Token
Token ID198
Feature activation+2.10e-01

Pos logit contributions
uble+0.386
outer+0.381
oro+0.365
oster+0.345
olphins+0.337
Neg logit contributions
 leaflets-0.505
senal-0.482
 Masquerade-0.478
 pse-0.472
 Rollins-0.464
Token
Token ID198
Feature activation+2.07e-01

Pos logit contributions
uble+0.649
outer+0.642
oro+0.615
oster+0.581
TEXTURE+0.566
Neg logit contributions
 leaflets-0.869
senal-0.839
 Masquerade-0.823
 pse-0.816
 Rollins-0.799
Token Share
Token ID8734
Feature activation-4.97e-01

Pos logit contributions
 leaflets+2.338
 Masquerade+2.149
 Rollins+2.072
 Dent+2.069
 pse+2.066
Neg logit contributions
uble-3.807
outer-3.790
oro-3.640
TEXTURE-3.492
olphins-3.491
Token this
Token ID428
Feature activation-7.55e-01

Pos logit contributions
 leaflets+1.710
 Masquerade+1.592
 Rollins+1.543
 Dent+1.535
 pse+1.528
Neg logit contributions
outer-1.885
uble-1.873
oro-1.795
oster-1.720
TEXTURE-1.693
Token story
Token ID1621
Feature activation-4.97e-01

Pos logit contributions
 leaflets+1.150
 Masquerade+0.965
 Dent+0.890
 pse+0.890
senal+0.887
Neg logit contributions
uble-4.294
outer-4.253
oro-4.174
oster-4.047
TEXTURE-4.015
Token:
Token ID25
Feature activation-2.55e-02

Pos logit contributions
 leaflets+1.556
 Masquerade+1.449
 Dent+1.392
 Rollins+1.388
 pse+1.388
Neg logit contributions
uble-2.012
outer-2.000
oro-1.939
oster-1.849
olphins-1.834
Token http
Token ID2638
Feature activation+9.82e-01

Pos logit contributions
 leaflets+0.133
senal+0.128
 Masquerade+0.128
 pse+0.126
 Rollins+0.125
Neg logit contributions
uble-0.051
outer-0.050
oro-0.046
oster-0.042
olphins-0.041
Token://
Token ID1378
Feature activation+1.60e+00

Pos logit contributions
uble+1.177
outer+1.152
oro+1.018
oster+0.876
TEXTURE+0.788
Neg logit contributions
senal-6.003
 leaflets-5.888
 pse-5.718
 Masquerade-5.662
cffff-5.568
Tokenusat
Token ID37937
Feature activation+1.12e+00

Pos logit contributions
outer+2.612
uble+2.570
oro+2.292
oster+2.106
obe+2.007
Neg logit contributions
senal-8.803
 leaflets-8.799
 Masquerade-8.590
 pse-8.524
 Dent-8.340
Token.
Token ID13
Feature activation+7.51e-01

Pos logit contributions
uble+2.607
outer+2.555
oro+2.442
oster+2.285
usa+2.188
Neg logit contributions
senal-5.805
 leaflets-5.440
 pse-5.410
 Masquerade-5.195
cffff-5.132
Tokenly
Token ID306
Feature activation+1.37e+00

Pos logit contributions
uble+1.517
outer+1.474
oro+1.389
oster+1.276
olphins+1.192
Neg logit contributions
 leaflets-3.919
senal-3.848
 Masquerade-3.765
 pse-3.736
 Rollins-3.677
Token/
Token ID14
Feature activation+6.10e-01

Pos logit contributions
uble+2.651
outer+2.538
oro+2.490
oster+2.262
TEXTURE+2.181
Neg logit contributions
senal-7.627
 leaflets-7.254
 pse-7.099
cffff-6.817
 Masquerade-6.813
Token1
Token ID16
Feature activation+8.79e-01

Pos logit contributions
uble+1.881
outer+1.867
oro+1.778
oster+1.682
TEXTURE+1.651
Neg logit contributions
 leaflets-2.556
senal-2.500
 Masquerade-2.411
 pse-2.381
 Dent-2.317
Token Share
Token ID8734
Feature activation-5.74e-01

Pos logit contributions
 leaflets+2.518
 Masquerade+2.294
 Dent+2.226
 Rollins+2.210
 pse+2.192
Neg logit contributions
uble-4.235
outer-4.216
oro-4.058
TEXTURE-3.910
olphins-3.899
Token this
Token ID428
Feature activation-6.64e-01

Pos logit contributions
 leaflets+1.956
 Masquerade+1.812
 Rollins+1.752
 Dent+1.747
 pse+1.730
Neg logit contributions
outer-2.202
uble-2.186
oro-2.101
oster-2.012
TEXTURE-1.986
Token story
Token ID1621
Feature activation-5.08e-01

Pos logit contributions
 leaflets+1.022
 Masquerade+0.859
 pse+0.805
senal+0.797
 Dent+0.794
Neg logit contributions
uble-3.775
outer-3.734
oro-3.663
oster-3.554
TEXTURE-3.523
Token:
Token ID25
Feature activation-1.04e-01

Pos logit contributions
 leaflets+1.586
 Masquerade+1.477
 Dent+1.419
 Rollins+1.414
 pse+1.412
Neg logit contributions
uble-2.064
outer-2.049
oro-1.986
oster-1.895
olphins-1.882
Token http
Token ID2638
Feature activation+9.05e-01

Pos logit contributions
 leaflets+0.534
senal+0.514
 Masquerade+0.511
 pse+0.505
 Rollins+0.500
Neg logit contributions
uble-0.219
outer-0.215
oro-0.201
oster-0.185
olphins-0.178
Token://
Token ID1378
Feature activation+1.60e+00

Pos logit contributions
uble+1.102
outer+1.093
oro+0.958
oster+0.824
TEXTURE+0.740
Neg logit contributions
senal-5.498
 leaflets-5.407
 pse-5.245
 Masquerade-5.210
cffff-5.108
Tokencin
Token ID17879
Feature activation+5.14e-01

Pos logit contributions
outer+6.526
uble+6.381
oro+6.129
oster+5.946
obe+5.772
Neg logit contributions
 leaflets-4.882
senal-4.874
 Masquerade-4.727
 pse-4.703
 Rollins-4.504
Token.
Token ID13
Feature activation+3.56e-01

Pos logit contributions
uble+1.257
outer+1.245
oro+1.182
oster+1.135
usa+1.091
Neg logit contributions
senal-2.485
 leaflets-2.433
 Masquerade-2.371
 pse-2.363
 Rollins-2.273
Tokenci
Token ID979
Feature activation+4.44e-01

Pos logit contributions
uble+1.216
outer+1.213
oro+1.182
oster+1.126
obe+1.086
Neg logit contributions
 leaflets-1.346
senal-1.326
 Masquerade-1.277
 pse-1.259
 Rollins-1.234
Token/
Token ID14
Feature activation+9.00e-01

Pos logit contributions
uble+1.055
outer+1.038
oro+0.983
oster+0.912
olphins+0.880
Neg logit contributions
 leaflets-2.145
senal-2.073
 Masquerade-2.050
 pse-2.027
 Rollins-2.001
Token2
Token ID17
Feature activation+7.38e-01

Pos logit contributions
uble+2.544
outer+2.543
oro+2.400
oster+2.271
usa+2.240
Neg logit contributions
 leaflets-3.962
senal-3.858
 Masquerade-3.738
 pse-3.680
 Dent-3.603
Token Share
Token ID8734
Feature activation-6.43e-01

Pos logit contributions
 leaflets+2.453
 Masquerade+2.254
 pse+2.178
 Rollins+2.171
senal+2.171
Neg logit contributions
uble-3.880
outer-3.862
oro-3.716
oster-3.563
TEXTURE-3.559
Token this
Token ID428
Feature activation-6.43e-01

Pos logit contributions
 leaflets+2.176
 Masquerade+2.020
 Rollins+1.958
 Dent+1.948
 pse+1.926
Neg logit contributions
outer-2.472
uble-2.448
oro-2.352
oster-2.256
TEXTURE-2.232
Token story
Token ID1621
Feature activation-4.44e-01

Pos logit contributions
 leaflets+1.024
 Masquerade+0.874
senal+0.839
 pse+0.818
 Dent+0.806
Neg logit contributions
uble-3.615
outer-3.585
oro-3.513
oster-3.404
TEXTURE-3.368
Token:
Token ID25
Feature activation-6.46e-02

Pos logit contributions
 leaflets+1.414
 Masquerade+1.316
senal+1.276
 pse+1.270
 Dent+1.265
Neg logit contributions
uble-1.783
outer-1.770
oro-1.716
oster-1.636
olphins-1.620
Token http
Token ID2638
Feature activation+9.35e-01

Pos logit contributions
 leaflets+0.339
senal+0.328
 Masquerade+0.326
 pse+0.322
 Rollins+0.319
Neg logit contributions
uble-0.127
outer-0.124
oro-0.115
oster-0.105
olphins-0.101
Token://
Token ID1378
Feature activation+1.59e+00

Pos logit contributions
uble+1.137
outer+1.113
oro+0.979
oster+0.848
TEXTURE+0.765
Neg logit contributions
senal-5.688
 leaflets-5.590
 pse-5.436
 Masquerade-5.380
cffff-5.292
Tokenusat
Token ID37937
Feature activation+1.07e+00

Pos logit contributions
outer+2.812
uble+2.807
oro+2.505
oster+2.269
usa+2.229
Neg logit contributions
 leaflets-8.506
senal-8.469
 Masquerade-8.325
 pse-8.238
 Dent-8.054
Token.
Token ID13
Feature activation+7.11e-01

Pos logit contributions
uble+2.531
outer+2.491
oro+2.375
oster+2.225
usa+2.136
Neg logit contributions
senal-5.499
 leaflets-5.190
 pse-5.140
 Masquerade-4.949
cffff-4.885
Tokenly
Token ID306
Feature activation+1.43e+00

Pos logit contributions
uble+1.435
outer+1.394
oro+1.317
oster+1.206
olphins+1.128
Neg logit contributions
 leaflets-3.708
senal-3.647
 Masquerade-3.565
 pse-3.536
 Rollins-3.482
Token/
Token ID14
Feature activation+5.61e-01

Pos logit contributions
uble+2.694
outer+2.573
oro+2.525
oster+2.285
TEXTURE+2.210
Neg logit contributions
senal-8.035
 leaflets-7.579
 pse-7.461
anwhile-7.152
cffff-7.145
Token1
Token ID16
Feature activation+8.32e-01

Pos logit contributions
uble+1.767
outer+1.750
oro+1.673
oster+1.579
TEXTURE+1.543
Neg logit contributions
 leaflets-2.321
senal-2.260
 Masquerade-2.184
 pse-2.157
 Dent-2.105
Token $
Token ID720
Feature activation+4.88e-01

Pos logit contributions
uble+1.917
outer+1.882
oro+1.834
oster+1.768
olphins+1.735
Neg logit contributions
 leaflets-1.668
senal-1.596
 Masquerade-1.563
 pse-1.535
 Rollins-1.484
Token11
Token ID1157
Feature activation-1.94e-01

Pos logit contributions
uble+1.686
outer+1.672
oro+1.609
oster+1.531
TEXTURE+1.508
Neg logit contributions
 leaflets-1.847
senal-1.834
 pse-1.756
 Masquerade-1.729
cffff-1.666
Token.
Token ID13
Feature activation-1.55e-02

Pos logit contributions
 leaflets+0.816
senal+0.775
 Masquerade+0.772
 pse+0.760
 Rollins+0.754
Neg logit contributions
uble-0.580
outer-0.575
oro-0.550
oster-0.514
TEXTURE-0.508
Token25
Token ID1495
Feature activation+8.14e-02

Pos logit contributions
 leaflets+0.056
senal+0.053
 Masquerade+0.053
 pse+0.052
 Rollins+0.051
Neg logit contributions
uble-0.056
outer-0.055
oro-0.053
oster-0.051
olphins-0.050
Token million
Token ID1510
Feature activation+9.55e-02

Pos logit contributions
uble+0.262
outer+0.258
oro+0.248
oster+0.234
olphins+0.229
Neg logit contributions
 leaflets-0.325
senal-0.310
 Masquerade-0.308
 pse-0.303
 Rollins-0.299
Token contract
Token ID2775
Feature activation+1.56e+00

Pos logit contributions
uble+0.387
outer+0.382
oro+0.371
oster+0.356
olphins+0.350
Neg logit contributions
 leaflets-0.303
senal-0.285
 Masquerade-0.282
 pse-0.276
 Rollins-0.271
Token signed
Token ID4488
Feature activation+5.21e-01

Pos logit contributions
uble+4.930
outer+4.750
oro+4.540
oster+4.454
olphins+4.253
Neg logit contributions
 leaflets-6.201
senal-6.101
 Masquerade-5.863
 pse-5.741
cffff-5.652
Token in
Token ID287
Feature activation+3.74e-01

Pos logit contributions
uble+1.951
outer+1.888
oro+1.840
oster+1.761
olphins+1.732
Neg logit contributions
 leaflets-1.804
senal-1.753
 Masquerade-1.694
 pse-1.679
 Rollins-1.643
Token March
Token ID2805
Feature activation+9.67e-01

Pos logit contributions
uble+1.099
outer+1.077
oro+1.039
oster+0.979
olphins+0.949
Neg logit contributions
 leaflets-1.577
senal-1.566
 Masquerade-1.500
 pse-1.493
cffff-1.469
Token 2016
Token ID1584
Feature activation+1.93e-01

Pos logit contributions
uble+2.849
outer+2.753
oro+2.691
oster+2.552
olphins+2.451
Neg logit contributions
senal-4.067
 leaflets-4.003
 pse-3.838
 Masquerade-3.830
cffff-3.780
Token
Token ID198
Feature activation+2.75e-01

Pos logit contributions
uble+0.602
outer+0.592
oro+0.568
oster+0.538
olphins+0.526
Neg logit contributions
 leaflets-0.791
senal-0.756
 Masquerade-0.750
 pse-0.739
 Rollins-0.728
Token at
Token ID379
Feature activation+2.87e-03

Pos logit contributions
uble+0.400
outer+0.396
oro+0.384
oster+0.368
olphins+0.361
Neg logit contributions
 leaflets-0.311
senal-0.293
 Masquerade-0.290
 pse-0.284
 Rollins-0.279
Token 9
Token ID860
Feature activation+4.85e-01

Pos logit contributions
uble+0.011
outer+0.011
oro+0.011
oster+0.010
olphins+0.010
Neg logit contributions
 leaflets-0.010
senal-0.009
 Masquerade-0.009
 pse-0.009
cffff-0.009
Token:
Token ID25
Feature activation+5.50e-02

Pos logit contributions
uble+1.807
outer+1.794
oro+1.734
oster+1.649
TEXTURE+1.613
Neg logit contributions
 leaflets-1.691
senal-1.691
 pse-1.600
 Masquerade-1.582
cffff-1.521
Token28
Token ID2078
Feature activation+3.57e-01

Pos logit contributions
uble+0.216
outer+0.214
oro+0.206
oster+0.197
TEXTURE+0.195
Neg logit contributions
 leaflets-0.183
senal-0.181
 pse-0.172
 Masquerade-0.170
cffff-0.163
Tokenam
Token ID321
Feature activation+9.23e-01

Pos logit contributions
uble+0.892
outer+0.882
oro+0.834
oster+0.775
olphins+0.749
Neg logit contributions
 leaflets-1.687
senal-1.626
 Masquerade-1.608
 pse-1.594
 Rollins-1.570
Token PST
Token ID28220
Feature activation+1.56e+00

Pos logit contributions
uble+2.247
outer+2.184
oro+2.049
oster+1.941
TERN+1.865
Neg logit contributions
senal-4.352
 leaflets-4.318
 pse-4.201
 Masquerade-4.102
cffff-4.083
Token
Token ID198
Feature activation+2.24e-02

Pos logit contributions
uble+4.164
outer+4.092
oro+3.900
oster+3.675
fashion+3.623
Neg logit contributions
 leaflets-6.690
 pse-6.427
senal-6.414
 Masquerade-6.273
 Rollins-6.196
Token
Token ID198
Feature activation-2.05e-02

Pos logit contributions
uble+0.072
outer+0.071
oro+0.068
oster+0.065
olphins+0.063
Neg logit contributions
 leaflets-0.089
 Masquerade-0.085
senal-0.083
 Rollins-0.082
 pse-0.082
TokenDo
Token ID5211
Feature activation-1.97e-01

Pos logit contributions
 leaflets+0.084
senal+0.080
 Masquerade+0.079
 pse+0.078
 Rollins+0.077
Neg logit contributions
uble-0.064
outer-0.064
oro-0.061
oster-0.058
TEXTURE-0.056
Token use
Token ID779
Feature activation+3.29e-01

Pos logit contributions
 leaflets+0.636
senal+0.599
 Masquerade+0.594
 pse+0.582
 Rollins+0.572
Neg logit contributions
uble-0.787
outer-0.779
oro-0.753
oster-0.721
olphins-0.709
Token social
Token ID1919
Feature activation+2.59e-01

Pos logit contributions
uble+1.545
outer+1.523
oro+1.488
oster+1.435
TEXTURE+1.412
Neg logit contributions
 leaflets-0.813
senal-0.774
 Masquerade-0.751
 pse-0.730
 Rollins-0.710
Token.,
Token ID1539
Feature activation+1.26e-01

Pos logit contributions
uble+1.608
outer+1.543
oro+1.485
oster+1.374
olphins+1.336
Neg logit contributions
 leaflets-3.648
senal-3.515
 Masquerade-3.492
 pse-3.458
 Rollins-3.416
Token where
Token ID810
Feature activation+2.23e-01

Pos logit contributions
uble+0.470
outer+0.464
oro+0.451
oster+0.430
olphins+0.425
Neg logit contributions
 leaflets-0.433
senal-0.416
 Masquerade-0.406
 pse-0.402
 Rollins-0.392
Token killer
Token ID11868
Feature activation+6.48e-01

Pos logit contributions
uble+0.870
outer+0.859
oro+0.843
oster+0.802
olphins+0.796
Neg logit contributions
 leaflets-0.723
senal-0.698
 Masquerade-0.678
 pse-0.668
 Rollins-0.654
Token whale
Token ID22206
Feature activation+9.42e-01

Pos logit contributions
uble+2.623
outer+2.585
oro+2.539
olphins+2.469
oster+2.420
Neg logit contributions
 leaflets-1.962
senal-1.959
 Masquerade-1.832
 pse-1.817
 Rollins-1.789
Token Til
Token ID40422
Feature activation+8.16e-01

Pos logit contributions
uble+3.784
outer+3.722
oro+3.708
olphins+3.557
oster+3.534
Neg logit contributions
senal-2.819
 leaflets-2.779
 Masquerade-2.643
 pse-2.588
cffff-2.579
Tokenik
Token ID1134
Feature activation+1.54e+00

Pos logit contributions
uble+2.335
outer+2.309
oro+2.274
oster+2.122
olphins+2.061
Neg logit contributions
 leaflets-3.555
senal-3.476
 Masquerade-3.388
 pse-3.347
cffff-3.287
Tokenum
Token ID388
Feature activation+3.65e-01

Pos logit contributions
oro+5.488
uble+5.399
outer+5.319
usa+5.045
olphins+4.962
Neg logit contributions
 leaflets-5.371
senal-5.280
cffff-5.263
 Masquerade-5.142
 pse-5.121
Token was
Token ID373
Feature activation-9.75e-02

Pos logit contributions
uble+1.391
outer+1.371
oro+1.350
oster+1.273
olphins+1.270
Neg logit contributions
 leaflets-1.217
senal-1.175
 Masquerade-1.147
 pse-1.121
 Rollins-1.102
Token involved
Token ID2950
Feature activation+8.82e-02

Pos logit contributions
 leaflets+0.244
senal+0.226
 Masquerade+0.223
 pse+0.217
 Rollins+0.212
Neg logit contributions
uble-0.459
outer-0.455
oro-0.443
oster-0.427
olphins-0.421
Token in
Token ID287
Feature activation-1.77e-03

Pos logit contributions
uble+0.311
outer+0.306
oro+0.296
oster+0.282
olphins+0.276
Neg logit contributions
 leaflets-0.325
senal-0.310
 Masquerade-0.306
 pse-0.301
 Rollins-0.296
Token three
Token ID1115
Feature activation+1.40e-01

Pos logit contributions
 leaflets+0.006
senal+0.005
 Masquerade+0.005
 pse+0.005
 Rollins+0.005
Neg logit contributions
uble-0.007
outer-0.007
oro-0.007
oster-0.006
olphins-0.006
Tokencin
Token ID17879
Feature activation+5.14e-01

Pos logit contributions
outer+6.526
uble+6.381
oro+6.129
oster+5.946
obe+5.772
Neg logit contributions
 leaflets-4.882
senal-4.874
 Masquerade-4.727
 pse-4.703
 Rollins-4.504
Token.
Token ID13
Feature activation+3.56e-01

Pos logit contributions
uble+1.257
outer+1.245
oro+1.182
oster+1.135
usa+1.091
Neg logit contributions
senal-2.485
 leaflets-2.433
 Masquerade-2.371
 pse-2.363
 Rollins-2.273
Tokenci
Token ID979
Feature activation+4.44e-01

Pos logit contributions
uble+1.216
outer+1.213
oro+1.182
oster+1.126
obe+1.086
Neg logit contributions
 leaflets-1.346
senal-1.326
 Masquerade-1.277
 pse-1.259
 Rollins-1.234
Token/
Token ID14
Feature activation+9.00e-01

Pos logit contributions
uble+1.055
outer+1.038
oro+0.983
oster+0.912
olphins+0.880
Neg logit contributions
 leaflets-2.145
senal-2.073
 Masquerade-2.050
 pse-2.027
 Rollins-2.001
Token2
Token ID17
Feature activation+7.38e-01

Pos logit contributions
uble+2.544
outer+2.543
oro+2.400
oster+2.271
usa+2.240
Neg logit contributions
 leaflets-3.962
senal-3.858
 Masquerade-3.738
 pse-3.680
 Dent-3.603
Tokenyp
Token ID4464
Feature activation+1.48e+00

Pos logit contributions
uble+2.273
outer+2.249
oro+2.178
oster+2.038
obe+1.968
Neg logit contributions
 leaflets-3.078
senal-2.973
 Masquerade-2.924
 pse-2.861
 Dent-2.828
Tokend
Token ID67
Feature activation+2.98e-01

Pos logit contributions
uble+4.592
outer+4.548
oro+4.430
oster+4.178
obe+4.017
Neg logit contributions
 leaflets-6.001
senal-5.851
 Masquerade-5.713
 pse-5.549
 Dent-5.463
TokenG
Token ID38
Feature activation+5.35e-01

Pos logit contributions
uble+0.945
outer+0.932
oro+0.896
oster+0.847
olphins+0.822
Neg logit contributions
 leaflets-1.217
senal-1.167
 Masquerade-1.154
 pse-1.132
 Rollins-1.115
Tokenuf
Token ID3046
Feature activation+1.98e-01

Pos logit contributions
uble+1.662
outer+1.649
oro+1.585
oster+1.490
obe+1.437
Neg logit contributions
 leaflets-2.221
senal-2.133
 Masquerade-2.102
 pse-2.069
 Rollins-2.032
Token<|endoftext|>
Token ID50256
Feature activation+1.01e-01

Pos logit contributions
uble+0.517
outer+0.510
oro+0.487
oster+0.455
olphins+0.440
Neg logit contributions
 leaflets-0.912
senal-0.882
 Masquerade-0.867
 pse-0.863
 Rollins-0.843
TokenA
Token ID32
Feature activation-2.76e-01

Pos logit contributions
uble+0.329
outer+0.327
oro+0.312
oster+0.296
TEXTURE+0.291
Neg logit contributions
 leaflets-0.403
senal-0.386
 Masquerade-0.380
 pse-0.376
 Rollins-0.368
Token at
Token ID379
Feature activation-8.84e-02

Pos logit contributions
 leaflets+0.381
 Masquerade+0.354
senal+0.349
 pse+0.344
 Rollins+0.341
Neg logit contributions
uble-0.505
outer-0.501
oro-0.484
oster-0.464
olphins-0.457
Token 9
Token ID860
Feature activation+4.65e-01

Pos logit contributions
 leaflets+0.293
senal+0.282
 Masquerade+0.273
 pse+0.271
 Rollins+0.263
Neg logit contributions
uble-0.344
outer-0.340
oro-0.330
oster-0.315
olphins-0.309
Token:
Token ID25
Feature activation-5.01e-03

Pos logit contributions
uble+1.719
outer+1.706
oro+1.649
oster+1.570
TEXTURE+1.537
Neg logit contributions
senal-1.663
 leaflets-1.638
 pse-1.561
 Masquerade-1.531
cffff-1.483
Token01
Token ID486
Feature activation+3.78e-01

Pos logit contributions
 leaflets+0.017
senal+0.016
 pse+0.016
 Masquerade+0.015
cffff+0.015
Neg logit contributions
uble-0.020
outer-0.019
oro-0.019
oster-0.018
TEXTURE-0.018
Tokenam
Token ID321
Feature activation+9.21e-01

Pos logit contributions
uble+0.964
outer+0.953
oro+0.903
oster+0.837
olphins+0.811
Neg logit contributions
 leaflets-1.777
senal-1.712
 Masquerade-1.692
 pse-1.679
 Rollins-1.651
Token PDT
Token ID28288
Feature activation+1.48e+00

Pos logit contributions
uble+3.014
outer+2.956
oro+2.869
oster+2.711
TEXTURE+2.672
Neg logit contributions
senal-3.661
 leaflets-3.545
 pse-3.436
 Masquerade-3.332
cffff-3.309
Token
Token ID198
Feature activation+2.25e-01

Pos logit contributions
uble+4.010
outer+3.958
oro+3.758
oster+3.533
olphins+3.519
Neg logit contributions
 leaflets-6.355
senal-6.072
 pse-6.054
 Masquerade-6.016
 Rollins-5.883
Token
Token ID198
Feature activation+1.50e-01

Pos logit contributions
uble+0.703
outer+0.694
oro+0.665
oster+0.629
olphins+0.614
Neg logit contributions
 leaflets-0.923
senal-0.882
 Masquerade-0.875
 pse-0.862
 Rollins-0.849
TokenDo
Token ID5211
Feature activation-2.17e-01

Pos logit contributions
uble+0.469
outer+0.466
oro+0.447
oster+0.422
TEXTURE+0.414
Neg logit contributions
 leaflets-0.613
senal-0.591
 Masquerade-0.577
 pse-0.575
 Rollins-0.560
Token use
Token ID779
Feature activation+4.24e-01

Pos logit contributions
 leaflets+0.685
senal+0.643
 Masquerade+0.639
 pse+0.624
 Rollins+0.615
Neg logit contributions
uble-0.878
outer-0.871
oro-0.842
oster-0.806
olphins-0.793
Token social
Token ID1919
Feature activation+3.05e-01

Pos logit contributions
uble+1.973
outer+1.944
oro+1.901
oster+1.832
TEXTURE+1.805
Neg logit contributions
 leaflets-1.056
senal-1.016
 Masquerade-0.978
 pse-0.950
 Rollins-0.925
Token import
Token ID1330
Feature activation+2.11e-01

Pos logit contributions
uble+0.412
outer+0.405
oro+0.382
oster+0.355
olphins+0.343
Neg logit contributions
 leaflets-0.781
senal-0.755
 Masquerade-0.744
 pse-0.733
 Rollins-0.731
Token paths
Token ID13532
Feature activation+9.36e-01

Pos logit contributions
uble+0.803
outer+0.796
oro+0.769
oster+0.739
TEXTURE+0.719
Neg logit contributions
 leaflets-0.707
senal-0.680
 Masquerade-0.661
 pse-0.643
 Rollins-0.641
Token import
Token ID1330
Feature activation+4.88e-01

Pos logit contributions
uble+3.200
outer+3.195
oro+3.044
oster+2.900
obe+2.818
Neg logit contributions
 leaflets-3.491
senal-3.348
 Masquerade-3.276
 Rollins-3.237
cffff-3.199
Token n
Token ID299
Feature activation+5.76e-01

Pos logit contributions
uble+1.868
outer+1.852
oro+1.795
oster+1.724
TEXTURE+1.668
Neg logit contributions
 leaflets-1.608
senal-1.562
 Masquerade-1.499
cffff-1.468
 Rollins-1.456
Tokenumpy
Token ID32152
Feature activation+1.55e-01

Pos logit contributions
uble+1.883
outer+1.878
oro+1.815
oster+1.726
obe+1.667
Neg logit contributions
 leaflets-2.266
senal-2.177
 Masquerade-2.145
 Rollins-2.087
 pse-2.081
Token as
Token ID355
Feature activation+1.47e+00

Pos logit contributions
uble+0.558
outer+0.551
oro+0.532
oster+0.508
TEXTURE+0.493
Neg logit contributions
 leaflets-0.564
senal-0.537
 Masquerade-0.530
 pse-0.520
 Rollins-0.516
Token np
Token ID45941
Feature activation+6.31e-01

Pos logit contributions
uble+5.715
oro+5.555
outer+5.530
oster+5.365
obe+5.076
Neg logit contributions
senal-4.676
 leaflets-4.675
 Masquerade-4.520
 Dent-4.309
cffff-4.292
Token import
Token ID1330
Feature activation+6.51e-01

Pos logit contributions
uble+1.928
outer+1.905
oro+1.835
oster+1.731
obe+1.667
Neg logit contributions
 leaflets-2.581
senal-2.499
 Masquerade-2.443
cffff-2.395
 Rollins-2.388
Token arg
Token ID1822
Feature activation+3.45e-01

Pos logit contributions
uble+2.559
outer+2.508
oro+2.464
oster+2.359
TEXTURE+2.267
Neg logit contributions
 leaflets-2.058
senal-2.043
 Masquerade-1.942
cffff-1.882
 Rollins-1.862
Tokenparse
Token ID29572
Feature activation+4.04e-01

Pos logit contributions
uble+1.213
outer+1.208
oro+1.151
oster+1.111
obe+1.066
Neg logit contributions
 leaflets-1.281
senal-1.213
 Masquerade-1.213
 Rollins-1.185
 pse-1.169
Token import
Token ID1330
Feature activation+5.22e-01

Pos logit contributions
uble+1.264
outer+1.249
oro+1.197
oster+1.128
TEXTURE+1.090
Neg logit contributions
 leaflets-1.644
senal-1.583
 Masquerade-1.555
 Rollins-1.525
 pse-1.519
Token import
Token ID1330
Feature activation-6.57e-02

Pos logit contributions
uble+0.710
outer+0.696
oro+0.653
oster+0.597
olphins+0.576
Neg logit contributions
 leaflets-1.725
senal-1.671
 Masquerade-1.654
 pse-1.634
 Rollins-1.618
Token paths
Token ID13532
Feature activation+1.15e+00

Pos logit contributions
 leaflets+0.163
senal+0.153
 Masquerade+0.150
 pse+0.145
 Rollins+0.143
Neg logit contributions
uble-0.309
outer-0.306
oro-0.298
oster-0.287
olphins-0.283
Token import
Token ID1330
Feature activation+3.40e-01

Pos logit contributions
outer+2.044
uble+2.037
oro+1.910
oster+1.704
usa+1.605
Neg logit contributions
senal-6.207
 leaflets-6.113
 Masquerade-5.892
 pse-5.856
cffff-5.848
Token n
Token ID299
Feature activation+5.57e-01

Pos logit contributions
uble+1.169
outer+1.157
oro+1.117
oster+1.058
TEXTURE+1.036
Neg logit contributions
 leaflets-1.270
senal-1.232
 Masquerade-1.203
 pse-1.173
 Rollins-1.167
Tokenumpy
Token ID32152
Feature activation+1.46e-01

Pos logit contributions
uble+1.781
outer+1.751
oro+1.718
oster+1.621
olphins+1.579
Neg logit contributions
senal-2.263
 leaflets-2.239
 Masquerade-2.148
 pse-2.101
 Rollins-2.061
Token as
Token ID355
Feature activation+1.44e+00

Pos logit contributions
uble+0.566
outer+0.560
oro+0.541
oster+0.517
olphins+0.508
Neg logit contributions
 leaflets-0.488
senal-0.459
 Masquerade-0.456
 pse-0.447
 Rollins-0.440
Token np
Token ID45941
Feature activation+8.57e-01

Pos logit contributions
uble+5.463
oro+5.432
outer+5.360
oster+5.072
olphins+5.003
Neg logit contributions
senal-5.025
 leaflets-4.481
 Masquerade-4.421
cffff-4.200
anwhile-4.199
Token import
Token ID1330
Feature activation+6.23e-01

Pos logit contributions
uble+1.572
outer+1.550
oro+1.453
oster+1.325
olphins+1.224
Neg logit contributions
senal-4.532
 leaflets-4.519
 Masquerade-4.378
cffff-4.313
 Rollins-4.306
Token arg
Token ID1822
Feature activation+6.62e-01

Pos logit contributions
uble+1.639
outer+1.617
oro+1.555
oster+1.452
olphins+1.365
Neg logit contributions
senal-2.787
 leaflets-2.784
 Masquerade-2.738
cffff-2.639
 Rollins-2.624
Tokenparse
Token ID29572
Feature activation+6.79e-01

Pos logit contributions
uble+2.344
outer+2.326
oro+2.236
oster+2.132
olphins+2.070
Neg logit contributions
senal-2.461
 leaflets-2.452
 Masquerade-2.333
 pse-2.274
 Rollins-2.259
Token import
Token ID1330
Feature activation+5.07e-01

Pos logit contributions
uble+1.296
outer+1.285
oro+1.198
oster+1.094
olphins+1.016
Neg logit contributions
 leaflets-3.566
senal-3.558
 Masquerade-3.432
 pse-3.391
 Rollins-3.387
Token $
Token ID720
Feature activation+4.72e-01

Pos logit contributions
uble+1.503
outer+1.477
oro+1.439
oster+1.385
olphins+1.360
Neg logit contributions
 leaflets-1.286
senal-1.231
 Masquerade-1.205
 pse-1.184
 Rollins-1.145
Token16
Token ID1433
Feature activation-1.25e-01

Pos logit contributions
uble+1.619
outer+1.607
oro+1.544
oster+1.470
TEXTURE+1.449
Neg logit contributions
 leaflets-1.805
senal-1.797
 pse-1.719
 Masquerade-1.689
cffff-1.630
Token.
Token ID13
Feature activation+7.65e-02

Pos logit contributions
 leaflets+0.524
senal+0.498
 Masquerade+0.496
 pse+0.488
 Rollins+0.484
Neg logit contributions
uble-0.377
outer-0.373
oro-0.357
oster-0.335
TEXTURE-0.330
Token25
Token ID1495
Feature activation+4.61e-02

Pos logit contributions
uble+0.266
outer+0.262
oro+0.252
oster+0.241
TEXTURE+0.235
Neg logit contributions
 leaflets-0.288
senal-0.278
 Masquerade-0.270
 pse-0.269
 Rollins-0.261
Token million
Token ID1510
Feature activation+6.66e-03

Pos logit contributions
uble+0.149
outer+0.147
oro+0.141
oster+0.134
TEXTURE+0.131
Neg logit contributions
 leaflets-0.183
senal-0.174
 Masquerade-0.173
 pse-0.170
 Rollins-0.168
Token contract
Token ID2775
Feature activation+1.44e+00

Pos logit contributions
uble+0.027
outer+0.026
oro+0.026
oster+0.025
olphins+0.024
Neg logit contributions
 leaflets-0.021
senal-0.020
 Masquerade-0.020
 pse-0.019
 Rollins-0.019
Token signed
Token ID4488
Feature activation+4.65e-01

Pos logit contributions
uble+4.646
outer+4.508
oro+4.308
oster+4.211
olphins+4.046
Neg logit contributions
 leaflets-5.641
senal-5.549
 Masquerade-5.331
 pse-5.221
cffff-5.128
Token in
Token ID287
Feature activation+3.57e-01

Pos logit contributions
uble+1.740
outer+1.688
oro+1.648
oster+1.574
olphins+1.547
Neg logit contributions
 leaflets-1.608
senal-1.576
 Masquerade-1.511
 pse-1.495
 Rollins-1.466
Token February
Token ID3945
Feature activation+1.01e+00

Pos logit contributions
uble+1.057
outer+1.037
oro+1.001
oster+0.943
olphins+0.918
Neg logit contributions
 leaflets-1.499
senal-1.486
 Masquerade-1.424
 pse-1.417
cffff-1.393
Token 2017
Token ID2177
Feature activation+3.78e-02

Pos logit contributions
uble+2.935
outer+2.820
oro+2.767
oster+2.618
olphins+2.527
Neg logit contributions
senal-4.325
 leaflets-4.252
 pse-4.100
 Masquerade-4.069
cffff-4.016
Token
Token ID198
Feature activation+2.55e-01

Pos logit contributions
uble+0.119
outer+0.118
oro+0.113
oster+0.107
olphins+0.104
Neg logit contributions
 leaflets-0.153
senal-0.146
 Masquerade-0.145
 pse-0.143
 Rollins-0.141
Tokenyear
Token ID1941
Feature activation+4.46e-01

Pos logit contributions
outer+0.469
uble+0.467
oro+0.446
oster+0.425
olphins+0.413
Neg logit contributions
 leaflets-0.629
senal-0.607
 Masquerade-0.596
 pse-0.594
 Rollins-0.575
Token,
Token ID11
Feature activation+2.61e-01

Pos logit contributions
uble+1.570
outer+1.531
oro+1.493
oster+1.417
olphins+1.397
Neg logit contributions
 leaflets-1.651
senal-1.593
 Masquerade-1.557
 pse-1.538
 Rollins-1.490
Token $
Token ID720
Feature activation+1.02e+00

Pos logit contributions
uble+1.015
outer+0.997
oro+0.971
oster+0.937
olphins+0.919
Neg logit contributions
 leaflets-0.861
senal-0.833
 Masquerade-0.809
 pse-0.795
 Dent-0.767
Token72
Token ID4761
Feature activation-8.54e-02

Pos logit contributions
uble+3.623
outer+3.608
oro+3.475
oster+3.314
TEXTURE+3.302
Neg logit contributions
senal-3.916
 leaflets-3.765
 pse-3.685
 Masquerade-3.485
cffff-3.389
Token million
Token ID1510
Feature activation+3.21e-01

Pos logit contributions
 leaflets+0.339
senal+0.320
 Masquerade+0.319
 pse+0.314
 Rollins+0.312
Neg logit contributions
uble-0.276
outer-0.274
oro-0.263
oster-0.246
TEXTURE-0.243
Token contract
Token ID2775
Feature activation+1.43e+00

Pos logit contributions
uble+1.229
outer+1.206
oro+1.173
oster+1.129
olphins+1.113
Neg logit contributions
 leaflets-1.092
senal-1.045
 Masquerade-1.022
 pse-1.006
 Rollins-0.977
Token with
Token ID351
Feature activation+2.36e-01

Pos logit contributions
uble+4.870
outer+4.736
oro+4.538
oster+4.372
olphins+4.262
Neg logit contributions
senal-5.365
 leaflets-5.216
 Masquerade-4.986
 pse-4.865
cffff-4.760
Token $
Token ID720
Feature activation+4.48e-01

Pos logit contributions
uble+0.907
outer+0.900
oro+0.872
oster+0.844
olphins+0.828
Neg logit contributions
 leaflets-0.774
senal-0.759
 Masquerade-0.732
 pse-0.720
cffff-0.698
Token37
Token ID2718
Feature activation-1.04e-01

Pos logit contributions
uble+1.589
outer+1.580
oro+1.521
oster+1.449
TEXTURE+1.429
Neg logit contributions
 leaflets-1.661
senal-1.645
 pse-1.570
 Masquerade-1.549
cffff-1.485
Token million
Token ID1510
Feature activation+5.51e-02

Pos logit contributions
 leaflets+0.426
senal+0.405
 Masquerade+0.403
 pse+0.396
 Rollins+0.392
Neg logit contributions
uble-0.327
outer-0.323
oro-0.309
oster-0.292
olphins-0.285
Token guaranteed
Token ID11462
Feature activation+1.14e-01

Pos logit contributions
uble+0.195
outer+0.192
oro+0.185
oster+0.178
olphins+0.174
Neg logit contributions
 leaflets-0.202
senal-0.195
 Masquerade-0.191
 pse-0.187
 Dent-0.183
Token:
Token ID25
Feature activation-6.46e-02

Pos logit contributions
 leaflets+1.414
 Masquerade+1.316
senal+1.276
 pse+1.270
 Dent+1.265
Neg logit contributions
uble-1.783
outer-1.770
oro-1.716
oster-1.636
olphins-1.620
Token http
Token ID2638
Feature activation+9.35e-01

Pos logit contributions
 leaflets+0.339
senal+0.328
 Masquerade+0.326
 pse+0.322
 Rollins+0.319
Neg logit contributions
uble-0.127
outer-0.124
oro-0.115
oster-0.105
olphins-0.101
Token://
Token ID1378
Feature activation+1.59e+00

Pos logit contributions
uble+1.137
outer+1.113
oro+0.979
oster+0.848
TEXTURE+0.765
Neg logit contributions
senal-5.688
 leaflets-5.590
 pse-5.436
 Masquerade-5.380
cffff-5.292
Tokenusat
Token ID37937
Feature activation+1.07e+00

Pos logit contributions
outer+2.812
uble+2.807
oro+2.505
oster+2.269
usa+2.229
Neg logit contributions
 leaflets-8.506
senal-8.469
 Masquerade-8.325
 pse-8.238
 Dent-8.054
Token.
Token ID13
Feature activation+7.11e-01

Pos logit contributions
uble+2.531
outer+2.491
oro+2.375
oster+2.225
usa+2.136
Neg logit contributions
senal-5.499
 leaflets-5.190
 pse-5.140
 Masquerade-4.949
cffff-4.885
Tokenly
Token ID306
Feature activation+1.43e+00

Pos logit contributions
uble+1.435
outer+1.394
oro+1.317
oster+1.206
olphins+1.128
Neg logit contributions
 leaflets-3.708
senal-3.647
 Masquerade-3.565
 pse-3.536
 Rollins-3.482
Token/
Token ID14
Feature activation+5.61e-01

Pos logit contributions
uble+2.694
outer+2.573
oro+2.525
oster+2.285
TEXTURE+2.210
Neg logit contributions
senal-8.035
 leaflets-7.579
 pse-7.461
anwhile-7.152
cffff-7.145
Token1
Token ID16
Feature activation+8.32e-01

Pos logit contributions
uble+1.767
outer+1.750
oro+1.673
oster+1.579
TEXTURE+1.543
Neg logit contributions
 leaflets-2.321
senal-2.260
 Masquerade-2.184
 pse-2.157
 Dent-2.105
TokenG
Token ID38
Feature activation+5.98e-01

Pos logit contributions
uble+2.583
outer+2.561
oro+2.479
oster+2.321
obe+2.249
Neg logit contributions
 leaflets-3.446
senal-3.332
 Masquerade-3.261
 pse-3.201
 Dent-3.160
Tokenq
Token ID80
Feature activation+5.52e-01

Pos logit contributions
uble+1.894
outer+1.881
oro+1.813
oster+1.702
obe+1.641
Neg logit contributions
 leaflets-2.448
senal-2.349
 Masquerade-2.318
 pse-2.273
 Rollins-2.238
TokenFP
Token ID5837
Feature activation+1.31e+00

Pos logit contributions
uble+1.740
outer+1.724
oro+1.660
oster+1.568
TEXTURE+1.508
Neg logit contributions
 leaflets-2.269
senal-2.180
 Masquerade-2.151
 pse-2.101
 Rollins-2.072
Token names
Token ID3891
Feature activation+2.86e-01

Pos logit contributions
 leaflets+0.245
senal+0.234
 Masquerade+0.230
 pse+0.224
 Rollins+0.221
Neg logit contributions
uble-0.322
outer-0.319
oro-0.309
oster-0.297
olphins-0.291
Token,
Token ID11
Feature activation-1.15e-01

Pos logit contributions
uble+1.034
outer+1.014
oro+0.980
oster+0.940
olphins+0.909
Neg logit contributions
 leaflets-1.022
senal-1.005
 Masquerade-0.968
 pse-0.951
 Rollins-0.932
Token and
Token ID290
Feature activation-1.25e-01

Pos logit contributions
 leaflets+0.388
senal+0.375
 Masquerade+0.367
 pse+0.357
 Rollins+0.350
Neg logit contributions
uble-0.441
outer-0.433
oro-0.419
oster-0.403
TEXTURE-0.393
Token the
Token ID262
Feature activation-3.48e-01

Pos logit contributions
 leaflets+0.412
senal+0.397
 Masquerade+0.389
 pse+0.376
 Rollins+0.368
Neg logit contributions
uble-0.486
outer-0.480
oro-0.464
oster-0.445
TEXTURE-0.434
Token #
Token ID1303
Feature activation+1.12e-01

Pos logit contributions
 leaflets+1.147
senal+1.099
 Masquerade+1.079
 pse+1.053
 Rollins+1.035
Neg logit contributions
uble-1.357
outer-1.342
oro-1.300
oster-1.240
olphins-1.215
TokenNever
Token ID12295
Feature activation+1.43e+00

Pos logit contributions
uble+0.275
outer+0.272
oro+0.258
oster+0.238
TEXTURE+0.231
Neg logit contributions
 leaflets-0.537
senal-0.515
 Masquerade-0.512
 pse-0.503
 Rollins-0.498
TokenTrump
Token ID6170
Feature activation+3.46e-01

Pos logit contributions
outer+3.293
uble+3.118
oro+3.082
oster+2.992
JUST+2.966
Neg logit contributions
senal-6.976
 leaflets-6.782
 pse-6.701
 Masquerade-6.570
anwhile-6.512
Token forces
Token ID3386
Feature activation+7.95e-02

Pos logit contributions
uble+1.304
outer+1.288
oro+1.255
oster+1.201
olphins+1.159
Neg logit contributions
 leaflets-1.173
senal-1.136
 Masquerade-1.114
 pse-1.090
 Rollins-1.066
Token have
Token ID423
Feature activation+4.34e-01

Pos logit contributions
uble+0.268
outer+0.265
oro+0.255
oster+0.244
olphins+0.236
Neg logit contributions
 leaflets-0.302
senal-0.294
 Masquerade-0.287
 pse-0.281
 Rollins-0.277
Token invested
Token ID13356
Feature activation+1.77e-01

Pos logit contributions
uble+1.626
outer+1.602
oro+1.547
oster+1.502
TEXTURE+1.441
Neg logit contributions
senal-1.472
 leaflets-1.447
 Masquerade-1.392
 pse-1.353
cffff-1.339
Token a
Token ID257
Feature activation+1.42e-01

Pos logit contributions
uble+0.668
outer+0.659
oro+0.637
oster+0.615
olphins+0.597
Neg logit contributions
 leaflets-0.595
senal-0.579
 Masquerade-0.564
 pse-0.550
 Rollins-0.542
Token we
Token ID356
Feature activation+1.62e-02

Pos logit contributions
 leaflets+0.693
senal+0.652
 Masquerade+0.649
 pse+0.636
 Rollins+0.626
Neg logit contributions
uble-0.799
outer-0.791
oro-0.764
oster-0.730
olphins-0.718
Token must
Token ID1276
Feature activation-2.15e-01

Pos logit contributions
uble+0.054
outer+0.053
oro+0.051
oster+0.049
olphins+0.047
Neg logit contributions
 leaflets-0.063
senal-0.060
 Masquerade-0.059
 pse-0.058
 Rollins-0.058
Token win
Token ID1592
Feature activation-1.90e-01

Pos logit contributions
 leaflets+0.666
senal+0.621
 Masquerade+0.619
 pse+0.607
 Rollins+0.596
Neg logit contributions
uble-0.885
outer-0.878
oro-0.851
oster-0.814
olphins-0.804
Token.
Token ID13
Feature activation+8.08e-02

Pos logit contributions
 leaflets+0.782
senal+0.746
 Masquerade+0.742
 pse+0.730
 Rollins+0.721
Neg logit contributions
uble-0.586
outer-0.578
oro-0.554
oster-0.523
olphins-0.511
Token<|endoftext|>
Token ID50256
Feature activation-1.32e-02

Pos logit contributions
uble+0.261
outer+0.258
oro+0.248
oster+0.236
TEXTURE+0.230
Neg logit contributions
 leaflets-0.321
senal-0.311
 pse-0.301
 Masquerade-0.299
cffff-0.293
TokenMr
Token ID5246
Feature activation+1.42e+00

Pos logit contributions
 leaflets+0.053
senal+0.050
 Masquerade+0.050
 pse+0.049
 Rollins+0.048
Neg logit contributions
uble-0.043
outer-0.043
oro-0.041
oster-0.039
TEXTURE-0.038
Token.
Token ID13
Feature activation+9.56e-01

Pos logit contributions
uble+5.012
outer+4.814
oro+4.739
oster+4.467
olphins+4.317
Neg logit contributions
 leaflets-5.127
senal-4.895
 pse-4.818
 Masquerade-4.768
cffff-4.655
Token Sel
Token ID15300
Feature activation+1.80e-01

Pos logit contributions
uble+3.840
outer+3.774
oro+3.676
oster+3.514
olphins+3.424
Neg logit contributions
 leaflets-2.987
senal-2.893
 pse-2.784
 Masquerade-2.723
cffff-2.694
Tokenz
Token ID89
Feature activation+9.10e-01

Pos logit contributions
uble+0.585
outer+0.579
oro+0.555
oster+0.527
olphins+0.513
Neg logit contributions
 leaflets-0.718
senal-0.687
 Masquerade-0.679
 pse-0.671
 Rollins-0.659
Tokennick
Token ID17172
Feature activation+9.84e-02

Pos logit contributions
uble+2.347
outer+2.291
oro+2.232
oster+2.077
obe+1.974
Neg logit contributions
 leaflets-4.200
senal-3.999
 Masquerade-3.989
 pse-3.914
cffff-3.845
Token was
Token ID373
Feature activation-7.64e-02

Pos logit contributions
uble+0.345
outer+0.339
oro+0.329
oster+0.311
olphins+0.304
Neg logit contributions
 leaflets-0.366
senal-0.351
 Masquerade-0.345
 pse-0.339
 Rollins-0.332
Token his
Token ID465
Feature activation-3.66e-02

Pos logit contributions
 leaflets+1.888
 Masquerade+1.747
senal+1.721
 Rollins+1.702
 pse+1.698
Neg logit contributions
uble-2.581
outer-2.560
oro-2.459
oster-2.341
TEXTURE-2.341
Token current
Token ID1459
Feature activation+7.00e-01

Pos logit contributions
 leaflets+0.119
senal+0.113
 Masquerade+0.111
 pse+0.109
 Rollins+0.107
Neg logit contributions
uble-0.145
outer-0.143
oro-0.139
oster-0.133
olphins-0.131
Token three
Token ID1115
Feature activation+3.92e-01

Pos logit contributions
uble+2.516
outer+2.501
oro+2.468
oster+2.344
olphins+2.322
Neg logit contributions
 leaflets-2.438
senal-2.409
 Masquerade-2.286
 pse-2.258
cffff-2.189
Token-
Token ID12
Feature activation+6.25e-02

Pos logit contributions
uble+1.314
outer+1.302
oro+1.253
oster+1.203
olphins+1.178
Neg logit contributions
 leaflets-1.494
senal-1.443
 Masquerade-1.420
 pse-1.395
 Rollins-1.370
Tokenyear
Token ID1941
Feature activation+4.99e-01

Pos logit contributions
uble+0.203
outer+0.201
oro+0.193
oster+0.183
olphins+0.179
Neg logit contributions
 leaflets-0.248
senal-0.236
 Masquerade-0.234
 pse-0.231
 Rollins-0.227
Token contract
Token ID2775
Feature activation+1.42e+00

Pos logit contributions
uble+1.789
outer+1.751
oro+1.713
oster+1.628
olphins+1.604
Neg logit contributions
 leaflets-1.805
senal-1.744
 Masquerade-1.699
 pse-1.679
 Rollins-1.625
Token.
Token ID13
Feature activation+3.37e-03

Pos logit contributions
uble+4.320
outer+4.244
oro+4.029
oster+3.874
olphins+3.783
Neg logit contributions
 leaflets-5.763
senal-5.680
 Masquerade-5.467
 pse-5.284
 Rollins-5.254
Token Last
Token ID4586
Feature activation-3.25e-01

Pos logit contributions
uble+0.012
outer+0.012
oro+0.011
oster+0.011
olphins+0.010
Neg logit contributions
 leaflets-0.013
senal-0.012
 Masquerade-0.012
 pse-0.012
 Rollins-0.011
Token year
Token ID614
Feature activation-1.13e-01

Pos logit contributions
 leaflets+1.074
senal+1.011
 Masquerade+1.005
 pse+0.985
 Rollins+0.969
Neg logit contributions
uble-1.269
outer-1.256
oro-1.213
oster-1.161
olphins-1.140
Token,
Token ID11
Feature activation+2.05e-01

Pos logit contributions
 leaflets+0.408
senal+0.388
 Masquerade+0.383
 pse+0.377
 Rollins+0.371
Neg logit contributions
uble-0.406
outer-0.400
oro-0.388
oster-0.370
olphins-0.363
Token he
Token ID339
Feature activation+8.77e-02

Pos logit contributions
uble+0.821
outer+0.810
oro+0.795
oster+0.762
olphins+0.755
Neg logit contributions
 leaflets-0.648
senal-0.620
 Masquerade-0.601
 pse-0.596
 Rollins-0.578
TokenBR
Token ID11473
Feature activation-2.17e-01

Pos logit contributions
 leaflets+0.043
senal+0.041
 Masquerade+0.040
 pse+0.040
 Rollins+0.039
Neg logit contributions
uble-0.035
outer-0.035
oro-0.033
oster-0.032
TEXTURE-0.031
TokenUSS
Token ID32835
Feature activation-2.12e-01

Pos logit contributions
 leaflets+0.812
senal+0.769
 Masquerade+0.766
 pse+0.751
 Rollins+0.742
Neg logit contributions
uble-0.755
outer-0.746
oro-0.717
oster-0.683
olphins-0.670
TokenELS
Token ID37142
Feature activation-4.53e-03

Pos logit contributions
 leaflets+0.331
senal+0.297
 Masquerade+0.284
 pse+0.277
 Rollins+0.258
Neg logit contributions
uble-1.202
outer-1.192
oro-1.167
oster-1.133
TEXTURE-1.121
Token (
Token ID357
Feature activation-6.06e-01

Pos logit contributions
 leaflets+0.016
senal+0.015
 Masquerade+0.015
 pse+0.015
 Rollins+0.015
Neg logit contributions
uble-0.017
outer-0.016
oro-0.016
oster-0.015
olphins-0.015
TokenReuters
Token ID12637
Feature activation-5.35e-01

Pos logit contributions
 leaflets+1.670
 Masquerade+1.549
senal+1.516
 pse+1.489
 Rollins+1.474
Neg logit contributions
uble-2.680
outer-2.620
oro-2.563
oster-2.453
olphins-2.440
Token)
Token ID8
Feature activation-2.06e+00

Pos logit contributions
 leaflets+1.777
 Masquerade+1.674
 Dent+1.632
 Rollins+1.629
 Typh+1.574
Neg logit contributions
uble-2.071
outer-2.055
oro-1.963
oster-1.873
olphins-1.862
Token -
Token ID532
Feature activation-1.32e+00

Pos logit contributions
 Masquerade+4.032
 leaflets+3.971
 Dent+3.959
 Rollins+3.876
 Typh+3.795
Neg logit contributions
uble-9.944
outer-9.875
oro-9.405
ibaba-9.336
obe-9.183
Token The
Token ID383
Feature activation-2.42e-01

Pos logit contributions
 leaflets+4.091
 Masquerade+3.898
 Dent+3.798
 Rollins+3.761
 Typh+3.752
Neg logit contributions
uble-5.277
outer-5.237
oro-5.055
oster-4.839
TEXTURE-4.791
Token world
Token ID995
Feature activation+1.54e-01

Pos logit contributions
 leaflets+0.906
senal+0.873
 Masquerade+0.858
 pse+0.845
 Rollins+0.830
Neg logit contributions
uble-0.836
outer-0.824
oro-0.794
oster-0.751
olphins-0.737
Token
Token ID447
Feature activation+1.45e-01

Pos logit contributions
uble+0.492
outer+0.483
oro+0.465
oster+0.441
TEXTURE+0.429
Neg logit contributions
 leaflets-0.615
senal-0.593
 Masquerade-0.585
 pse-0.575
 Rollins-0.567
Token
Token ID247
Feature activation+2.82e-01

Pos logit contributions
uble+0.387
outer+0.378
oro+0.362
oster+0.336
TEXTURE+0.326
Neg logit contributions
 leaflets-0.661
senal-0.639
 Masquerade-0.631
 pse-0.621
 Rollins-0.616
TokenHA
Token ID7801
Feature activation+4.26e-02

Pos logit contributions
uble+0.048
outer+0.048
oro+0.046
oster+0.043
TEXTURE+0.042
Neg logit contributions
 leaflets-0.059
senal-0.056
 Masquerade-0.056
 pse-0.055
 Rollins-0.054
TokenV
Token ID53
Feature activation+2.16e-02

Pos logit contributions
uble+0.135
outer+0.133
oro+0.127
oster+0.121
TEXTURE+0.118
Neg logit contributions
 leaflets-0.173
senal-0.166
 Masquerade-0.163
 pse-0.162
 Rollins-0.159
TokenANA
Token ID31574
Feature activation+6.42e-02

Pos logit contributions
uble+0.076
outer+0.076
oro+0.073
oster+0.069
olphins+0.068
Neg logit contributions
 leaflets-0.079
senal-0.075
 Masquerade-0.075
 pse-0.073
 Rollins-0.072
Token (
Token ID357
Feature activation-6.78e-01

Pos logit contributions
uble+0.228
outer+0.225
oro+0.218
oster+0.206
TEXTURE+0.203
Neg logit contributions
 leaflets-0.235
senal-0.224
 Masquerade-0.221
 pse-0.218
 Rollins-0.213
TokenReuters
Token ID12637
Feature activation-5.20e-01

Pos logit contributions
 leaflets+1.955
 Masquerade+1.815
senal+1.802
 pse+1.744
 Rollins+1.738
Neg logit contributions
uble-2.927
outer-2.870
oro-2.789
oster-2.678
olphins-2.646
Token)
Token ID8
Feature activation-2.02e+00

Pos logit contributions
 leaflets+1.735
 Masquerade+1.636
 Dent+1.592
 Rollins+1.589
 pse+1.539
Neg logit contributions
uble-2.011
outer-1.994
oro-1.907
oster-1.820
olphins-1.804
Token -
Token ID532
Feature activation-1.25e+00

Pos logit contributions
 Masquerade+3.992
 Dent+3.920
 leaflets+3.915
 Rollins+3.832
 Typh+3.748
Neg logit contributions
uble-9.723
outer-9.646
oro-9.171
ibaba-9.086
obe-8.966
Token Latin
Token ID9133
Feature activation-3.16e-01

Pos logit contributions
 leaflets+3.825
 Masquerade+3.646
 Dent+3.515
 Rollins+3.505
senal+3.462
Neg logit contributions
uble-5.144
outer-5.107
oro-4.884
oster-4.692
TEXTURE-4.652
Token American
Token ID1605
Feature activation+2.21e-01

Pos logit contributions
 leaflets+1.080
senal+1.013
 Masquerade+1.007
 pse+0.987
 Rollins+0.977
Neg logit contributions
uble-1.204
outer-1.192
oro-1.148
oster-1.096
olphins-1.079
Token and
Token ID290
Feature activation-1.42e-01

Pos logit contributions
uble+0.921
outer+0.910
oro+0.890
oster+0.851
olphins+0.835
Neg logit contributions
 leaflets-0.657
senal-0.635
 Masquerade-0.617
 pse-0.602
cffff-0.600
Token Caribbean
Token ID18020
Feature activation+5.43e-01

Pos logit contributions
 leaflets+0.636
 Masquerade+0.604
senal+0.604
 pse+0.595
 Rollins+0.589
Neg logit contributions
uble-0.386
outer-0.381
oro-0.362
oster-0.341
TEXTURE-0.332
TokenOT
Token ID2394
Feature activation+1.91e-01

Pos logit contributions
 leaflets+0.063
senal+0.060
 Masquerade+0.060
 pse+0.059
 Rollins+0.058
Neg logit contributions
uble-0.052
outer-0.051
oro-0.049
oster-0.047
TEXTURE-0.046
TokenTA
Token ID5603
Feature activation-3.09e-01

Pos logit contributions
uble+0.510
outer+0.506
oro+0.491
oster+0.458
TEXTURE+0.439
Neg logit contributions
 leaflets-0.862
senal-0.831
 Masquerade-0.822
 pse-0.807
 Rollins-0.791
TokenWA
Token ID15543
Feature activation-4.18e-01

Pos logit contributions
 leaflets+1.074
senal+1.044
 pse+1.020
 Masquerade+0.991
cffff+0.987
Neg logit contributions
uble-1.143
outer-1.131
oro-1.105
oster-1.056
TEXTURE-1.044
Token (
Token ID357
Feature activation-7.21e-01

Pos logit contributions
 leaflets+1.529
senal+1.443
 Masquerade+1.442
 pse+1.412
 Rollins+1.394
Neg logit contributions
uble-1.483
outer-1.467
oro-1.413
oster-1.343
olphins-1.319
TokenReuters
Token ID12637
Feature activation-3.90e-01

Pos logit contributions
 leaflets+2.091
 Masquerade+1.956
senal+1.914
 Dent+1.884
 Rollins+1.876
Neg logit contributions
uble-3.089
outer-3.029
oro-2.948
oster-2.816
olphins-2.808
Token)
Token ID8
Feature activation-1.95e+00

Pos logit contributions
 leaflets+1.312
 Masquerade+1.235
 Dent+1.202
 Rollins+1.202
 pse+1.168
Neg logit contributions
uble-1.499
outer-1.487
oro-1.422
oster-1.357
olphins-1.343
Token -
Token ID532
Feature activation-1.34e+00

Pos logit contributions
 Masquerade+3.860
 Dent+3.813
 leaflets+3.812
 Rollins+3.707
 Typh+3.638
Neg logit contributions
uble-9.407
outer-9.349
oro-8.893
ibaba-8.771
obe-8.671
Token Canada
Token ID3340
Feature activation-7.83e-01

Pos logit contributions
 leaflets+3.883
 Masquerade+3.735
 Dent+3.667
 Rollins+3.584
 Typh+3.522
Neg logit contributions
uble-5.660
outer-5.612
oro-5.382
oster-5.183
olphins-5.115
Token
Token ID447
Feature activation+5.61e-03

Pos logit contributions
 leaflets+3.015
senal+2.834
 Masquerade+2.831
 pse+2.792
 Dent+2.764
Neg logit contributions
uble-2.621
outer-2.604
oro-2.495
oster-2.373
olphins-2.326
Token
Token ID247
Feature activation+2.58e-01

Pos logit contributions
uble+0.016
outer+0.015
oro+0.015
oster+0.014
olphins+0.013
Neg logit contributions
 leaflets-0.025
senal-0.024
 Masquerade-0.024
 pse-0.023
 Rollins-0.023
Tokens
Token ID82
Feature activation+3.58e-02

Pos logit contributions
uble+0.894
outer+0.884
oro+0.852
oster+0.807
olphins+0.790
Neg logit contributions
 leaflets-0.969
senal-0.926
 Masquerade-0.919
 pse-0.898
 Rollins-0.890
TokenITED
Token ID22061
Feature activation-1.61e-01

Pos logit contributions
uble+1.962
outer+1.922
oro+1.872
oster+1.759
TEXTURE+1.737
Neg logit contributions
 leaflets-2.646
senal-2.571
 Masquerade-2.517
 pse-2.476
 Rollins-2.440
Token N
Token ID399
Feature activation+1.15e-01

Pos logit contributions
 leaflets+0.511
senal+0.478
 Masquerade+0.477
 pse+0.466
 Rollins+0.460
Neg logit contributions
uble-0.651
outer-0.645
oro-0.623
oster-0.597
olphins-0.588
TokenATIONS
Token ID18421
Feature activation-2.93e-01

Pos logit contributions
uble+0.460
outer+0.454
oro+0.440
oster+0.423
olphins+0.415
Neg logit contributions
 leaflets-0.367
senal-0.348
 Masquerade-0.342
 pse-0.338
 Rollins-0.331
Token (
Token ID357
Feature activation-7.06e-01

Pos logit contributions
 leaflets+1.012
senal+0.950
 Masquerade+0.949
 pse+0.929
 Rollins+0.915
Neg logit contributions
uble-1.101
outer-1.089
oro-1.050
oster-1.004
olphins-0.985
TokenReuters
Token ID12637
Feature activation-4.98e-01

Pos logit contributions
 leaflets+2.005
 Masquerade+1.867
senal+1.813
 Rollins+1.795
 Dent+1.784
Neg logit contributions
uble-3.068
outer-3.004
oro-2.917
oster-2.794
olphins-2.773
Token)
Token ID8
Feature activation-1.89e+00

Pos logit contributions
 leaflets+1.668
 Masquerade+1.566
 Dent+1.526
 Rollins+1.526
 pse+1.488
Neg logit contributions
uble-1.918
outer-1.903
oro-1.820
oster-1.733
olphins-1.723
Token -
Token ID532
Feature activation-1.30e+00

Pos logit contributions
 Masquerade+3.836
 leaflets+3.752
 Dent+3.741
 Rollins+3.640
 Typh+3.552
Neg logit contributions
uble-9.143
outer-9.059
oro-8.649
ibaba-8.620
obe-8.465
Token An
Token ID1052
Feature activation-6.66e-01

Pos logit contributions
 leaflets+4.020
 Masquerade+3.832
 Dent+3.735
 Rollins+3.718
 Typh+3.649
Neg logit contributions
uble-5.282
outer-5.226
oro-5.012
oster-4.813
TEXTURE-4.745
Token army
Token ID5428
Feature activation+1.78e-01

Pos logit contributions
 leaflets+2.167
 Masquerade+1.995
senal+1.990
 pse+1.961
 Rollins+1.929
Neg logit contributions
uble-2.634
outer-2.600
oro-2.502
oster-2.419
TEXTURE-2.385
Token battalion
Token ID36328
Feature activation-3.19e-01

Pos logit contributions
uble+0.700
outer+0.695
oro+0.673
oster+0.647
olphins+0.630
Neg logit contributions
 leaflets-0.574
senal-0.554
 Masquerade-0.545
 pse-0.530
cffff-0.521
Token in
Token ID287
Feature activation-4.39e-02

Pos logit contributions
 leaflets+1.016
senal+0.947
 Masquerade+0.944
 pse+0.925
 Rollins+0.910
Neg logit contributions
uble-1.287
outer-1.274
oro-1.231
oster-1.180
olphins-1.162
TokenONG
Token ID18494
Feature activation-6.79e-01

Pos logit contributions
 leaflets+0.969
senal+0.905
 Masquerade+0.898
 pse+0.882
 Rollins+0.867
Neg logit contributions
uble-1.240
outer-1.220
oro-1.182
oster-1.132
olphins-1.114
Token K
Token ID509
Feature activation+1.06e-01

Pos logit contributions
 leaflets+2.197
 Rollins+2.054
 Dent+2.035
 Masquerade+2.024
senal+1.996
Neg logit contributions
uble-2.715
outer-2.589
oro-2.459
oster-2.431
olphins-2.403
TokenONG
Token ID18494
Feature activation-9.15e-01

Pos logit contributions
uble+0.473
outer+0.469
oro+0.456
oster+0.439
olphins+0.431
Neg logit contributions
 leaflets-0.289
senal-0.273
 Masquerade-0.267
 pse-0.263
 Rollins-0.255
Token (
Token ID357
Feature activation-3.79e-01

Pos logit contributions
 leaflets+3.115
 Masquerade+2.927
senal+2.855
 Dent+2.849
 Rollins+2.819
Neg logit contributions
uble-3.462
outer-3.439
oro-3.238
oster-3.129
olphins-3.054
TokenReuters
Token ID12637
Feature activation-3.47e-01

Pos logit contributions
 leaflets+1.080
 Masquerade+0.995
senal+0.989
 pse+0.963
 Rollins+0.953
Neg logit contributions
uble-1.657
outer-1.631
oro-1.586
oster-1.521
olphins-1.504
Token)
Token ID8
Feature activation-1.83e+00

Pos logit contributions
 leaflets+1.169
 Masquerade+1.104
 Dent+1.072
 Rollins+1.070
senal+1.040
Neg logit contributions
uble-1.338
outer-1.321
oro-1.270
oster-1.207
olphins-1.194
Token -
Token ID532
Feature activation-1.22e+00

Pos logit contributions
 Masquerade+3.774
 Dent+3.697
 leaflets+3.621
 Rollins+3.545
 Typh+3.469
Neg logit contributions
uble-8.963
outer-8.859
ibaba-8.458
oro-8.391
obe-8.186
Token One
Token ID1881
Feature activation+1.10e-01

Pos logit contributions
 leaflets+3.929
 Masquerade+3.717
 Dent+3.636
 Rollins+3.578
senal+3.554
Neg logit contributions
uble-4.868
outer-4.795
oro-4.582
oster-4.404
TEXTURE-4.378
Token needs
Token ID2476
Feature activation+3.44e-01

Pos logit contributions
uble+0.426
outer+0.420
oro+0.410
oster+0.391
olphins+0.384
Neg logit contributions
 leaflets-0.360
senal-0.348
 Masquerade-0.340
 pse-0.332
 Rollins-0.327
Token to
Token ID284
Feature activation-3.86e-01

Pos logit contributions
uble+1.214
outer+1.184
oro+1.156
oster+1.104
olphins+1.078
Neg logit contributions
 leaflets-1.252
senal-1.212
 Masquerade-1.197
 pse-1.164
 Rollins-1.154
Token look
Token ID804
Feature activation+2.57e-02

Pos logit contributions
 leaflets+1.300
 Masquerade+1.213
senal+1.208
 pse+1.197
 Rollins+1.172
Neg logit contributions
uble-1.476
outer-1.461
oro-1.411
oster-1.346
TEXTURE-1.328
Token a
Token ID257
Feature activation+1.47e-01

Pos logit contributions
uble+0.732
outer+0.725
oro+0.704
oster+0.671
olphins+0.657
Neg logit contributions
 leaflets-0.638
senal-0.608
 Masquerade-0.598
 pse-0.589
 Dent-0.574
Token fighter
Token ID10543
Feature activation-3.20e-01

Pos logit contributions
uble+0.635
outer+0.633
oro+0.613
oster+0.589
olphins+0.577
Neg logit contributions
 leaflets-0.424
senal-0.398
 Masquerade-0.389
 pse-0.377
 Rollins-0.373
Token.
Token ID13
Feature activation+2.33e-01

Pos logit contributions
 leaflets+1.241
 Masquerade+1.175
senal+1.175
 pse+1.154
 Rollins+1.141
Neg logit contributions
uble-1.061
outer-1.047
oro-1.006
oster-0.951
olphins-0.938
Token As
Token ID1081
Feature activation-2.05e-01

Pos logit contributions
uble+0.748
outer+0.740
oro+0.715
oster+0.678
olphins+0.658
Neg logit contributions
 leaflets-0.933
senal-0.901
 pse-0.877
 Masquerade-0.873
cffff-0.850
Token they
Token ID484
Feature activation+6.36e-02

Pos logit contributions
 leaflets+0.711
senal+0.673
 Masquerade+0.668
 pse+0.655
 Rollins+0.644
Neg logit contributions
uble-0.768
outer-0.760
oro-0.734
oster-0.700
olphins-0.687
Token say
Token ID910
Feature activation-1.81e+00

Pos logit contributions
uble+0.239
outer+0.237
oro+0.229
oster+0.219
TEXTURE+0.213
Neg logit contributions
 leaflets-0.219
senal-0.209
 Masquerade-0.206
 pse-0.202
 Rollins-0.199
Token,
Token ID11
Feature activation-7.29e-01

Pos logit contributions
 leaflets+5.674
 Masquerade+5.276
 pse+5.137
senal+5.118
 Dent+5.078
Neg logit contributions
outer-6.878
uble-6.868
oro-6.554
TEXTURE-6.314
oster-6.307
Token nothing
Token ID2147
Feature activation+4.01e-01

Pos logit contributions
 leaflets+2.440
 Masquerade+2.275
senal+2.263
 pse+2.238
 Rollins+2.195
Neg logit contributions
uble-2.803
outer-2.776
oro-2.669
oster-2.552
olphins-2.529
Token is
Token ID318
Feature activation+4.34e-01

Pos logit contributions
uble+1.277
outer+1.261
oro+1.216
oster+1.152
TEXTURE+1.117
Neg logit contributions
 leaflets-1.604
senal-1.560
 Masquerade-1.514
 pse-1.497
 Rollins-1.475
Token more
Token ID517
Feature activation+4.01e-01

Pos logit contributions
uble+1.575
outer+1.564
oro+1.506
oster+1.442
olphins+1.392
Neg logit contributions
 leaflets-1.554
senal-1.491
 Masquerade-1.453
 pse-1.429
 Rollins-1.406
Token dangerous
Token ID4923
Feature activation+2.91e-01

Pos logit contributions
uble+1.321
outer+1.307
oro+1.263
oster+1.194
TEXTURE+1.168
Neg logit contributions
 leaflets-1.561
senal-1.506
 Masquerade-1.467
 pse-1.456
 Rollins-1.429
Tokenote
Token ID1258
Feature activation-3.27e-01

Pos logit contributions
outer+1.803
uble+1.789
oro+1.729
oster+1.615
obe+1.516
Neg logit contributions
 leaflets-3.213
senal-3.192
 Masquerade-3.117
 pse-3.065
 Rollins-3.007
Token (
Token ID357
Feature activation+1.20e-02

Pos logit contributions
 leaflets+1.074
senal+1.009
 Masquerade+1.008
 pse+0.984
 Rollins+0.977
Neg logit contributions
uble-1.270
outer-1.261
oro-1.215
oster-1.164
TEXTURE-1.151
TokenO
Token ID46
Feature activation-2.07e-01

Pos logit contributions
uble+0.039
outer+0.039
oro+0.037
oster+0.035
TEXTURE+0.034
Neg logit contributions
 leaflets-0.048
senal-0.045
 Masquerade-0.045
 pse-0.044
 Rollins-0.044
Tokenmega
Token ID13731
Feature activation-8.72e-01

Pos logit contributions
 leaflets+0.843
senal+0.805
 Masquerade+0.802
 pse+0.787
 Rollins+0.777
Neg logit contributions
uble-0.642
outer-0.632
oro-0.603
oster-0.572
olphins-0.565
Token Pharma
Token ID41845
Feature activation-1.31e+00

Pos logit contributions
 leaflets+3.215
 Masquerade+3.005
 Dent+2.988
 Rollins+2.974
 pse+2.918
Neg logit contributions
uble-3.051
outer-3.041
oro-2.861
oster-2.755
TEXTURE-2.700
Token -
Token ID532
Feature activation-1.73e+00

Pos logit contributions
 leaflets+3.572
 Masquerade+3.376
 Dent+3.331
 Rollins+3.198
 Typh+3.163
Neg logit contributions
uble-5.785
outer-5.764
oro-5.396
olphins-5.272
oster-5.227
Token Quick
Token ID12029
Feature activation-7.28e-01

Pos logit contributions
 Masquerade+3.216
 leaflets+3.167
 Dent+3.036
 Rollins+2.977
 Typh+2.816
Neg logit contributions
uble-8.795
outer-8.746
oro-8.496
olphins-8.368
oster-8.291
Tokenstep
Token ID9662
Feature activation-3.01e-01

Pos logit contributions
 leaflets+2.139
 Masquerade+1.970
 pse+1.936
 Rollins+1.927
als+1.898
Neg logit contributions
uble-3.044
outer-2.960
oro-2.910
olphins-2.809
oster-2.782
Token)
Token ID8
Feature activation-2.88e-01

Pos logit contributions
 leaflets+1.032
 Masquerade+0.968
 Rollins+0.942
 Dent+0.938
senal+0.924
Neg logit contributions
uble-1.130
outer-1.119
oro-1.076
oster-1.029
olphins-1.017
Token s
Token ID264
Feature activation-2.72e-01

Pos logit contributions
 leaflets+0.972
senal+0.917
 Masquerade+0.911
 pse+0.896
 Rollins+0.882
Neg logit contributions
uble-1.106
outer-1.096
oro-1.056
oster-1.011
olphins-0.994
Token.
Token ID13
Feature activation-1.88e-01

Pos logit contributions
 leaflets+1.105
 Masquerade+1.044
 Rollins+1.030
 Dent+1.024
als+1.020
Neg logit contributions
uble-0.843
outer-0.829
oro-0.789
oster-0.748
olphins-0.745
Token country
Token ID1499
Feature activation-1.98e-01

Pos logit contributions
outer+2.644
uble+2.629
oro+2.547
oster+2.413
obe+2.347
Neg logit contributions
 leaflets-2.560
senal-2.524
 Masquerade-2.413
 pse-2.349
 Rollins-2.323
Token.
Token ID13
Feature activation+1.41e-01

Pos logit contributions
 leaflets+0.827
senal+0.789
 Masquerade+0.785
 pse+0.773
 Rollins+0.763
Neg logit contributions
uble-0.598
outer-0.590
oro-0.564
oster-0.533
olphins-0.520
Token
Token ID198
Feature activation+1.12e-01

Pos logit contributions
uble+0.430
outer+0.426
oro+0.410
oster+0.386
olphins+0.378
Neg logit contributions
 leaflets-0.582
senal-0.559
 Masquerade-0.548
 pse-0.546
 Rollins-0.533
Token
Token ID198
Feature activation+8.03e-02

Pos logit contributions
uble+0.347
outer+0.343
oro+0.328
oster+0.310
olphins+0.303
Neg logit contributions
 leaflets-0.458
senal-0.439
 Masquerade-0.434
 pse-0.428
 Rollins-0.421
TokenRead
Token ID5569
Feature activation-4.04e-01

Pos logit contributions
uble+0.264
outer+0.262
oro+0.252
oster+0.238
TEXTURE+0.233
Neg logit contributions
 leaflets-0.316
senal-0.304
 Masquerade-0.298
 pse-0.295
 Rollins-0.289
Token full
Token ID1336
Feature activation-1.66e+00

Pos logit contributions
 leaflets+1.336
senal+1.244
 Masquerade+1.237
 pse+1.215
 Rollins+1.205
Neg logit contributions
uble-1.578
outer-1.556
oro-1.506
oster-1.446
TEXTURE-1.437
Token story
Token ID1621
Feature activation-8.71e-01

Pos logit contributions
 leaflets+2.206
 Story+1.663
 Dent+1.655
 Rollins+1.647
 Masquerade+1.612
Neg logit contributions
uble-9.524
outer-9.470
oro-9.099
oster-9.040
TEXTURE-9.008
Token<|endoftext|>
Token ID50256
Feature activation-3.82e-02

Pos logit contributions
 leaflets+3.699
 Masquerade+3.499
senal+3.466
 Dent+3.418
 pse+3.410
Neg logit contributions
uble-2.586
outer-2.567
oro-2.413
oster-2.267
TEXTURE-2.234
TokenAsia
Token ID38555
Feature activation-5.18e-02

Pos logit contributions
 leaflets+0.152
senal+0.145
 Masquerade+0.143
 pse+0.141
 Rollins+0.139
Neg logit contributions
uble-0.124
outer-0.123
oro-0.118
oster-0.112
TEXTURE-0.109
Token Health
Token ID3893
Feature activation-6.85e-01

Pos logit contributions
 leaflets+0.193
senal+0.184
 Masquerade+0.182
 pse+0.179
 Rollins+0.176
Neg logit contributions
uble-0.180
outer-0.178
oro-0.172
oster-0.163
olphins-0.160
Token Correspond
Token ID34428
Feature activation-3.94e-01

Pos logit contributions
 leaflets+2.374
 Masquerade+2.222
senal+2.214
 pse+2.176
 Rollins+2.157
Neg logit contributions
uble-2.573
outer-2.533
oro-2.436
oster-2.327
olphins-2.297
Token.
Token ID13
Feature activation-2.16e-01

Pos logit contributions
 leaflets+1.958
 Masquerade+1.846
senal+1.814
 pse+1.805
 Rollins+1.785
Neg logit contributions
uble-2.208
outer-2.178
oro-2.100
oster-2.004
olphins-1.985
Token (
Token ID357
Feature activation-3.16e-01

Pos logit contributions
 leaflets+0.742
senal+0.703
 Masquerade+0.693
 pse+0.684
 Rollins+0.668
Neg logit contributions
uble-0.818
outer-0.809
oro-0.782
oster-0.747
olphins-0.733
TokenPhoto
Token ID6191
Feature activation-3.13e-01

Pos logit contributions
 leaflets+1.074
senal+1.014
 Masquerade+1.005
 pse+0.988
 Rollins+0.970
Neg logit contributions
uble-1.207
outer-1.195
oro-1.154
oster-1.103
olphins-1.082
Token by
Token ID416
Feature activation-1.72e-01

Pos logit contributions
 leaflets+0.963
senal+0.904
 Masquerade+0.899
 pse+0.879
 Rollins+0.864
Neg logit contributions
uble-1.296
outer-1.284
oro-1.242
oster-1.189
olphins-1.172
Token REUTERS
Token ID15862
Feature activation-4.00e-01

Pos logit contributions
 leaflets+0.565
senal+0.533
 Masquerade+0.528
 pse+0.518
 Rollins+0.509
Neg logit contributions
uble-0.679
outer-0.672
oro-0.650
oster-0.622
olphins-0.611
Token/
Token ID14
Feature activation-1.65e+00

Pos logit contributions
 leaflets+1.806
 Masquerade+1.738
 Rollins+1.700
 Dent+1.696
 Typh+1.662
Neg logit contributions
uble-1.068
outer-1.050
oro-0.990
oster-0.922
olphins-0.909
TokenCar
Token ID9914
Feature activation-3.86e-01

Pos logit contributions
 leaflets+5.414
 Masquerade+5.316
 Rollins+5.169
 Dent+5.113
als+5.039
Neg logit contributions
uble-5.973
outer-5.776
oro-5.556
ibaba-5.526
olphins-5.338
Tokenlo
Token ID5439
Feature activation-3.04e-01

Pos logit contributions
 leaflets+1.510
senal+1.432
 Masquerade+1.431
 Rollins+1.398
 pse+1.393
Neg logit contributions
uble-1.271
outer-1.249
oro-1.204
oster-1.133
TEXTURE-1.121
Token Alleg
Token ID26326
Feature activation+2.44e-02

Pos logit contributions
 leaflets+0.859
senal+0.807
 Masquerade+0.792
 pse+0.780
 Rollins+0.754
Neg logit contributions
uble-1.334
outer-1.320
oro-1.288
oster-1.240
olphins-1.219
Tokenri
Token ID380
Feature activation-2.87e-03

Pos logit contributions
uble+0.086
outer+0.085
oro+0.080
TEXTURE+0.077
olphins+0.076
Neg logit contributions
 leaflets-0.090
 Masquerade-0.084
senal-0.083
 Rollins-0.082
 pse-0.082
Token)
Token ID8
Feature activation-8.28e-01

Pos logit contributions
 leaflets+0.011
senal+0.011
 Masquerade+0.011
 pse+0.011
 Rollins+0.010
Neg logit contributions
uble-0.009
outer-0.009
oro-0.009
oster-0.008
olphins-0.008
Tokenk
Token ID74
Feature activation+5.08e-02

Pos logit contributions
uble+0.707
outer+0.693
oro+0.674
oster+0.644
usa+0.610
Neg logit contributions
 leaflets-1.011
senal-0.978
 Masquerade-0.968
 pse-0.959
cffff-0.929
Token (
Token ID357
Feature activation+2.63e-01

Pos logit contributions
uble+0.192
outer+0.189
oro+0.184
oster+0.175
olphins+0.171
Neg logit contributions
 leaflets-0.176
senal-0.166
 Masquerade-0.165
 pse-0.162
 Rollins-0.159
TokenO
Token ID46
Feature activation-2.63e-02

Pos logit contributions
outer+0.820
uble+0.816
oro+0.786
oster+0.740
TEXTURE+0.733
Neg logit contributions
 leaflets-1.082
senal-1.049
 pse-1.026
 Masquerade-1.011
cffff-0.998
Tokenmega
Token ID13731
Feature activation-8.46e-01

Pos logit contributions
 leaflets+0.102
senal+0.097
 Masquerade+0.097
 pse+0.095
 Rollins+0.094
Neg logit contributions
uble-0.087
outer-0.086
oro-0.083
oster-0.079
olphins-0.077
Token Pharma
Token ID41845
Feature activation-1.24e+00

Pos logit contributions
 leaflets+3.134
 Masquerade+2.935
 Dent+2.902
 Rollins+2.898
senal+2.868
Neg logit contributions
uble-2.923
outer-2.917
oro-2.760
oster-2.641
TEXTURE-2.606
Token -
Token ID532
Feature activation-1.63e+00

Pos logit contributions
 leaflets+3.393
 Masquerade+3.169
 Dent+3.140
 Rollins+3.039
senal+3.036
Neg logit contributions
uble-5.440
outer-5.435
oro-5.093
olphins-4.972
TEXTURE-4.936
Token Quick
Token ID12029
Feature activation-6.13e-01

Pos logit contributions
 leaflets+3.213
 Masquerade+3.151
 Dent+3.004
 Rollins+2.967
 Typh+2.818
Neg logit contributions
uble-8.198
outer-8.120
oro-7.857
olphins-7.713
oster-7.623
Tokenstep
Token ID9662
Feature activation-2.98e-01

Pos logit contributions
 leaflets+1.876
 Masquerade+1.740
 pse+1.707
 Rollins+1.696
 Dent+1.675
Neg logit contributions
uble-2.512
outer-2.459
oro-2.401
olphins-2.299
oster-2.295
Token)
Token ID8
Feature activation-2.42e-01

Pos logit contributions
 leaflets+1.029
 Masquerade+0.965
 Rollins+0.938
 Dent+0.934
senal+0.931
Neg logit contributions
uble-1.111
outer-1.100
oro-1.058
oster-1.012
olphins-0.999
Token s
Token ID264
Feature activation-2.71e-01

Pos logit contributions
 leaflets+0.825
senal+0.779
 Masquerade+0.773
 pse+0.759
 Rollins+0.747
Neg logit contributions
uble-0.919
outer-0.910
oro-0.878
oster-0.839
olphins-0.824
Token.
Token ID13
Feature activation-1.63e-01

Pos logit contributions
 leaflets+1.102
 Masquerade+1.041
 Rollins+1.027
 Dent+1.022
als+1.017
Neg logit contributions
uble-0.838
outer-0.825
oro-0.785
oster-0.744
olphins-0.741
Token.
Token ID13
Feature activation-1.21e-01

Pos logit contributions
 leaflets+0.213
senal+0.204
 Masquerade+0.202
 pse+0.198
 Rollins+0.195
Neg logit contributions
uble-0.198
outer-0.196
oro-0.189
oster-0.180
olphins-0.175
Token (
Token ID357
Feature activation-3.18e-01

Pos logit contributions
 leaflets+0.415
senal+0.397
 Masquerade+0.386
 pse+0.385
cffff+0.373
Neg logit contributions
uble-0.462
outer-0.456
oro-0.442
oster-0.422
olphins-0.414
TokenPhoto
Token ID6191
Feature activation-3.25e-01

Pos logit contributions
 leaflets+1.033
senal+0.973
 Masquerade+0.964
 pse+0.946
 Rollins+0.929
Neg logit contributions
uble-1.260
outer-1.247
oro-1.206
oster-1.155
olphins-1.134
Token by
Token ID416
Feature activation-2.35e-01

Pos logit contributions
 leaflets+0.989
senal+0.927
 Masquerade+0.924
 pse+0.902
 Rollins+0.888
Neg logit contributions
uble-1.352
outer-1.341
oro-1.298
oster-1.241
olphins-1.225
Token REUTERS
Token ID15862
Feature activation-3.80e-01

Pos logit contributions
 leaflets+0.769
senal+0.724
 Masquerade+0.719
 pse+0.704
 Rollins+0.693
Neg logit contributions
uble-0.928
outer-0.919
oro-0.888
oster-0.850
olphins-0.836
Token/
Token ID14
Feature activation-1.62e+00

Pos logit contributions
 leaflets+1.713
 Masquerade+1.649
 Rollins+1.612
 Dent+1.610
 Typh+1.577
Neg logit contributions
uble-1.016
outer-1.000
oro-0.942
oster-0.880
olphins-0.867
TokenGary
Token ID33820
Feature activation-3.93e-01

Pos logit contributions
 leaflets+5.080
 Masquerade+4.967
 Rollins+4.820
 Dent+4.805
als+4.692
Neg logit contributions
uble-6.116
outer-5.962
oro-5.743
ibaba-5.675
olphins-5.515
Token Cameron
Token ID10821
Feature activation-8.36e-01

Pos logit contributions
 leaflets+1.541
 Masquerade+1.471
senal+1.446
 Rollins+1.446
 Dent+1.432
Neg logit contributions
uble-1.289
outer-1.272
oro-1.223
oster-1.149
olphins-1.128
Token/
Token ID14
Feature activation-4.11e-01

Pos logit contributions
 leaflets+3.105
 Masquerade+2.983
senal+2.924
 Dent+2.908
 Rollins+2.891
Neg logit contributions
uble-2.892
outer-2.859
oro-2.707
oster-2.569
TEXTURE-2.545
TokenFile
Token ID8979
Feature activation+1.89e-01

Pos logit contributions
 leaflets+1.458
 Masquerade+1.377
senal+1.376
 pse+1.340
 Rollins+1.333
Neg logit contributions
uble-1.502
outer-1.483
oro-1.428
oster-1.359
olphins-1.340
Token photo
Token ID4590
Feature activation+4.16e-01

Pos logit contributions
uble+0.840
outer+0.832
oro+0.814
oster+0.784
olphins+0.772
Neg logit contributions
 leaflets-0.513
senal-0.480
 Masquerade-0.469
 pse-0.467
 Rollins-0.449
Token Ryan
Token ID6047
Feature activation+1.74e-02

Pos logit contributions
uble+0.239
outer+0.236
oro+0.229
oster+0.219
olphins+0.214
Neg logit contributions
 leaflets-0.204
senal-0.194
 Masquerade-0.190
 pse-0.188
 Rollins-0.183
Token,
Token ID11
Feature activation+5.79e-02

Pos logit contributions
uble+0.065
outer+0.064
oro+0.062
oster+0.059
olphins+0.058
Neg logit contributions
 leaflets-0.061
senal-0.058
 Masquerade-0.057
 pse-0.056
 Rollins-0.055
Token who
Token ID508
Feature activation+1.55e-01

Pos logit contributions
uble+0.228
outer+0.226
oro+0.218
oster+0.209
olphins+0.205
Neg logit contributions
 leaflets-0.190
senal-0.180
 Masquerade-0.177
 pse-0.173
 Rollins-0.170
Token was
Token ID373
Feature activation+2.13e-01

Pos logit contributions
uble+0.511
outer+0.502
oro+0.485
oster+0.459
olphins+0.449
Neg logit contributions
 leaflets-0.602
senal-0.579
 Masquerade-0.571
 pse-0.561
 Rollins-0.552
Token em
Token ID795
Feature activation+7.60e-01

Pos logit contributions
uble+0.860
outer+0.847
oro+0.822
oster+0.787
TEXTURE+0.771
Neg logit contributions
 leaflets-0.675
senal-0.640
 Masquerade-0.627
 pse-0.616
 Rollins-0.597
Tokence
Token ID344
Feature activation-1.61e+00

Pos logit contributions
uble+2.513
outer+2.503
oro+2.371
oster+2.237
obe+2.210
Neg logit contributions
 leaflets-2.951
senal-2.796
 pse-2.785
 Masquerade-2.763
 Rollins-2.675
Tokene
Token ID68
Feature activation+1.26e-01

Pos logit contributions
 leaflets+5.275
 Masquerade+5.072
 Rollins+4.892
 Dent+4.814
als+4.804
Neg logit contributions
uble-5.847
outer-5.668
oro-5.539
olphins-5.465
TEXTURE-5.409
Tokening
Token ID278
Feature activation-3.58e-01

Pos logit contributions
uble+0.458
outer+0.450
oro+0.436
oster+0.416
olphins+0.404
Neg logit contributions
 leaflets-0.450
senal-0.430
 Masquerade-0.422
 pse-0.415
 Rollins-0.407
Token the
Token ID262
Feature activation+2.86e-03

Pos logit contributions
 leaflets+1.192
senal+1.119
 Masquerade+1.116
 pse+1.092
 Rollins+1.079
Neg logit contributions
uble-1.390
outer-1.378
oro-1.330
oster-1.273
olphins-1.250
Token program
Token ID1430
Feature activation-4.38e-02

Pos logit contributions
uble+0.011
outer+0.011
oro+0.011
oster+0.010
olphins+0.010
Neg logit contributions
 leaflets-0.009
senal-0.009
 Masquerade-0.009
 pse-0.009
cffff-0.008
Token,
Token ID11
Feature activation-5.11e-04

Pos logit contributions
 leaflets+0.155
senal+0.148
 Masquerade+0.145
 pse+0.143
 Rollins+0.140
Neg logit contributions
uble-0.161
outer-0.159
oro-0.154
oster-0.147
olphins-0.144
Token"
Token ID1
Feature activation-1.86e-01

Pos logit contributions
uble+0.422
outer+0.419
oro+0.403
oster+0.381
TEXTURE+0.375
Neg logit contributions
 leaflets-0.494
senal-0.476
 Masquerade-0.465
 pse-0.461
 Rollins-0.450
TokenAs
Token ID1722
Feature activation-3.80e-01

Pos logit contributions
 leaflets+0.746
senal+0.708
 Masquerade+0.708
 pse+0.694
 Rollins+0.687
Neg logit contributions
uble-0.592
outer-0.584
oro-0.560
oster-0.530
olphins-0.519
Token you
Token ID345
Feature activation-1.11e-01

Pos logit contributions
 leaflets+1.247
senal+1.167
 Masquerade+1.164
 pse+1.141
 Rollins+1.123
Neg logit contributions
uble-1.495
outer-1.482
oro-1.427
oster-1.368
olphins-1.347
Token may
Token ID743
Feature activation-1.03e+00

Pos logit contributions
 leaflets+0.405
senal+0.387
 Masquerade+0.382
 pse+0.374
 Rollins+0.369
Neg logit contributions
uble-0.397
outer-0.393
oro-0.379
oster-0.361
olphins-0.354
Token have
Token ID423
Feature activation-7.41e-01

Pos logit contributions
 leaflets+3.423
 Masquerade+3.112
 pse+3.101
 Rollins+3.025
 Dent+3.007
Neg logit contributions
uble-3.977
outer-3.935
oro-3.778
TEXTURE-3.647
oster-3.580
Token heard
Token ID2982
Feature activation-1.57e+00

Pos logit contributions
 leaflets+2.623
 Masquerade+2.421
 pse+2.416
 Rollins+2.378
 Dent+2.344
Neg logit contributions
uble-2.731
outer-2.706
oro-2.583
TEXTURE-2.469
oster-2.455
Token,
Token ID11
Feature activation-3.85e-01

Pos logit contributions
 leaflets+4.841
 Masquerade+4.432
 Rollins+4.329
 pse+4.324
 Dent+4.301
Neg logit contributions
outer-6.322
uble-6.252
oro-5.972
olphins-5.743
oster-5.697
Token Winter
Token ID10633
Feature activation+1.14e-01

Pos logit contributions
 leaflets+1.255
 Masquerade+1.171
senal+1.170
 pse+1.145
 Rollins+1.128
Neg logit contributions
uble-1.527
outer-1.513
oro-1.461
oster-1.400
olphins-1.379
Tokenke
Token ID365
Feature activation+2.41e-01

Pos logit contributions
uble+0.443
outer+0.438
oro+0.422
oster+0.405
olphins+0.396
Neg logit contributions
 leaflets-0.382
senal-0.365
 Masquerade-0.357
 pse-0.353
 Rollins-0.346
Tokenwl
Token ID40989
Feature activation+2.20e-02

Pos logit contributions
uble+0.703
outer+0.694
oro+0.662
oster+0.624
olphins+0.609
Neg logit contributions
 leaflets-1.031
senal-0.993
 Masquerade-0.982
 pse-0.969
 Rollins-0.955
Token Games
Token ID5776
Feature activation+1.22e-01

Pos logit contributions
uble+0.073
outer+0.072
oro+0.069
oster+0.065
olphins+0.064
Neg logit contributions
 leaflets-0.086
senal-0.082
 Masquerade-0.082
 pse-0.080
 Rollins-0.079
Token could
Token ID714
Feature activation-1.53e-01

Pos logit contributions
 leaflets+0.211
senal+0.205
 Masquerade+0.201
 pse+0.196
 Rollins+0.195
Neg logit contributions
uble-0.176
outer-0.172
oro-0.166
oster-0.159
olphins-0.154
Token name
Token ID1438
Feature activation+1.02e-01

Pos logit contributions
 leaflets+0.560
senal+0.536
 Masquerade+0.529
 pse+0.518
 Rollins+0.511
Neg logit contributions
uble-0.545
outer-0.538
oro-0.518
oster-0.495
olphins-0.484
Token.
Token ID13
Feature activation+5.09e-02

Pos logit contributions
uble+0.372
outer+0.364
oro+0.353
oster+0.339
olphins+0.328
Neg logit contributions
 leaflets-0.362
senal-0.350
 Masquerade-0.342
 pse-0.335
 Rollins-0.327
Token The
Token ID383
Feature activation-1.17e-01

Pos logit contributions
uble+0.186
outer+0.184
oro+0.179
oster+0.171
=~+0.166
Neg logit contributions
 leaflets-0.181
senal-0.175
 pse-0.169
 Masquerade-0.167
cffff-0.165
Token g
Token ID308
Feature activation-4.92e-01

Pos logit contributions
 leaflets+0.385
senal+0.370
 Masquerade+0.361
 pse+0.352
 Rollins+0.346
Neg logit contributions
uble-0.457
outer-0.452
oro-0.436
oster-0.418
TEXTURE-0.409
Tokenreg
Token ID2301
Feature activation-1.56e+00

Pos logit contributions
 leaflets+1.710
senal+1.608
 Masquerade+1.601
 pse+1.569
 Rollins+1.550
Neg logit contributions
uble-1.835
outer-1.815
oro-1.751
oster-1.672
TEXTURE-1.644
Tokenarious
Token ID27129
Feature activation-2.68e-01

Pos logit contributions
 leaflets+3.675
 Masquerade+3.439
als+3.334
 Dent+3.205
 Rollins+3.179
Neg logit contributions
outer-7.231
uble-7.190
oro-6.828
olphins-6.819
TEXTURE-6.735
Token Massachusetts
Token ID10140
Feature activation-4.24e-02

Pos logit contributions
 leaflets+0.896
senal+0.855
 Masquerade+0.840
 pse+0.821
 Rollins+0.807
Neg logit contributions
uble-1.033
outer-1.022
oro-0.986
oster-0.944
olphins-0.924
Token pol
Token ID755
Feature activation+3.27e-01

Pos logit contributions
 leaflets+0.134
senal+0.128
 Masquerade+0.126
 pse+0.123
 Rollins+0.121
Neg logit contributions
uble-0.171
outer-0.169
oro-0.164
oster-0.157
olphins-0.154
Token,
Token ID11
Feature activation-2.70e-02

Pos logit contributions
uble+1.182
outer+1.167
oro+1.127
oster+1.078
olphins+1.041
Neg logit contributions
 leaflets-1.189
senal-1.144
 Masquerade-1.118
 pse-1.089
 Rollins-1.067
Token House
Token ID2097
Feature activation+5.17e-01

Pos logit contributions
 leaflets+0.086
senal+0.082
 Masquerade+0.081
 pse+0.079
 Rollins+0.077
Neg logit contributions
uble-0.109
outer-0.107
oro-0.104
oster-0.099
olphins-0.097
Token request
Token ID2581
Feature activation+4.79e-01

Pos logit contributions
uble+0.592
outer+0.584
oro+0.561
oster+0.535
olphins+0.517
Neg logit contributions
 leaflets-0.714
senal-0.698
 Masquerade-0.677
 pse-0.668
 Rollins-0.659
Token stamp
Token ID17977
Feature activation+2.57e-01

Pos logit contributions
uble+1.748
outer+1.727
oro+1.683
oster+1.601
TEXTURE+1.551
Neg logit contributions
 leaflets-1.660
senal-1.637
 Masquerade-1.572
 pse-1.545
cffff-1.531
Token.
Token ID13
Feature activation-1.91e-01

Pos logit contributions
outer+0.964
uble+0.963
oro+0.936
oster+0.899
obe+0.870
Neg logit contributions
 leaflets-0.865
senal-0.836
 Masquerade-0.824
 pse-0.799
cffff-0.796
Token<|endoftext|>
Token ID50256
Feature activation-1.46e-01

Pos logit contributions
 leaflets+0.728
senal+0.692
 Masquerade+0.687
 pse+0.676
 Rollins+0.665
Neg logit contributions
uble-0.653
outer-0.646
oro-0.621
oster-0.590
olphins-0.578
TokenED
Token ID1961
Feature activation-6.58e-02

Pos logit contributions
 leaflets+0.580
senal+0.552
 Masquerade+0.549
 pse+0.540
 Rollins+0.532
Neg logit contributions
uble-0.476
outer-0.470
oro-0.451
oster-0.428
olphins-0.418
TokenMON
Token ID27857
Feature activation-1.55e+00

Pos logit contributions
 leaflets+0.235
senal+0.222
 Masquerade+0.221
 pse+0.217
 Dent+0.212
Neg logit contributions
uble-0.241
outer-0.238
oro-0.230
oster-0.218
TEXTURE-0.215
TokenTON
Token ID11357
Feature activation-7.01e-01

Pos logit contributions
 leaflets+4.771
 Dent+4.624
 Masquerade+4.563
 Rollins+4.436
 pse+4.387
Neg logit contributions
uble-6.175
outer-5.756
oro-5.746
olphins-5.549
ibaba-5.502
Token
Token ID784
Feature activation-1.35e+00

Pos logit contributions
 leaflets+2.603
 Masquerade+2.461
senal+2.433
 pse+2.387
 Dent+2.382
Neg logit contributions
uble-2.452
outer-2.425
oro-2.315
oster-2.205
olphins-2.163
Token Omar
Token ID24980
Feature activation-4.25e-01

Pos logit contributions
 leaflets+4.222
 Masquerade+4.053
 Dent+3.982
 Rollins+3.947
 Typh+3.824
Neg logit contributions
uble-5.380
outer-5.327
oro-5.101
oster-4.866
TEXTURE-4.822
Token Kh
Token ID5311
Feature activation-3.07e-01

Pos logit contributions
 leaflets+1.241
 Masquerade+1.154
senal+1.149
 Rollins+1.113
 Dent+1.110
Neg logit contributions
uble-1.815
outer-1.804
oro-1.733
oster-1.672
olphins-1.654
Tokenadr
Token ID41909
Feature activation+4.89e-01

Pos logit contributions
 leaflets+1.429
 Masquerade+1.362
senal+1.352
 pse+1.334
 Rollins+1.318
Neg logit contributions
uble-0.768
outer-0.763
oro-0.716
oster-0.673
TEXTURE-0.660
Token<|endoftext|>
Token ID50256
Feature activation+1.31e-01

Pos logit contributions
uble+1.698
outer+1.674
oro+1.646
oster+1.561
olphins+1.521
Neg logit contributions
 leaflets-1.914
senal-1.908
 pse-1.822
cffff-1.793
 Masquerade-1.791
TokenMetro
Token ID45141
Feature activation-1.33e-01

Pos logit contributions
uble+0.427
outer+0.425
oro+0.406
oster+0.384
TEXTURE+0.378
Neg logit contributions
 leaflets-0.523
senal-0.502
 Masquerade-0.493
 pse-0.488
 Rollins-0.478
Token Manila
Token ID31721
Feature activation-1.20e+00

Pos logit contributions
 leaflets+0.459
senal+0.434
 Masquerade+0.431
 pse+0.423
 Rollins+0.416
Neg logit contributions
uble-0.497
outer-0.491
oro-0.476
oster-0.453
olphins-0.445
Token (
Token ID357
Feature activation-5.70e-01

Pos logit contributions
 leaflets+3.889
 Masquerade+3.624
senal+3.582
 Dent+3.582
 pse+3.502
Neg logit contributions
uble-4.708
outer-4.659
oro-4.408
oster-4.286
TEXTURE-4.239
TokenCNN
Token ID18474
Feature activation-8.54e-01

Pos logit contributions
 leaflets+1.042
 Masquerade+0.920
senal+0.919
 pse+0.878
 Rollins+0.857
Neg logit contributions
uble-3.066
outer-3.024
oro-2.948
oster-2.869
TEXTURE-2.834
Token Philippines
Token ID13316
Feature activation-1.50e+00

Pos logit contributions
 leaflets+2.553
 Masquerade+2.369
senal+2.331
 Dent+2.312
 Rollins+2.272
Neg logit contributions
uble-3.604
outer-3.565
oro-3.393
oster-3.260
olphins-3.232
Token)
Token ID8
Feature activation-1.07e+00

Pos logit contributions
 leaflets+4.618
 Dent+4.156
senal+4.147
 pse+4.131
 Masquerade+4.112
Neg logit contributions
uble-6.068
outer-5.990
oro-5.570
oster-5.480
TEXTURE-5.437
Token
Token ID851
Feature activation-6.98e-01

Pos logit contributions
 leaflets+3.747
 Masquerade+3.608
 Dent+3.532
 Rollins+3.502
senal+3.489
Neg logit contributions
uble-3.908
outer-3.829
oro-3.643
oster-3.484
TEXTURE-3.457
Token A
Token ID317
Feature activation-4.03e-01

Pos logit contributions
 leaflets+2.320
 Masquerade+2.190
senal+2.154
 Rollins+2.122
 Dent+2.122
Neg logit contributions
uble-2.715
outer-2.677
oro-2.572
oster-2.468
TEXTURE-2.433
Token "
Token ID366
Feature activation+1.72e-01

Pos logit contributions
 leaflets+1.318
senal+1.228
 Masquerade+1.226
 pse+1.204
 Rollins+1.186
Neg logit contributions
uble-1.586
outer-1.570
oro-1.515
oster-1.451
TEXTURE-1.430
Tokenspecial
Token ID20887
Feature activation-2.85e-01

Pos logit contributions
outer+0.548
uble+0.546
oro+0.523
oster+0.492
TEXTURE+0.481
Neg logit contributions
 leaflets-0.698
senal-0.664
 Masquerade-0.659
 pse-0.651
 Rollins-0.640
Token a
Token ID257
Feature activation-5.10e-02

Pos logit contributions
 leaflets+0.542
senal+0.514
 Masquerade+0.506
 pse+0.496
 Rollins+0.487
Neg logit contributions
uble-0.671
outer-0.665
oro-0.642
oster-0.615
olphins-0.606
Token model
Token ID2746
Feature activation-1.53e-02

Pos logit contributions
 leaflets+0.174
senal+0.165
 Masquerade+0.163
 pse+0.159
 Rollins+0.157
Neg logit contributions
uble-0.194
outer-0.192
oro-0.186
oster-0.178
olphins-0.174
Tokenine
Token ID500
Feature activation-2.55e-01

Pos logit contributions
 leaflets+0.040
senal+0.037
 Masquerade+0.036
 pse+0.036
 Rollins+0.035
Neg logit contributions
uble-0.071
outer-0.070
oro-0.068
oster-0.066
olphins-0.065
Token only
Token ID691
Feature activation-6.40e-01

Pos logit contributions
 leaflets+0.886
senal+0.836
 Masquerade+0.831
 pse+0.816
 Rollins+0.803
Neg logit contributions
uble-0.953
outer-0.942
oro-0.910
oster-0.868
olphins-0.853
Token for
Token ID329
Feature activation-5.29e-01

Pos logit contributions
 leaflets+2.197
senal+2.060
 Masquerade+2.054
 pse+2.019
 Rollins+1.986
Neg logit contributions
uble-2.412
outer-2.389
oro-2.308
oster-2.206
TEXTURE-2.163
Token Vim
Token ID36645
Feature activation-1.50e+00

Pos logit contributions
 leaflets+1.649
 Masquerade+1.533
senal+1.531
 pse+1.499
 Rollins+1.475
Neg logit contributions
uble-2.176
outer-2.151
oro-2.082
oster-2.001
TEXTURE-1.963
Token 6
Token ID718
Feature activation-6.68e-01

Pos logit contributions
 leaflets+4.471
 Masquerade+4.096
senal+4.057
 pse+4.007
 Rollins+3.983
Neg logit contributions
uble-6.104
outer-6.017
oro-5.761
oster-5.634
ibaba-5.578
Token.
Token ID13
Feature activation-4.70e-01

Pos logit contributions
 leaflets+2.781
senal+2.637
 Masquerade+2.633
 pse+2.586
 Rollins+2.560
Neg logit contributions
uble-2.011
outer-1.984
oro-1.907
oster-1.795
TEXTURE-1.774
Token0
Token ID15
Feature activation-2.59e-01

Pos logit contributions
 leaflets+1.847
 Masquerade+1.753
senal+1.748
 pse+1.713
 Rollins+1.695
Neg logit contributions
uble-1.534
outer-1.511
oro-1.454
oster-1.382
olphins-1.354
Token and
Token ID290
Feature activation-5.45e-02

Pos logit contributions
 leaflets+0.914
senal+0.868
 Masquerade+0.859
 pse+0.843
 Rollins+0.830
Neg logit contributions
uble-0.955
outer-0.944
oro-0.910
oster-0.868
olphins-0.852
Token later
Token ID1568
Feature activation-5.83e-02

Pos logit contributions
 leaflets+0.166
senal+0.158
 Masquerade+0.155
 pse+0.152
 Rollins+0.149
Neg logit contributions
uble-0.226
outer-0.224
oro-0.217
oster-0.208
olphins-0.205
Token cameras
Token ID9073
Feature activation-1.46e-01

Pos logit contributions
 leaflets+0.541
senal+0.513
 Masquerade+0.505
 pse+0.493
 Rollins+0.486
Neg logit contributions
uble-0.699
outer-0.694
oro-0.671
oster-0.643
olphins-0.631
Token being
Token ID852
Feature activation+2.15e-01

Pos logit contributions
 leaflets+0.513
senal+0.485
 Masquerade+0.482
 pse+0.473
 Rollins+0.466
Neg logit contributions
uble-0.538
outer-0.532
oro-0.513
oster-0.489
olphins-0.481
Token defective
Token ID32129
Feature activation-4.25e-01

Pos logit contributions
uble+0.849
outer+0.841
oro+0.813
oster+0.784
TEXTURE+0.767
Neg logit contributions
 leaflets-0.692
senal-0.662
 Masquerade-0.648
 pse-0.628
 Rollins-0.623
Token (
Token ID357
Feature activation+1.76e-01

Pos logit contributions
 leaflets+1.444
 Masquerade+1.352
senal+1.348
 pse+1.327
 Rollins+1.302
Neg logit contributions
uble-1.615
outer-1.604
oro-1.545
oster-1.475
olphins-1.457
Tokencons
Token ID5936
Feature activation-1.39e-01

Pos logit contributions
outer+0.526
uble+0.525
oro+0.500
oster+0.472
TEXTURE+0.460
Neg logit contributions
 leaflets-0.745
senal-0.715
 Masquerade-0.705
 pse-0.695
 Rollins-0.686
Tokenist
Token ID396
Feature activation-1.49e+00

Pos logit contributions
 leaflets+0.610
senal+0.585
 Masquerade+0.581
 pse+0.572
 Rollins+0.565
Neg logit contributions
uble-0.396
outer-0.390
oro-0.372
oster-0.351
olphins-0.340
Tokenently
Token ID1473
Feature activation-4.43e-01

Pos logit contributions
 leaflets+5.027
senal+4.818
 Masquerade+4.704
 Dent+4.695
 pse+4.677
Neg logit contributions
outer-5.316
uble-5.274
oro-5.017
TEXTURE-4.939
olphins-4.851
Token front
Token ID2166
Feature activation-7.14e-01

Pos logit contributions
 leaflets+1.516
senal+1.422
 Masquerade+1.419
 pse+1.398
 Rollins+1.375
Neg logit contributions
uble-1.678
outer-1.660
oro-1.604
oster-1.527
olphins-1.511
Token-
Token ID12
Feature activation-1.34e-01

Pos logit contributions
 leaflets+2.516
 Masquerade+2.342
senal+2.337
 pse+2.308
 Rollins+2.271
Neg logit contributions
uble-2.602
outer-2.570
oro-2.489
olphins-2.360
oster-2.354
Tokenf
Token ID69
Feature activation-4.10e-01

Pos logit contributions
 leaflets+0.511
senal+0.484
 Masquerade+0.483
 pse+0.474
 Rollins+0.468
Neg logit contributions
uble-0.452
outer-0.444
oro-0.428
oster-0.407
olphins-0.400
Tokenocusing
Token ID45743
Feature activation-6.73e-01

Pos logit contributions
 leaflets+1.565
 Masquerade+1.477
senal+1.454
 Rollins+1.454
 pse+1.451
Neg logit contributions
uble-1.347
outer-1.327
oro-1.297
TEXTURE-1.214
olphins-1.205
Token.
Token ID13
Feature activation-1.20e-01

Pos logit contributions
 leaflets+0.839
senal+0.799
 Masquerade+0.796
 pse+0.783
 Rollins+0.775
Neg logit contributions
uble-0.602
outer-0.595
oro-0.568
oster-0.536
olphins-0.524
Token (
Token ID357
Feature activation-2.18e-01

Pos logit contributions
 leaflets+0.419
senal+0.399
 Masquerade+0.392
 pse+0.387
 Rollins+0.377
Neg logit contributions
uble-0.450
outer-0.445
oro-0.430
oster-0.411
olphins-0.403
TokenPhoto
Token ID6191
Feature activation-2.79e-01

Pos logit contributions
 leaflets+0.835
senal+0.794
 Masquerade+0.789
 pse+0.775
 Rollins+0.765
Neg logit contributions
uble-0.735
outer-0.726
oro-0.698
oster-0.662
olphins-0.649
Token by
Token ID416
Feature activation+1.14e-02

Pos logit contributions
 leaflets+0.880
senal+0.827
 Masquerade+0.821
 pse+0.804
 Rollins+0.790
Neg logit contributions
uble-1.129
outer-1.118
oro-1.081
oster-1.036
olphins-1.019
Token REUTERS
Token ID15862
Feature activation-2.13e-01

Pos logit contributions
uble+0.045
outer+0.045
oro+0.043
oster+0.042
olphins+0.041
Neg logit contributions
 leaflets-0.037
senal-0.035
 Masquerade-0.035
 pse-0.034
 Rollins-0.033
Token/
Token ID14
Feature activation-1.48e+00

Pos logit contributions
 leaflets+0.955
 Masquerade+0.911
senal+0.909
 pse+0.894
 Rollins+0.888
Neg logit contributions
uble-0.584
outer-0.573
oro-0.545
oster-0.509
olphins-0.498
TokenJohn
Token ID7554
Feature activation-3.64e-01

Pos logit contributions
 leaflets+4.801
 Masquerade+4.690
 Rollins+4.550
 Dent+4.480
 Typh+4.403
Neg logit contributions
uble-5.483
outer-5.376
oro-5.090
ibaba-5.054
olphins-4.918
Token S
Token ID311
Feature activation-6.12e-01

Pos logit contributions
 leaflets+0.846
 Masquerade+0.778
 Rollins+0.768
 Dent+0.757
senal+0.751
Neg logit contributions
uble-1.754
outer-1.749
oro-1.697
olphins-1.630
TEXTURE-1.625
Tokenomm
Token ID2002
Feature activation+1.79e-02

Pos logit contributions
 leaflets+2.120
 Rollins+1.987
 Masquerade+1.977
senal+1.960
 Dent+1.936
Neg logit contributions
uble-2.241
outer-2.181
oro-2.108
TEXTURE-2.046
olphins-2.021
Tokeners
Token ID364
Feature activation+5.16e-01

Pos logit contributions
uble+0.075
outer+0.074
oro+0.072
oster+0.069
olphins+0.067
Neg logit contributions
 leaflets-0.055
senal-0.052
 Masquerade-0.051
 pse-0.050
 Rollins-0.048
Token II
Token ID2873
Feature activation+2.63e-01

Pos logit contributions
uble+1.667
outer+1.649
oro+1.619
oster+1.528
olphins+1.461
Neg logit contributions
 leaflets-2.039
senal-1.967
 pse-1.913
 Masquerade-1.908
cffff-1.852
Token an
Token ID281
Feature activation+2.91e-01

Pos logit contributions
uble+1.159
outer+1.142
oro+1.118
oster+1.066
olphins+1.054
Neg logit contributions
 leaflets-0.958
senal-0.918
 Masquerade-0.891
 pse-0.877
cffff-0.860
Token Amber
Token ID21896
Feature activation-1.85e-01

Pos logit contributions
uble+1.076
outer+1.071
oro+1.038
oster+0.982
olphins+0.965
Neg logit contributions
 leaflets-1.018
senal-0.971
 Masquerade-0.948
 pse-0.933
 Rollins-0.919
Token Rose
Token ID8049
Feature activation-1.62e-01

Pos logit contributions
 leaflets+0.637
senal+0.602
 Masquerade+0.598
 pse+0.586
 Rollins+0.578
Neg logit contributions
uble-0.694
outer-0.687
oro-0.663
oster-0.633
olphins-0.622
Token-
Token ID12
Feature activation-2.22e-01

Pos logit contributions
 leaflets+0.582
senal+0.551
 Masquerade+0.547
 pse+0.537
 Rollins+0.529
Neg logit contributions
uble-0.588
outer-0.582
oro-0.561
oster-0.535
olphins-0.524
Tokenre
Token ID260
Feature activation-8.72e-02

Pos logit contributions
 leaflets+1.057
senal+1.015
 Masquerade+1.010
 pse+0.996
 Rollins+0.986
Neg logit contributions
uble-0.542
outer-0.533
oro-0.505
oster-0.469
olphins-0.455
Tokenmin
Token ID1084
Feature activation-1.48e+00

Pos logit contributions
 leaflets+0.330
senal+0.315
 Masquerade+0.310
 pse+0.306
 Dent+0.300
Neg logit contributions
uble-0.302
outer-0.298
oro-0.286
oster-0.274
olphins-0.265
Tokenis
Token ID271
Feature activation-4.82e-01

Pos logit contributions
 leaflets+5.764
 Masquerade+5.609
als+5.492
 Rollins+5.403
 Dent+5.372
Neg logit contributions
outer-4.425
uble-4.354
oro-4.209
TEXTURE-4.113
oster-4.011
Tokencent
Token ID1087
Feature activation-7.28e-01

Pos logit contributions
 leaflets+1.259
 Masquerade+1.165
senal+1.162
 pse+1.144
 Dent+1.112
Neg logit contributions
uble-2.182
outer-2.179
oro-2.107
oster-2.034
olphins-2.015
Token voice
Token ID3809
Feature activation+8.63e-02

Pos logit contributions
 leaflets+2.466
 Masquerade+2.340
senal+2.322
 pse+2.293
 Dent+2.259
Neg logit contributions
uble-2.740
outer-2.719
oro-2.607
oster-2.497
olphins-2.463
Token actress
Token ID14549
Feature activation-8.16e-02

Pos logit contributions
uble+0.309
outer+0.305
oro+0.294
oster+0.280
olphins+0.274
Neg logit contributions
 leaflets-0.315
senal-0.298
 Masquerade-0.296
 pse-0.290
 Rollins-0.286
Token to
Token ID284
Feature activation+3.63e-01

Pos logit contributions
 leaflets+0.299
senal+0.284
 Masquerade+0.282
 pse+0.277
 Rollins+0.272
Neg logit contributions
uble-0.290
outer-0.286
oro-0.276
oster-0.262
olphins-0.257
Tokenem
Token ID368
Feature activation+5.65e-01

Pos logit contributions
uble+0.120
outer+0.118
oro+0.114
oster+0.110
olphins+0.108
Neg logit contributions
 leaflets-0.091
senal-0.085
 Masquerade-0.085
 pse-0.083
 Rollins-0.082
Token ruining
Token ID39842
Feature activation+1.15e-01

Pos logit contributions
uble+1.798
outer+1.736
oro+1.713
oster+1.613
obe+1.574
Neg logit contributions
 leaflets-2.247
senal-2.149
 Masquerade-2.124
 pse-2.096
 Rollins-2.068
Token your
Token ID534
Feature activation-3.36e-01

Pos logit contributions
uble+0.452
outer+0.446
oro+0.433
oster+0.414
olphins+0.406
Neg logit contributions
 leaflets-0.376
senal-0.358
 Masquerade-0.351
 pse-0.346
 Rollins-0.339
Token attempt
Token ID2230
Feature activation-4.37e-01

Pos logit contributions
 leaflets+1.142
 Masquerade+1.074
senal+1.068
 pse+1.048
 Rollins+1.033
Neg logit contributions
uble-1.285
outer-1.273
oro-1.226
oster-1.173
olphins-1.155
Token to
Token ID284
Feature activation-2.00e-01

Pos logit contributions
 leaflets+1.668
senal+1.580
 Masquerade+1.579
 pse+1.547
 Rollins+1.526
Neg logit contributions
uble-1.465
outer-1.460
oro-1.392
oster-1.330
olphins-1.308
Token tape
Token ID9154
Feature activation+1.04e+00

Pos logit contributions
 leaflets+0.707
 Masquerade+0.664
senal+0.662
 pse+0.652
 Rollins+0.642
Neg logit contributions
uble-0.736
outer-0.730
oro-0.704
oster-0.672
olphins-0.660
Token record
Token ID1700
Feature activation+5.45e-01

Pos logit contributions
uble+3.749
outer+3.707
oro+3.605
oster+3.412
fashion+3.374
Neg logit contributions
 leaflets-3.538
senal-3.503
 Masquerade-3.339
 pse-3.330
cffff-3.226
Token the
Token ID262
Feature activation+7.70e-02

Pos logit contributions
uble+2.014
outer+1.979
oro+1.928
oster+1.834
olphins+1.794
Neg logit contributions
 leaflets-1.881
senal-1.833
 Masquerade-1.779
 pse-1.758
 Dent-1.708
Token first
Token ID717
Feature activation-1.15e-01

Pos logit contributions
uble+0.304
outer+0.301
oro+0.291
oster+0.278
olphins+0.273
Neg logit contributions
 leaflets-0.250
senal-0.238
 Masquerade-0.233
 pse-0.229
 Rollins-0.225
Token Western
Token ID4885
Feature activation+1.09e-01

Pos logit contributions
 leaflets+0.383
senal+0.361
 Masquerade+0.359
 pse+0.352
 Rollins+0.346
Neg logit contributions
uble-0.445
outer-0.441
oro-0.426
oster-0.407
olphins-0.400
Token song
Token ID3496
Feature activation-1.32e-01

Pos logit contributions
uble+0.413
outer+0.409
oro+0.395
oster+0.377
olphins+0.371
Neg logit contributions
 leaflets-0.371
senal-0.351
 Masquerade-0.347
 pse-0.341
 Rollins-0.335
Tokens
Token ID82
Feature activation+1.54e-01

Pos logit contributions
 leaflets+1.055
senal+0.998
 Masquerade+0.996
 pse+0.977
 Rollins+0.963
Neg logit contributions
uble-0.988
outer-0.980
oro-0.941
oster-0.896
olphins-0.879
Token books
Token ID3835
Feature activation+4.62e-01

Pos logit contributions
uble+0.627
outer+0.620
oro+0.601
oster+0.576
olphins+0.565
Neg logit contributions
 leaflets-0.483
senal-0.460
 Masquerade-0.448
 pse-0.442
 Rollins-0.434
Token take
Token ID1011
Feature activation+1.98e-01

Pos logit contributions
uble+1.603
outer+1.573
oro+1.525
oster+1.453
olphins+1.416
Neg logit contributions
 leaflets-1.713
senal-1.660
 Masquerade-1.608
 pse-1.590
 Rollins-1.574
Token the
Token ID262
Feature activation+1.65e-01

Pos logit contributions
uble+0.756
outer+0.747
oro+0.724
oster+0.692
olphins+0.677
Neg logit contributions
 leaflets-0.666
senal-0.644
 Masquerade-0.627
 pse-0.616
 Rollins-0.606
Token reader
Token ID9173
Feature activation-3.50e-03

Pos logit contributions
uble+0.621
outer+0.617
oro+0.596
oster+0.570
olphins+0.557
Neg logit contributions
 leaflets-0.567
senal-0.547
 Masquerade-0.531
 pse-0.523
 Rollins-0.512
Token beyond
Token ID3675
Feature activation+9.22e-01

Pos logit contributions
 leaflets+0.012
senal+0.012
 Masquerade+0.012
 pse+0.012
 Rollins+0.011
Neg logit contributions
uble-0.013
outer-0.013
oro-0.012
oster-0.012
olphins-0.011
Token falling
Token ID7463
Feature activation-5.26e-01

Pos logit contributions
uble+3.410
outer+3.347
oro+3.221
oster+3.072
olphins+3.010
Neg logit contributions
senal-3.156
 leaflets-3.146
 Masquerade-2.952
 pse-2.931
cffff-2.882
Token in
Token ID287
Feature activation+5.65e-02

Pos logit contributions
 leaflets+1.754
 Masquerade+1.640
senal+1.640
 pse+1.603
 Rollins+1.577
Neg logit contributions
uble-2.042
outer-2.024
oro-1.955
oster-1.872
olphins-1.840
Token love
Token ID1842
Feature activation+2.94e-01

Pos logit contributions
uble+0.201
outer+0.198
oro+0.191
oster+0.182
olphins+0.178
Neg logit contributions
 leaflets-0.207
senal-0.198
 Masquerade-0.194
 pse-0.192
 Rollins-0.189
Token and
Token ID290
Feature activation+1.40e-01

Pos logit contributions
uble+1.060
outer+1.043
oro+1.010
oster+0.960
olphins+0.943
Neg logit contributions
 leaflets-1.063
senal-1.018
 Masquerade-0.999
 pse-0.985
 Rollins-0.969
Token into
Token ID656
Feature activation-3.61e-01

Pos logit contributions
uble+0.502
outer+0.498
oro+0.479
oster+0.456
olphins+0.447
Neg logit contributions
 leaflets-0.508
senal-0.484
 Masquerade-0.478
 pse-0.470
 Rollins-0.463
Token.
Token ID13
Feature activation+9.05e-02

Pos logit contributions
uble+0.591
outer+0.583
oro+0.567
oster+0.539
olphins+0.527
Neg logit contributions
 leaflets-0.548
senal-0.523
 Masquerade-0.516
 pse-0.504
 Rollins-0.499
Token
Token ID220
Feature activation-1.89e-01

Pos logit contributions
uble+0.337
outer+0.333
oro+0.323
oster+0.308
olphins+0.301
Neg logit contributions
 leaflets-0.315
senal-0.300
 Masquerade-0.295
 pse-0.291
 Rollins-0.284
Token
Token ID134
Feature activation+1.12e+00

Pos logit contributions
 leaflets+0.932
senal+0.894
 Masquerade+0.892
 pse+0.881
 Rollins+0.870
Neg logit contributions
uble-0.429
outer-0.422
oro-0.394
oster-0.366
olphins-0.354
Token
Token ID119
Feature activation+3.20e-01

Pos logit contributions
uble+2.982
outer+2.827
oro+2.792
oster+2.515
=~+2.490
Neg logit contributions
 leaflets-4.939
 Masquerade-4.768
senal-4.723
 Rollins-4.676
cffff-4.596
TokenA
Token ID32
Feature activation+4.31e-01

Pos logit contributions
uble+0.937
outer+0.925
oro+0.890
oster+0.834
olphins+0.809
Neg logit contributions
 leaflets-1.372
senal-1.317
 Masquerade-1.305
 pse-1.284
 Rollins-1.269
Token
Token ID134
Feature activation+8.72e-01

Pos logit contributions
uble+1.491
outer+1.467
oro+1.429
oster+1.349
olphins+1.309
Neg logit contributions
 leaflets-1.616
senal-1.545
 Masquerade-1.526
 pse-1.488
 Rollins-1.483
Token
Token ID119
Feature activation+2.25e-01

Pos logit contributions
uble+2.424
outer+2.321
oro+2.274
oster+2.075
=~+2.062
Neg logit contributions
 leaflets-3.791
 Masquerade-3.631
senal-3.620
 Rollins-3.578
 Dent-3.519
Tokenole
Token ID2305
Feature activation+1.48e-01

Pos logit contributions
uble+0.720
outer+0.710
oro+0.685
oster+0.646
olphins+0.629
Neg logit contributions
 leaflets-0.909
senal-0.869
 Masquerade-0.862
 pse-0.846
 Rollins-0.836
Token i
Token ID1312
Feature activation+3.71e-01

Pos logit contributions
uble+0.489
outer+0.483
oro+0.464
oster+0.440
olphins+0.431
Neg logit contributions
 leaflets-0.578
senal-0.549
 Masquerade-0.546
 pse-0.537
 Rollins-0.529
Token
Token ID220
Feature activation-1.53e-01

Pos logit contributions
uble+1.458
outer+1.434
oro+1.406
oster+1.335
olphins+1.303
Neg logit contributions
 leaflets-1.210
senal-1.156
 Masquerade-1.131
 pse-1.100
 Rollins-1.094
Token
Token ID134
Feature activation+7.69e-01

Pos logit contributions
 leaflets+0.798
senal+0.769
 Masquerade+0.765
 pse+0.758
 Rollins+0.747
Neg logit contributions
uble-0.303
outer-0.298
oro-0.274
oster-0.252
TEXTURE-0.245
Token the
Token ID262
Feature activation+1.22e-02

Pos logit contributions
 leaflets+0.830
senal+0.779
 Masquerade+0.778
 pse+0.764
 Rollins+0.752
Neg logit contributions
uble-0.892
outer-0.883
oro-0.848
oster-0.811
olphins-0.800
Token information
Token ID1321
Feature activation-6.90e-02

Pos logit contributions
uble+0.047
outer+0.047
oro+0.046
oster+0.044
TEXTURE+0.043
Neg logit contributions
 leaflets-0.040
senal-0.039
 Masquerade-0.038
 pse-0.037
 Rollins-0.036
Token containing
Token ID7268
Feature activation-4.65e-01

Pos logit contributions
 leaflets+0.269
senal+0.257
 Masquerade+0.255
 pse+0.250
 Rollins+0.247
Neg logit contributions
uble-0.228
outer-0.226
oro-0.217
oster-0.206
olphins-0.201
Token those
Token ID883
Feature activation-5.90e-01

Pos logit contributions
 leaflets+1.504
 Masquerade+1.397
senal+1.392
 pse+1.370
 Dent+1.348
Neg logit contributions
uble-1.860
outer-1.840
oro-1.771
oster-1.694
olphins-1.674
Token allegations
Token ID7636
Feature activation-2.39e-01

Pos logit contributions
 leaflets+1.805
 Masquerade+1.656
senal+1.648
 pse+1.627
 Dent+1.594
Neg logit contributions
uble-2.468
outer-2.438
oro-2.350
oster-2.257
olphins-2.234
Token?
Token ID30
Feature activation+9.57e-01

Pos logit contributions
 leaflets+1.001
senal+0.949
 Masquerade+0.948
 pse+0.933
 Rollins+0.922
Neg logit contributions
uble-0.721
outer-0.713
oro-0.680
oster-0.640
olphins-0.628
Token DEF
Token ID23449
Feature activation+7.28e-01

Pos logit contributions
uble+3.414
outer+3.368
oro+3.312
TEXTURE+3.202
oster+3.173
Neg logit contributions
senal-3.354
 leaflets-3.325
 pse-3.156
 Masquerade-3.060
cffff-3.042
TokenEND
Token ID10619
Feature activation-2.66e-01

Pos logit contributions
outer+1.939
uble+1.908
oro+1.805
oster+1.728
TEXTURE+1.728
Neg logit contributions
senal-3.360
 leaflets-3.348
 pse-3.203
 Masquerade-3.166
cffff-3.079
TokenAN
Token ID1565
Feature activation+1.88e-01

Pos logit contributions
 leaflets+0.974
 Masquerade+0.919
senal+0.917
 pse+0.897
 Rollins+0.889
Neg logit contributions
uble-0.942
outer-0.931
oro-0.896
oster-0.851
olphins-0.837
TokenTS
Token ID4694
Feature activation+9.91e-02

Pos logit contributions
uble+0.650
outer+0.641
oro+0.618
oster+0.590
TEXTURE+0.580
Neg logit contributions
 leaflets-0.704
senal-0.682
 Masquerade-0.666
 pse-0.659
 Rollins-0.642
Token
Token ID447
Feature activation-6.85e-02

Pos logit contributions
uble+0.306
outer+0.302
oro+0.289
oster+0.273
olphins+0.267
Neg logit contributions
 leaflets-0.409
senal-0.390
 Masquerade-0.388
 pse-0.382
 Rollins-0.377
Token protect
Token ID1805
Feature activation+1.42e-01

Pos logit contributions
uble+0.812
outer+0.801
oro+0.769
oster+0.739
olphins+0.720
Neg logit contributions
 leaflets-0.784
senal-0.768
 Masquerade-0.739
 pse-0.726
 Rollins-0.718
Token them
Token ID606
Feature activation-8.33e-02

Pos logit contributions
uble+0.495
outer+0.490
oro+0.472
oster+0.454
olphins+0.442
Neg logit contributions
 leaflets-0.526
senal-0.517
 Masquerade-0.499
 pse-0.492
 Rollins-0.485
Token from
Token ID422
Feature activation-3.58e-01

Pos logit contributions
 leaflets+0.275
senal+0.262
 Masquerade+0.258
 pse+0.253
 Rollins+0.249
Neg logit contributions
uble-0.326
outer-0.322
oro-0.312
oster-0.299
olphins-0.293
Token the
Token ID262
Feature activation+1.52e-01

Pos logit contributions
 leaflets+1.028
 Masquerade+0.945
senal+0.939
 pse+0.923
 Rollins+0.904
Neg logit contributions
uble-1.561
outer-1.544
oro-1.496
oster-1.434
TEXTURE-1.417
Token harsh
Token ID11859
Feature activation+4.59e-01

Pos logit contributions
uble+0.567
outer+0.562
oro+0.544
oster+0.519
olphins+0.509
Neg logit contributions
 leaflets-0.521
senal-0.504
 Masquerade-0.491
 pse-0.482
 Rollins-0.476
Token Antarctic
Token ID33149
Feature activation+8.48e-01

Pos logit contributions
outer+1.738
uble+1.734
oro+1.688
oster+1.602
olphins+1.573
Neg logit contributions
 leaflets-1.526
senal-1.501
 Masquerade-1.446
 pse-1.419
 Rollins-1.407
Token winter
Token ID7374
Feature activation-1.28e-02

Pos logit contributions
uble+3.268
outer+3.256
oro+3.202
oster+3.029
olphins+2.971
Neg logit contributions
 leaflets-2.712
senal-2.695
 Masquerade-2.573
 pse-2.544
cffff-2.514
Token,
Token ID11
Feature activation-1.12e-01

Pos logit contributions
 leaflets+0.046
senal+0.044
 Masquerade+0.043
 pse+0.043
 Rollins+0.042
Neg logit contributions
uble-0.046
outer-0.046
oro-0.044
oster-0.042
olphins-0.041
Token incub
Token ID25543
Feature activation-4.70e-02

Pos logit contributions
 leaflets+0.408
senal+0.393
 Masquerade+0.386
 pse+0.378
 Rollins+0.373
Neg logit contributions
uble-0.398
outer-0.392
oro-0.378
oster-0.362
olphins-0.353
Tokenate
Token ID378
Feature activation+1.24e-01

Pos logit contributions
 leaflets+0.194
senal+0.184
 Masquerade+0.184
 pse+0.181
 Rollins+0.178
Neg logit contributions
uble-0.145
outer-0.143
oro-0.137
oster-0.129
olphins-0.126
Token their
Token ID511
Feature activation+1.61e-01

Pos logit contributions
uble+0.483
outer+0.477
oro+0.461
oster+0.444
olphins+0.434
Neg logit contributions
 leaflets-0.409
senal-0.396
 Masquerade-0.385
 pse-0.378
 Rollins-0.371
Token-
Token ID12
Feature activation-8.29e-02

Pos logit contributions
uble+0.117
outer+0.116
oro+0.112
oster+0.106
olphins+0.104
Neg logit contributions
 leaflets-0.127
senal-0.121
 Masquerade-0.120
 pse-0.118
 Rollins-0.116
TokenACC
Token ID26861
Feature activation+4.53e-01

Pos logit contributions
 leaflets+0.303
senal+0.289
 Masquerade+0.284
 pse+0.283
 Rollins+0.274
Neg logit contributions
uble-0.295
outer-0.293
oro-0.282
oster-0.269
TEXTURE-0.264
Token Fresh
Token ID20138
Feature activation-2.85e-01

Pos logit contributions
outer+1.888
uble+1.879
oro+1.825
oster+1.761
olphins+1.727
Neg logit contributions
 leaflets-1.339
senal-1.300
 Masquerade-1.237
 pse-1.236
cffff-1.202
Tokenman
Token ID805
Feature activation-5.64e-03

Pos logit contributions
 leaflets+1.096
senal+1.043
 Masquerade+1.034
 pse+1.019
 Rollins+1.003
Neg logit contributions
uble-0.960
outer-0.951
oro-0.913
oster-0.868
olphins-0.850
Token first
Token ID717
Feature activation-2.02e-01

Pos logit contributions
 leaflets+0.018
senal+0.017
 Masquerade+0.017
 pse+0.017
 Rollins+0.016
Neg logit contributions
uble-0.023
outer-0.022
oro-0.022
oster-0.021
olphins-0.020
Token team
Token ID1074
Feature activation-8.10e-02

Pos logit contributions
 leaflets+0.510
senal+0.477
 Masquerade+0.469
 pse+0.456
 Rollins+0.446
Neg logit contributions
uble-0.946
outer-0.939
oro-0.913
oster-0.881
olphins-0.868
Token (
Token ID357
Feature activation+4.48e-01

Pos logit contributions
 leaflets+0.309
senal+0.293
 Masquerade+0.292
 pse+0.287
 Rollins+0.283
Neg logit contributions
uble-0.275
outer-0.272
oro-0.261
oster-0.248
olphins-0.243
Tokenalong
Token ID24176
Feature activation+4.52e-01

Pos logit contributions
outer+1.414
uble+1.392
oro+1.341
oster+1.267
TEXTURE+1.234
Neg logit contributions
 leaflets-1.831
senal-1.753
 Masquerade-1.720
 pse-1.706
 Dent-1.673
Token with
Token ID351
Feature activation-2.13e-01

Pos logit contributions
uble+1.458
outer+1.450
oro+1.398
oster+1.347
olphins+1.297
Neg logit contributions
 leaflets-1.779
senal-1.692
 Masquerade-1.679
 pse-1.648
 Dent-1.608
Token Jones
Token ID5437
Feature activation-6.57e-02

Pos logit contributions
 leaflets+0.688
senal+0.644
 Masquerade+0.644
 pse+0.629
 Rollins+0.623
Neg logit contributions
uble-0.848
outer-0.839
oro-0.811
oster-0.776
olphins-0.763
Token and
Token ID290
Feature activation+1.05e-01

Pos logit contributions
 leaflets+0.228
senal+0.215
 Masquerade+0.214
 pse+0.210
 Rollins+0.206
Neg logit contributions
uble-0.246
outer-0.243
oro-0.235
oster-0.224
olphins-0.220
Token
Token ID198
Feature activation-6.08e-01

Pos logit contributions
 leaflets+1.145
senal+1.086
 Masquerade+1.081
 pse+1.061
 Rollins+1.048
Neg logit contributions
uble-1.045
outer-1.033
oro-0.993
oster-0.944
olphins-0.925
Token
Token ID198
Feature activation-3.59e-01

Pos logit contributions
 leaflets+2.190
 Masquerade+2.067
 Rollins+2.032
 Dent+2.023
als+2.003
Neg logit contributions
uble-2.145
outer-2.108
oro-2.024
olphins-1.928
oster-1.921
TokenSee
Token ID6214
Feature activation+9.62e-02

Pos logit contributions
 leaflets+1.315
 Masquerade+1.244
senal+1.242
 pse+1.215
 Rollins+1.204
Neg logit contributions
uble-1.270
outer-1.248
oro-1.203
oster-1.146
olphins-1.126
Token also
Token ID635
Feature activation-5.33e-01

Pos logit contributions
uble+0.248
outer+0.245
oro+0.234
oster+0.218
olphins+0.212
Neg logit contributions
 leaflets-0.445
senal-0.430
 Masquerade-0.425
 pse-0.419
 Rollins-0.413
Token [
Token ID685
Feature activation-1.65e-01

Pos logit contributions
 leaflets+1.461
 Masquerade+1.340
senal+1.328
 pse+1.297
 Dent+1.287
Neg logit contributions
uble-2.387
outer-2.365
oro-2.275
oster-2.199
TEXTURE-2.170
Token edit
Token ID4370
Feature activation+8.28e-02

Pos logit contributions
 leaflets+0.460
 Masquerade+0.424
senal+0.423
 pse+0.413
 Rollins+0.406
Neg logit contributions
uble-0.726
outer-0.719
oro-0.698
oster-0.671
olphins-0.662
Token ]
Token ID2361
Feature activation-4.34e-01

Pos logit contributions
uble+0.302
outer+0.299
oro+0.288
oster+0.275
olphins+0.270
Neg logit contributions
 leaflets-0.295
senal-0.280
 Masquerade-0.277
 pse-0.273
 Rollins-0.268
Token<|endoftext|>
Token ID50256
Feature activation-2.13e-02

Pos logit contributions
 leaflets+1.786
 Masquerade+1.690
senal+1.688
 Rollins+1.654
 pse+1.646
Neg logit contributions
uble-1.341
outer-1.321
oro-1.253
oster-1.179
TEXTURE-1.161
TokenI
Token ID40
Feature activation+3.77e-01

Pos logit contributions
 leaflets+0.085
senal+0.081
 Masquerade+0.080
 pse+0.079
 Rollins+0.077
Neg logit contributions
uble-0.070
outer-0.069
oro-0.066
oster-0.063
TEXTURE-0.061
Tokenke
Token ID365
Feature activation-5.98e-01

Pos logit contributions
uble+1.229
outer+1.198
oro+1.171
oster+1.111
olphins+1.068
Neg logit contributions
 leaflets-1.492
senal-1.437
 Masquerade-1.408
 pse-1.376
 Rollins-1.355
Tokena
Token ID64
Feature activation-1.72e-01

Pos logit contributions
 leaflets+2.077
 Masquerade+1.957
senal+1.949
 pse+1.907
 Rollins+1.890
Neg logit contributions
uble-2.231
outer-2.215
oro-2.121
oster-2.031
TEXTURE-1.995
Token a
Token ID257
Feature activation+2.21e-03

Pos logit contributions
 leaflets+0.283
senal+0.271
 Masquerade+0.264
 pse+0.258
 Rollins+0.253
Neg logit contributions
uble-0.412
outer-0.407
oro-0.395
oster-0.380
olphins-0.372
Token week
Token ID1285
Feature activation-7.72e-02

Pos logit contributions
uble+0.010
outer+0.010
oro+0.010
oster+0.010
olphins+0.009
Neg logit contributions
 leaflets-0.006
senal-0.005
 Masquerade-0.005
 pse-0.005
 Rollins-0.005
Token to
Token ID284
Feature activation+2.09e-01

Pos logit contributions
 leaflets+0.309
senal+0.293
 Masquerade+0.292
 pse+0.287
 Rollins+0.284
Neg logit contributions
uble-0.247
outer-0.244
oro-0.234
oster-0.222
olphins-0.217
Token a
Token ID257
Feature activation+3.35e-01

Pos logit contributions
uble+0.888
outer+0.874
oro+0.853
oster+0.819
olphins+0.798
Neg logit contributions
 leaflets-0.620
senal-0.595
 Masquerade-0.578
 pse-0.566
 Rollins-0.553
Token couple
Token ID3155
Feature activation+8.40e-02

Pos logit contributions
uble+1.367
outer+1.347
oro+1.313
oster+1.256
olphins+1.226
Neg logit contributions
 leaflets-1.047
senal-0.997
 Masquerade-0.977
 pse-0.955
 Rollins-0.935
Token of
Token ID286
Feature activation-3.88e-02

Pos logit contributions
uble+0.348
outer+0.345
oro+0.334
oster+0.321
olphins+0.315
Neg logit contributions
 leaflets-0.258
senal-0.242
 Masquerade-0.240
 pse-0.235
 Rollins-0.231
Token months
Token ID1933
Feature activation-1.25e-02

Pos logit contributions
 leaflets+0.105
senal+0.097
 Masquerade+0.097
 pse+0.094
 Rollins+0.093
Neg logit contributions
uble-0.174
outer-0.173
oro-0.168
oster-0.162
olphins-0.159
Token,
Token ID11
Feature activation-9.98e-02

Pos logit contributions
 leaflets+0.049
senal+0.046
 Masquerade+0.046
 pse+0.045
 Rollins+0.045
Neg logit contributions
uble-0.041
outer-0.041
oro-0.039
oster-0.037
olphins-0.037
Token and
Token ID290
Feature activation-2.06e-02

Pos logit contributions
 leaflets+0.324
senal+0.309
 Masquerade+0.304
 pse+0.298
 Rollins+0.291
Neg logit contributions
uble-0.395
outer-0.391
oro-0.378
oster-0.363
olphins-0.355
Token the
Token ID262
Feature activation-2.00e-01

Pos logit contributions
 leaflets+0.074
senal+0.070
 Masquerade+0.070
 pse+0.068
 Rollins+0.067
Neg logit contributions
uble-0.075
outer-0.074
oro-0.071
oster-0.068
olphins-0.066
Token pressure
Token ID3833
Feature activation+2.93e-02

Pos logit contributions
 leaflets+0.659
senal+0.620
 Masquerade+0.616
 pse+0.603
 Rollins+0.593
Neg logit contributions
uble-0.783
outer-0.775
oro-0.749
oster-0.717
olphins-0.704
Token me
Token ID502
Feature activation+5.94e-02

Pos logit contributions
uble+1.256
outer+1.235
oro+1.205
oster+1.140
TEXTURE+1.108
Neg logit contributions
 leaflets-1.398
senal-1.357
 Masquerade-1.317
 pse-1.304
 Rollins-1.276
Token.
Token ID13
Feature activation+3.05e-01

Pos logit contributions
uble+0.191
outer+0.189
oro+0.181
oster+0.171
olphins+0.168
Neg logit contributions
 leaflets-0.237
senal-0.226
 Masquerade-0.225
 pse-0.221
 Rollins-0.218
Token I
Token ID314
Feature activation+1.97e-01

Pos logit contributions
uble+0.922
outer+0.910
oro+0.876
oster+0.826
TEXTURE+0.803
Neg logit contributions
 leaflets-1.274
senal-1.224
 Masquerade-1.201
 pse-1.192
 Rollins-1.168
Token am
Token ID716
Feature activation+3.55e-01

Pos logit contributions
uble+0.649
outer+0.640
oro+0.616
oster+0.585
olphins+0.569
Neg logit contributions
 leaflets-0.770
senal-0.738
 Masquerade-0.726
 pse-0.716
 Rollins-0.705
Token ready
Token ID3492
Feature activation+4.14e-02

Pos logit contributions
uble+1.298
outer+1.282
oro+1.241
oster+1.184
TEXTURE+1.155
Neg logit contributions
 leaflets-1.262
senal-1.201
 Masquerade-1.181
 pse-1.169
 Rollins-1.140
Token.
Token ID13
Feature activation+2.47e-01

Pos logit contributions
uble+0.127
outer+0.126
oro+0.121
oster+0.114
olphins+0.111
Neg logit contributions
 leaflets-0.171
senal-0.163
 Masquerade-0.162
 pse-0.160
 Rollins-0.158
Token
Token ID564
Feature activation-9.39e-03

Pos logit contributions
uble+0.817
outer+0.806
oro+0.778
oster+0.738
TEXTURE+0.720
Neg logit contributions
 leaflets-0.967
senal-0.927
 Masquerade-0.907
 pse-0.901
 Rollins-0.880
Token
Token ID251
Feature activation+3.42e-01

Pos logit contributions
 leaflets+0.037
senal+0.035
 Masquerade+0.035
 pse+0.034
 Rollins+0.034
Neg logit contributions
uble-0.031
outer-0.031
oro-0.029
oster-0.028
olphins-0.027
Token Then
Token ID3244
Feature activation+2.23e-01

Pos logit contributions
uble+1.087
outer+1.073
oro+1.036
oster+0.979
TEXTURE+0.955
Neg logit contributions
 leaflets-1.381
senal-1.332
 Masquerade-1.294
 pse-1.292
 Rollins-1.259
Token,
Token ID11
Feature activation+2.32e-01

Pos logit contributions
uble+0.768
outer+0.759
oro+0.736
oster+0.698
TEXTURE+0.683
Neg logit contributions
 leaflets-0.829
senal-0.804
 Masquerade-0.783
 pse-0.774
 Rollins-0.755
Token it
Token ID340
Feature activation+1.58e-01

Pos logit contributions
uble+0.835
outer+0.825
oro+0.800
oster+0.762
TEXTURE+0.745
Neg logit contributions
 leaflets-0.827
senal-0.805
 Masquerade-0.781
 pse-0.771
 Rollins-0.750
Token all
Token ID477
Feature activation-9.59e-02

Pos logit contributions
uble+2.020
outer+1.978
oro+1.911
oster+1.830
olphins+1.774
Neg logit contributions
 leaflets-2.268
senal-2.227
 Masquerade-2.156
 pse-2.127
 Rollins-2.087
Token?
Token ID30
Feature activation+7.40e-01

Pos logit contributions
 leaflets+0.402
 Masquerade+0.380
senal+0.379
 pse+0.374
 Dent+0.370
Neg logit contributions
uble-0.290
outer-0.287
oro-0.273
oster-0.257
TEXTURE-0.252
Token
Token ID198
Feature activation+1.91e-01

Pos logit contributions
uble+2.379
outer+2.338
oro+2.295
oster+2.154
usa+2.096
Neg logit contributions
 leaflets-2.908
senal-2.857
 pse-2.748
cffff-2.681
 Masquerade-2.664
Token
Token ID198
Feature activation+1.93e-01

Pos logit contributions
uble+0.583
outer+0.576
oro+0.552
oster+0.521
TEXTURE+0.509
Neg logit contributions
 leaflets-0.793
senal-0.770
 Masquerade-0.751
 pse-0.747
 Rollins-0.728
TokenThe
Token ID464
Feature activation+7.60e-02

Pos logit contributions
uble+0.622
outer+0.617
oro+0.594
oster+0.559
TEXTURE+0.556
Neg logit contributions
 leaflets-0.775
senal-0.751
 pse-0.725
 Masquerade-0.725
 Rollins-0.702
Token first
Token ID717
Feature activation+2.29e-01

Pos logit contributions
uble+0.298
outer+0.294
oro+0.287
oster+0.271
olphins+0.266
Neg logit contributions
 leaflets-0.248
senal-0.242
 Masquerade-0.233
 pse-0.228
cffff-0.223
Token proposal
Token ID6961
Feature activation+7.81e-01

Pos logit contributions
uble+0.855
outer+0.843
oro+0.822
oster+0.782
olphins+0.762
Neg logit contributions
 leaflets-0.788
senal-0.770
 Masquerade-0.743
 pse-0.731
 Rollins-0.718
Token,
Token ID11
Feature activation+7.55e-01

Pos logit contributions
uble+2.620
outer+2.547
oro+2.487
oster+2.363
obe+2.277
Neg logit contributions
senal-2.954
 leaflets-2.905
 Masquerade-2.770
 pse-2.731
cffff-2.716
Token Mandatory
Token ID47018
Feature activation-7.27e-02

Pos logit contributions
uble+2.720
outer+2.681
oro+2.605
oster+2.489
olphins+2.415
Neg logit contributions
 leaflets-2.591
senal-2.584
 Masquerade-2.456
 pse-2.441
cffff-2.406
Token In
Token ID554
Feature activation+7.08e-02

Pos logit contributions
 leaflets+0.227
senal+0.215
 Masquerade+0.211
 pse+0.210
 Rollins+0.204
Neg logit contributions
uble-0.296
outer-0.293
oro-0.285
oster-0.273
olphins-0.268
Tokenclusion
Token ID4717
Feature activation-1.20e-01

Pos logit contributions
uble+0.257
outer+0.253
oro+0.244
oster+0.233
olphins+0.228
Neg logit contributions
 leaflets-0.255
senal-0.243
 Masquerade-0.239
 pse-0.237
 Rollins-0.232
Token that
Token ID326
Feature activation+2.33e-02

Pos logit contributions
 leaflets+0.928
senal+0.873
 Masquerade+0.867
 pse+0.849
 Rollins+0.836
Neg logit contributions
uble-1.126
outer-1.115
oro-1.078
oster-1.032
olphins-1.014
Token authorities
Token ID4773
Feature activation+4.50e-01

Pos logit contributions
uble+0.092
outer+0.091
oro+0.088
oster+0.084
olphins+0.083
Neg logit contributions
 leaflets-0.075
senal-0.072
 Masquerade-0.070
 pse-0.069
cffff-0.067
Token are
Token ID389
Feature activation-6.52e-01

Pos logit contributions
outer+1.509
uble+1.504
oro+1.464
oster+1.399
olphins+1.336
Neg logit contributions
senal-1.679
 leaflets-1.661
 Masquerade-1.600
 pse-1.575
cffff-1.561
Token questioning
Token ID14085
Feature activation-9.14e-02

Pos logit contributions
 leaflets+2.264
 Masquerade+2.089
senal+2.071
 pse+2.055
 Rollins+2.047
Neg logit contributions
uble-2.452
outer-2.423
oro-2.331
oster-2.222
TEXTURE-2.207
Token a
Token ID257
Feature activation-2.59e-01

Pos logit contributions
 leaflets+0.281
senal+0.271
 Masquerade+0.263
 pse+0.259
cffff+0.251
Neg logit contributions
uble-0.375
outer-0.370
oro-0.360
oster-0.346
olphins-0.340
Token person
Token ID1048
Feature activation-1.89e-01

Pos logit contributions
 leaflets+0.864
senal+0.815
 Masquerade+0.809
 pse+0.793
 Rollins+0.780
Neg logit contributions
uble-1.002
outer-0.992
oro-0.958
oster-0.916
olphins-0.900
Token of
Token ID286
Feature activation-7.27e-01

Pos logit contributions
 leaflets+0.573
senal+0.543
 Masquerade+0.534
 pse+0.524
 Rollins+0.511
Neg logit contributions
uble-0.790
outer-0.780
oro-0.758
oster-0.728
olphins-0.714
Token interest
Token ID1393
Feature activation-5.63e-02

Pos logit contributions
 leaflets+2.791
 Masquerade+2.621
 pse+2.592
senal+2.582
 Dent+2.563
Neg logit contributions
uble-2.425
outer-2.415
oro-2.304
oster-2.191
olphins-2.163
Token at
Token ID379
Feature activation-5.07e-01

Pos logit contributions
 leaflets+0.190
senal+0.183
 Masquerade+0.179
 pse+0.176
 Rollins+0.171
Neg logit contributions
uble-0.216
outer-0.213
oro-0.206
oster-0.197
olphins-0.192
Token Brigham
Token ID37434
Feature activation+4.36e-01

Pos logit contributions
 leaflets+1.649
senal+1.550
 Masquerade+1.542
 pse+1.507
 Rollins+1.488
Neg logit contributions
uble-2.005
outer-1.984
oro-1.918
oster-1.836
olphins-1.804
Token and
Token ID290
Feature activation+3.63e-02

Pos logit contributions
uble+1.859
outer+1.845
oro+1.829
oster+1.766
TEXTURE+1.704
Neg logit contributions
 leaflets-1.233
senal-1.193
 Masquerade-1.143
 pse-1.143
cffff-1.113
Token the
Token ID262
Feature activation-3.46e-01

Pos logit contributions
 leaflets+0.911
senal+0.863
 Masquerade+0.854
 pse+0.839
 Rollins+0.823
Neg logit contributions
uble-1.007
outer-0.997
oro-0.964
oster-0.920
olphins-0.902
Token rooft
Token ID27291
Feature activation-4.17e-01

Pos logit contributions
 leaflets+1.139
senal+1.074
 Masquerade+1.064
 pse+1.044
 Rollins+1.026
Neg logit contributions
uble-1.357
outer-1.343
oro-1.299
oster-1.242
olphins-1.220
Tokenops
Token ID2840
Feature activation-1.59e-01

Pos logit contributions
 leaflets+0.979
 Masquerade+0.875
 pse+0.847
senal+0.840
 Dent+0.832
Neg logit contributions
uble-2.016
outer-1.991
oro-1.938
oster-1.868
TEXTURE-1.866
Token to
Token ID284
Feature activation-4.45e-01

Pos logit contributions
 leaflets+0.559
senal+0.531
 Masquerade+0.526
 pse+0.516
 Rollins+0.507
Neg logit contributions
uble-0.586
outer-0.579
oro-0.560
oster-0.533
olphins-0.523
Token duel
Token ID24662
Feature activation-2.21e-01

Pos logit contributions
 leaflets+1.621
 Masquerade+1.528
senal+1.506
 pse+1.494
 Rollins+1.473
Neg logit contributions
uble-1.588
outer-1.567
oro-1.507
oster-1.440
olphins-1.419
Token to
Token ID284
Feature activation-2.05e-01

Pos logit contributions
 leaflets+0.748
senal+0.707
 Masquerade+0.701
 pse+0.688
 Rollins+0.676
Neg logit contributions
uble-0.845
outer-0.836
oro-0.808
oster-0.772
olphins-0.758
Token the
Token ID262
Feature activation+3.64e-01

Pos logit contributions
 leaflets+0.713
senal+0.671
 Masquerade+0.670
 pse+0.657
 Rollins+0.647
Neg logit contributions
uble-0.769
outer-0.760
oro-0.733
oster-0.700
olphins-0.688
Token death
Token ID1918
Feature activation+1.14e-01

Pos logit contributions
uble+1.829
outer+1.821
oro+1.786
oster+1.706
olphins+1.684
Neg logit contributions
 leaflets-0.782
senal-0.731
 pse-0.685
 Masquerade-0.681
cffff-0.667
Token in
Token ID287
Feature activation-2.92e-01

Pos logit contributions
uble+0.363
outer+0.358
oro+0.344
oster+0.325
olphins+0.317
Neg logit contributions
 leaflets-0.462
senal-0.441
 Masquerade-0.438
 pse-0.432
 Rollins-0.423
Token the
Token ID262
Feature activation-4.00e-01

Pos logit contributions
 leaflets+0.984
senal+0.924
 Masquerade+0.922
 pse+0.903
 Rollins+0.890
Neg logit contributions
uble-1.122
outer-1.109
oro-1.071
oster-1.025
olphins-1.007
Token name
Token ID1438
Feature activation+1.16e-02

Pos logit contributions
 leaflets+1.338
 Masquerade+1.257
senal+1.252
 pse+1.226
 Rollins+1.210
Neg logit contributions
uble-1.551
outer-1.532
oro-1.477
oster-1.417
olphins-1.393
Token
Token ID198
Feature activation+2.31e-01

Pos logit contributions
uble+0.838
outer+0.828
oro+0.806
oster+0.759
olphins+0.734
Neg logit contributions
 leaflets-1.114
senal-1.080
 pse-1.051
 Masquerade-1.043
cffff-1.025
Token
Token ID198
Feature activation+1.58e-01

Pos logit contributions
uble+0.710
outer+0.702
oro+0.672
oster+0.635
TEXTURE+0.619
Neg logit contributions
 leaflets-0.955
senal-0.924
 Masquerade-0.905
 pse-0.898
 Rollins-0.878
Token
Token ID447
Feature activation-8.69e-02

Pos logit contributions
uble+0.466
outer+0.460
oro+0.443
oster+0.416
TEXTURE+0.407
Neg logit contributions
 leaflets-0.675
senal-0.651
 Masquerade-0.638
 pse-0.633
 Rollins-0.619
Token
Token ID250
Feature activation-1.69e-02

Pos logit contributions
 leaflets+0.341
senal+0.324
 Masquerade+0.322
 pse+0.317
 Rollins+0.313
Neg logit contributions
uble-0.286
outer-0.283
oro-0.271
oster-0.257
olphins-0.252
TokenMaybe
Token ID13300
Feature activation+7.77e-02

Pos logit contributions
 leaflets+0.070
senal+0.067
 Masquerade+0.066
 pse+0.065
 Rollins+0.064
Neg logit contributions
uble-0.052
outer-0.052
oro-0.050
oster-0.047
TEXTURE-0.046
Token we
Token ID356
Feature activation-2.42e-01

Pos logit contributions
uble+0.295
outer+0.292
oro+0.283
oster+0.270
olphins+0.263
Neg logit contributions
 leaflets-0.263
senal-0.253
 Masquerade-0.249
 pse-0.242
 Rollins-0.239
Token have
Token ID423
Feature activation-1.40e-01

Pos logit contributions
 leaflets+0.947
senal+0.904
 Masquerade+0.896
 pse+0.881
 Rollins+0.869
Neg logit contributions
uble-0.801
outer-0.791
oro-0.760
oster-0.721
olphins-0.705
Token to
Token ID284
Feature activation-5.25e-01

Pos logit contributions
 leaflets+0.506
senal+0.480
 Masquerade+0.477
 pse+0.468
 Rollins+0.461
Neg logit contributions
uble-0.504
outer-0.498
oro-0.480
oster-0.458
olphins-0.449
Token pray
Token ID12472
Feature activation-3.99e-01

Pos logit contributions
 leaflets+1.807
 Masquerade+1.684
 pse+1.664
senal+1.662
 Rollins+1.630
Neg logit contributions
uble-1.975
outer-1.955
oro-1.884
oster-1.798
TEXTURE-1.780
Token,
Token ID11
Feature activation-1.96e-01

Pos logit contributions
 leaflets+1.399
senal+1.314
 Masquerade+1.310
 pse+1.288
 Rollins+1.269
Neg logit contributions
uble-1.476
outer-1.460
oro-1.409
oster-1.342
olphins-1.321
Token
Token ID447
Feature activation+1.82e-02

Pos logit contributions
 leaflets+0.816
senal+0.780
 Masquerade+0.774
 pse+0.762
 Rollins+0.752
Neg logit contributions
uble-0.597
outer-0.589
oro-0.564
oster-0.533
olphins-0.519
Token
Token ID564
Feature activation-5.09e-01

Pos logit contributions
 leaflets+1.463
 Masquerade+1.361
senal+1.361
 pse+1.336
 Dent+1.322
Neg logit contributions
uble-1.958
outer-1.950
oro-1.882
oster-1.805
TEXTURE-1.782
Token
Token ID250
Feature activation-1.89e-01

Pos logit contributions
 leaflets+1.877
senal+1.778
 Masquerade+1.771
 pse+1.754
 Rollins+1.727
Neg logit contributions
outer-1.760
uble-1.746
oro-1.675
oster-1.598
TEXTURE-1.584
Tokenparent
Token ID8000
Feature activation-5.50e-01

Pos logit contributions
 leaflets+0.711
senal+0.674
 Masquerade+0.669
 pse+0.657
 Rollins+0.647
Neg logit contributions
uble-0.657
outer-0.650
oro-0.625
oster-0.594
olphins-0.581
Token
Token ID447
Feature activation-3.52e-01

Pos logit contributions
 leaflets+2.201
senal+2.091
 Masquerade+2.087
 pse+2.061
 Dent+2.029
Neg logit contributions
uble-1.746
outer-1.733
oro-1.654
oster-1.565
olphins-1.545
Token
Token ID251
Feature activation-5.06e-01

Pos logit contributions
 leaflets+1.373
senal+1.305
 Masquerade+1.302
 pse+1.284
 Rollins+1.268
Neg logit contributions
outer-1.145
uble-1.141
oro-1.086
oster-1.036
olphins-1.021
Token since
Token ID1201
Feature activation-4.03e-01

Pos logit contributions
 leaflets+1.783
senal+1.680
 Masquerade+1.678
 pse+1.645
 Rollins+1.634
Neg logit contributions
uble-1.848
outer-1.837
oro-1.769
oster-1.681
TEXTURE-1.669
Token 2016
Token ID1584
Feature activation+5.38e-02

Pos logit contributions
 leaflets+1.468
 Masquerade+1.385
 pse+1.360
senal+1.360
 Rollins+1.355
Neg logit contributions
uble-1.435
outer-1.425
oro-1.363
oster-1.294
TEXTURE-1.290
Token.
Token ID13
Feature activation-6.18e-02

Pos logit contributions
uble+0.160
outer+0.157
oro+0.150
oster+0.142
olphins+0.138
Neg logit contributions
 leaflets-0.228
senal-0.218
 Masquerade-0.217
 pse-0.214
 Rollins-0.211
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
 leaflets+0.247
senal+0.236
 Masquerade+0.234
 pse+0.231
 Rollins+0.227
Neg logit contributions
uble-0.198
outer-0.196
oro-0.188
oster-0.178
olphins-0.174
Token
Token ID198
Feature activation-2.55e-02

Pos logit contributions
 leaflets+0.537
 Masquerade+0.508
 Rollins+0.496
 Dent+0.494
 pse+0.487
Neg logit contributions
uble-0.452
outer-0.445
oro-0.427
oster-0.404
olphins-0.399
TokenShe
Token ID3347
Feature activation-4.29e-01

Pos logit contributions
 leaflets+0.104
senal+0.099
 Masquerade+0.098
 pse+0.097
 Rollins+0.095
Neg logit contributions
uble-0.080
outer-0.079
oro-0.076
oster-0.072
olphins-0.070
Token.
Token ID13
Feature activation+1.61e-01

Pos logit contributions
uble+0.027
outer+0.027
oro+0.026
oster+0.024
olphins+0.024
Neg logit contributions
 leaflets-0.039
 Masquerade-0.037
 Rollins-0.037
 Dent-0.036
senal-0.036
Token A
Token ID317
Feature activation-4.11e-02

Pos logit contributions
uble+0.573
outer+0.567
oro+0.549
oster+0.522
TEXTURE+0.511
Neg logit contributions
 leaflets-0.582
senal-0.559
 Masquerade-0.545
 pse-0.540
cffff-0.528
TokenUS
Token ID2937
Feature activation+4.21e-01

Pos logit contributions
 leaflets+0.171
senal+0.164
 Masquerade+0.162
 pse+0.160
 Rollins+0.157
Neg logit contributions
uble-0.126
outer-0.124
oro-0.120
oster-0.113
TEXTURE-0.110
Token 5
Token ID642
Feature activation-1.06e-01

Pos logit contributions
outer+1.554
uble+1.543
oro+1.498
oster+1.427
TEXTURE+1.391
Neg logit contributions
 leaflets-1.468
senal-1.407
 Masquerade-1.390
 pse-1.353
cffff-1.330
Token Robbie
Token ID34855
Feature activation+6.18e-02

Pos logit contributions
 leaflets+0.339
senal+0.319
 Masquerade+0.316
 pse+0.310
 Rollins+0.303
Neg logit contributions
uble-0.426
outer-0.422
oro-0.408
oster-0.391
olphins-0.384
Token M
Token ID337
Feature activation-5.00e-01

Pos logit contributions
uble+0.282
outer+0.279
oro+0.271
oster+0.261
olphins+0.258
Neg logit contributions
 leaflets-0.164
 Masquerade-0.151
senal-0.149
 pse-0.146
 Rollins-0.145
Tokence
Token ID344
Feature activation-3.03e-01

Pos logit contributions
 leaflets+2.172
 Masquerade+2.066
senal+2.057
 Rollins+2.035
 Dent+2.025
Neg logit contributions
uble-1.411
outer-1.371
oro-1.312
oster-1.224
olphins-1.222
Tokenwen
Token ID21006
Feature activation+3.04e-01

Pos logit contributions
 leaflets+1.215
senal+1.154
 Masquerade+1.150
 pse+1.130
 Rollins+1.120
Neg logit contributions
uble-0.965
outer-0.953
oro-0.913
oster-0.863
TEXTURE-0.849
Token (
Token ID357
Feature activation+1.03e-01

Pos logit contributions
uble+1.093
outer+1.079
oro+1.046
oster+1.002
olphins+0.965
Neg logit contributions
 leaflets-1.115
senal-1.067
 Masquerade-1.034
 pse-1.012
cffff-1.001
TokenGreen
Token ID13719
Feature activation-1.33e-01

Pos logit contributions
uble+0.318
outer+0.317
oro+0.305
oster+0.286
TEXTURE+0.281
Neg logit contributions
 leaflets-0.422
senal-0.406
 Masquerade-0.398
 pse-0.397
 Rollins-0.385
TokenEdge
Token ID37021
Feature activation-4.17e-01

Pos logit contributions
 leaflets+0.591
senal+0.569
 Masquerade+0.563
 pse+0.556
 Rollins+0.548
Neg logit contributions
uble-0.366
outer-0.361
oro-0.344
oster-0.322
olphins-0.313
Token upsetting
Token ID38423
Feature activation+1.11e-01

Pos logit contributions
uble+0.380
outer+0.376
oro+0.363
oster+0.348
TEXTURE+0.338
Neg logit contributions
 leaflets-0.365
senal-0.351
 Masquerade-0.345
 pse-0.338
 Rollins-0.333
Token.
Token ID764
Feature activation-4.88e-02

Pos logit contributions
uble+0.385
outer+0.379
oro+0.367
oster+0.352
olphins+0.340
Neg logit contributions
 leaflets-0.414
senal-0.399
 Masquerade-0.393
 pse-0.386
 Rollins-0.380
Token.
Token ID764
Feature activation-1.79e-01

Pos logit contributions
 leaflets+0.179
senal+0.170
 Masquerade+0.168
 pse+0.166
 Rollins+0.163
Neg logit contributions
uble-0.173
outer-0.171
oro-0.165
oster-0.157
olphins-0.154
Token.
Token ID764
Feature activation-3.42e-01

Pos logit contributions
 leaflets+0.629
senal+0.593
 Masquerade+0.590
 pse+0.581
 Rollins+0.571
Neg logit contributions
uble-0.660
outer-0.653
oro-0.627
oster-0.599
olphins-0.592
Token the
Token ID262
Feature activation-3.73e-01

Pos logit contributions
 leaflets+1.197
senal+1.132
 Masquerade+1.124
 pse+1.103
 Rollins+1.086
Neg logit contributions
uble-1.268
outer-1.254
oro-1.210
oster-1.155
olphins-1.133
Token bottom
Token ID4220
Feature activation-1.16e+00

Pos logit contributions
 leaflets+1.270
senal+1.217
 Masquerade+1.197
 pse+1.173
 Rollins+1.153
Neg logit contributions
uble-1.414
outer-1.402
oro-1.353
oster-1.295
olphins-1.267
Token line
Token ID1627
Feature activation-3.08e-01

Pos logit contributions
 leaflets+4.627
 Masquerade+4.335
 pse+4.276
 Rollins+4.276
 Dent+4.265
Neg logit contributions
uble-3.624
outer-3.598
oro-3.426
TEXTURE-3.260
olphins-3.221
Token is
Token ID318
Feature activation-3.91e-02

Pos logit contributions
 leaflets+1.252
senal+1.183
 Masquerade+1.181
 pse+1.162
 Rollins+1.152
Neg logit contributions
uble-0.973
outer-0.959
oro-0.919
oster-0.867
olphins-0.853
Token the
Token ID262
Feature activation+1.75e-01

Pos logit contributions
 leaflets+0.132
senal+0.127
 Masquerade+0.125
 pse+0.122
 Rollins+0.120
Neg logit contributions
uble-0.149
outer-0.147
oro-0.142
oster-0.136
TEXTURE-0.133
Token comments
Token ID3651
Feature activation+2.47e-01

Pos logit contributions
uble+0.669
outer+0.666
oro+0.645
oster+0.619
TEXTURE+0.605
Neg logit contributions
senal-0.574
 leaflets-0.567
 Masquerade-0.542
 pse-0.533
cffff-0.532
Token are
Token ID389
Feature activation-8.69e-02

Pos logit contributions
uble+0.854
outer+0.843
oro+0.822
oster+0.783
TEXTURE+0.761
Neg logit contributions
 leaflets-0.902
senal-0.899
 Masquerade-0.858
 pse-0.844
cffff-0.842
Token minimized
Token ID49491
Feature activation-3.61e-01

Pos logit contributions
 leaflets+0.362
senal+0.340
 Masquerade+0.336
 pse+0.328
 Rollins+0.322
Neg logit contributions
uble-0.511
outer-0.506
oro-0.491
oster-0.471
olphins-0.463
Token.
Token ID13
Feature activation-2.06e-01

Pos logit contributions
 leaflets+1.287
 Masquerade+1.198
senal+1.194
 pse+1.178
 Rollins+1.166
Neg logit contributions
uble-1.321
outer-1.306
oro-1.261
oster-1.199
olphins-1.182
Token
Token ID198
Feature activation-2.12e-01

Pos logit contributions
 leaflets+0.812
senal+0.772
 Masquerade+0.769
 pse+0.755
 Rollins+0.746
Neg logit contributions
uble-0.671
outer-0.662
oro-0.636
oster-0.602
olphins-0.590
Token
Token ID198
Feature activation-1.31e-01

Pos logit contributions
 leaflets+0.824
 Masquerade+0.779
 Rollins+0.760
 Dent+0.757
als+0.745
Neg logit contributions
uble-0.703
outer-0.692
oro-0.665
oster-0.629
olphins-0.621
TokenTwitter
Token ID14254
Feature activation-7.30e-01

Pos logit contributions
 leaflets+0.509
senal+0.484
 Masquerade+0.481
 pse+0.473
 Rollins+0.467
Neg logit contributions
uble-0.434
outer-0.428
oro-0.412
oster-0.391
olphins-0.382
Token:
Token ID25
Feature activation-1.36e+00

Pos logit contributions
 leaflets+2.386
 Masquerade+2.229
senal+2.224
 pse+2.179
 Rollins+2.151
Neg logit contributions
uble-2.871
outer-2.844
oro-2.742
oster-2.628
olphins-2.593
Token @
Token ID2488
Feature activation-2.10e-01

Pos logit contributions
 leaflets+4.501
 Masquerade+4.144
 pse+4.129
 Dent+4.110
 Rollins+4.083
Neg logit contributions
uble-5.156
outer-5.025
oro-4.874
TEXTURE-4.673
oster-4.669
Tokenbrand
Token ID17938
Feature activation-1.54e-02

Pos logit contributions
 leaflets+0.856
senal+0.817
 Masquerade+0.811
 pse+0.798
 Rollins+0.788
Neg logit contributions
uble-0.664
outer-0.657
oro-0.629
oster-0.595
olphins-0.580
Tokent
Token ID83
Feature activation-4.07e-01

Pos logit contributions
 leaflets+0.062
senal+0.059
 Masquerade+0.059
 pse+0.058
 Rollins+0.057
Neg logit contributions
uble-0.049
outer-0.048
oro-0.046
oster-0.044
olphins-0.043
Tokenst
Token ID301
Feature activation+2.55e-01

Pos logit contributions
 leaflets+1.662
senal+1.573
 Masquerade+1.565
 pse+1.552
 Rollins+1.535
Neg logit contributions
uble-1.250
outer-1.229
oro-1.176
oster-1.109
TEXTURE-1.103
Tokenrib
Token ID822
Feature activation+1.98e-01

Pos logit contributions
uble+0.829
outer+0.819
oro+0.790
oster+0.745
olphins+0.727
Neg logit contributions
 leaflets-1.019
senal-0.976
 Masquerade-0.966
 pse-0.952
 Rollins-0.934
Token G
Token ID402
Feature activation-5.24e-01

Pos logit contributions
 leaflets+0.761
senal+0.719
 Masquerade+0.712
 pse+0.698
 Rollins+0.686
Neg logit contributions
uble-0.898
outer-0.889
oro-0.859
oster-0.823
olphins-0.808
TokenQ
Token ID48
Feature activation-8.60e-01

Pos logit contributions
 leaflets+1.889
senal+1.769
 Masquerade+1.767
 pse+1.726
 Rollins+1.719
Neg logit contributions
uble-1.886
outer-1.855
oro-1.777
oster-1.706
TEXTURE-1.682
Token (
Token ID357
Feature activation-2.02e-01

Pos logit contributions
 leaflets+2.667
 Masquerade+2.502
senal+2.466
 pse+2.418
 Dent+2.403
Neg logit contributions
uble-3.511
outer-3.450
oro-3.342
oster-3.195
TEXTURE-3.189
Tokenread
Token ID961
Feature activation-4.12e-01

Pos logit contributions
 leaflets+0.823
senal+0.784
 Masquerade+0.781
 pse+0.767
 Rollins+0.758
Neg logit contributions
uble-0.633
outer-0.622
oro-0.597
oster-0.565
olphins-0.554
Token the
Token ID262
Feature activation-7.83e-01

Pos logit contributions
 leaflets+1.375
senal+1.293
 Masquerade+1.287
 pse+1.262
 Rollins+1.243
Neg logit contributions
uble-1.594
outer-1.575
oro-1.524
oster-1.457
TEXTURE-1.432
Token full
Token ID1336
Feature activation-1.32e+00

Pos logit contributions
 leaflets+2.473
 Masquerade+2.298
senal+2.275
 pse+2.249
 Rollins+2.206
Neg logit contributions
uble-3.182
outer-3.120
oro-3.042
oster-2.913
olphins-2.875
Token profile
Token ID7034
Feature activation-2.91e-01

Pos logit contributions
 leaflets+3.954
 Masquerade+3.644
 pse+3.545
 Dent+3.494
senal+3.473
Neg logit contributions
uble-5.548
outer-5.346
oro-5.265
oster-5.057
TEXTURE-5.023
Token here
Token ID994
Feature activation-7.98e-01

Pos logit contributions
 leaflets+1.198
senal+1.143
 Masquerade+1.136
 pse+1.118
 Rollins+1.104
Neg logit contributions
uble-0.903
outer-0.891
oro-0.854
oster-0.807
olphins-0.788
Token).
Token ID737
Feature activation-8.49e-02

Pos logit contributions
 leaflets+2.711
senal+2.523
 Masquerade+2.519
 pse+2.480
 Rollins+2.450
Neg logit contributions
uble-3.005
outer-2.976
oro-2.869
oster-2.742
TEXTURE-2.706
Token Talking
Token ID33445
Feature activation+1.74e-01

Pos logit contributions
 leaflets+0.325
senal+0.311
 Masquerade+0.305
 pse+0.304
 Rollins+0.295
Neg logit contributions
uble-0.287
outer-0.283
oro-0.273
oster-0.260
olphins-0.254
Token Points
Token ID11045
Feature activation-3.01e-01

Pos logit contributions
uble+0.671
outer+0.662
oro+0.641
oster+0.613
olphins+0.603
Neg logit contributions
 leaflets-0.585
senal-0.552
 Masquerade-0.547
 pse-0.538
 Rollins-0.528
Tokening
Token ID278
Feature activation+6.77e-02

Pos logit contributions
 leaflets+1.638
senal+1.538
 Masquerade+1.532
 pse+1.504
 Rollins+1.480
Neg logit contributions
uble-1.731
outer-1.716
oro-1.649
oster-1.578
TEXTURE-1.551
Token to
Token ID284
Feature activation-1.51e-01

Pos logit contributions
uble+0.222
outer+0.219
oro+0.211
oster+0.200
olphins+0.195
Neg logit contributions
 leaflets-0.265
senal-0.254
 Masquerade-0.251
 pse-0.247
 Rollins-0.244
Token other
Token ID584
Feature activation+1.69e-01

Pos logit contributions
 leaflets+0.496
senal+0.472
 Masquerade+0.464
 pse+0.456
 Rollins+0.447
Neg logit contributions
uble-0.588
outer-0.583
oro-0.563
oster-0.539
olphins-0.529
Token browsers
Token ID22616
Feature activation-4.54e-01

Pos logit contributions
uble+0.483
outer+0.477
oro+0.457
oster+0.428
olphins+0.418
Neg logit contributions
 leaflets-0.728
senal-0.712
 Masquerade-0.695
 pse-0.685
 Rollins-0.678
Token,
Token ID11
Feature activation+1.82e-02

Pos logit contributions
 leaflets+1.721
 Masquerade+1.618
senal+1.598
 pse+1.589
 Rollins+1.574
Neg logit contributions
uble-1.558
outer-1.539
oro-1.478
oster-1.409
TEXTURE-1.392
Token Mozilla
Token ID29258
Feature activation-1.24e+00

Pos logit contributions
uble+0.066
outer+0.066
oro+0.064
oster+0.060
olphins+0.059
Neg logit contributions
 leaflets-0.064
senal-0.062
 Masquerade-0.060
 pse-0.059
 Rollins-0.058
Token has
Token ID468
Feature activation-4.96e-01

Pos logit contributions
 leaflets+3.724
 Masquerade+3.501
 pse+3.403
senal+3.358
 Rollins+3.346
Neg logit contributions
uble-5.087
outer-5.045
oro-4.844
oster-4.644
olphins-4.638
Token said
Token ID531
Feature activation-3.62e-01

Pos logit contributions
 leaflets+1.532
 Masquerade+1.425
senal+1.414
 pse+1.393
 Rollins+1.374
Neg logit contributions
uble-2.047
outer-2.026
oro-1.962
oster-1.876
olphins-1.860
Token.
Token ID13
Feature activation+7.18e-02

Pos logit contributions
 leaflets+1.515
 Masquerade+1.437
senal+1.429
 pse+1.412
 Rollins+1.397
Neg logit contributions
uble-1.091
outer-1.081
oro-1.032
oster-0.971
olphins-0.955
Token
Token ID198
Feature activation+5.01e-02

Pos logit contributions
uble+0.235
outer+0.233
oro+0.224
oster+0.212
olphins+0.208
Neg logit contributions
 leaflets-0.283
senal-0.272
 pse-0.265
 Masquerade-0.264
cffff-0.257
Token
Token ID198
Feature activation+8.13e-02

Pos logit contributions
uble+0.161
outer+0.159
oro+0.152
oster+0.144
olphins+0.142
Neg logit contributions
 leaflets-0.200
 Masquerade-0.189
senal-0.185
 Rollins-0.184
 pse-0.183
Token it
Token ID340
Feature activation+5.31e-02

Pos logit contributions
 leaflets+0.743
senal+0.699
 Masquerade+0.698
 pse+0.685
 Rollins+0.674
Neg logit contributions
uble-0.798
outer-0.789
oro-0.761
oster-0.727
olphins-0.715
Token is
Token ID318
Feature activation-4.46e-01

Pos logit contributions
uble+0.169
outer+0.167
oro+0.160
oster+0.151
olphins+0.148
Neg logit contributions
 leaflets-0.214
senal-0.205
 Masquerade-0.203
 pse-0.199
 Rollins-0.197
Token).
Token ID737
Feature activation+2.58e-01

Pos logit contributions
 leaflets+1.515
senal+1.417
 Masquerade+1.416
 pse+1.394
 Rollins+1.368
Neg logit contributions
uble-1.695
outer-1.677
oro-1.619
oster-1.550
olphins-1.523
Token
Token ID198
Feature activation-1.01e-01

Pos logit contributions
uble+0.821
outer+0.815
oro+0.788
oster+0.741
olphins+0.722
Neg logit contributions
 leaflets-1.032
senal-1.001
 Masquerade-0.968
 pse-0.951
 Rollins-0.940
Token
Token ID198
Feature activation-1.71e-01

Pos logit contributions
 leaflets+0.398
 Masquerade+0.377
 Rollins+0.367
 Dent+0.366
 pse+0.364
Neg logit contributions
uble-0.329
outer-0.325
oro-0.312
oster-0.295
olphins-0.291
Tokensudo
Token ID24032
Feature activation-1.29e+00

Pos logit contributions
 leaflets+0.602
senal+0.571
 Masquerade+0.564
 pse+0.553
 Rollins+0.545
Neg logit contributions
uble-0.632
outer-0.626
oro-0.603
oster-0.575
olphins-0.564
Token system
Token ID1080
Feature activation-1.60e-02

Pos logit contributions
 leaflets+4.376
 Masquerade+4.109
 pse+4.078
senal+4.010
 Dent+3.939
Neg logit contributions
uble-4.838
outer-4.804
oro-4.619
oster-4.433
TEXTURE-4.359
Tokenctl
Token ID34168
Feature activation-5.21e-01

Pos logit contributions
 leaflets+0.082
senal+0.081
 Masquerade+0.079
 pse+0.078
 Dent+0.077
Neg logit contributions
outer-0.032
uble-0.032
oro-0.030
oster-0.028
=~-0.027
Token restart
Token ID15765
Feature activation-7.32e-01

Pos logit contributions
 leaflets+1.728
senal+1.652
 Masquerade+1.622
 pse+1.587
 Rollins+1.557
Neg logit contributions
uble-2.026
outer-2.012
oro-1.939
oster-1.860
olphins-1.819
Token network
Token ID3127
Feature activation+1.63e-01

Pos logit contributions
 leaflets+2.594
 Masquerade+2.434
senal+2.418
 pse+2.402
 Rollins+2.350
Neg logit contributions
uble-2.645
outer-2.617
oro-2.527
oster-2.416
TEXTURE-2.388
Token-
Token ID12
Feature activation-3.83e-01

Pos logit contributions
uble+0.596
outer+0.593
oro+0.571
oster+0.545
olphins+0.531
Neg logit contributions
 leaflets-0.580
senal-0.550
 Masquerade-0.544
 pse-0.532
 Dent-0.526