TOP ACTIVATIONS
MAX = 3.254

social justice math ." ( Fre ire was a Brazilian leftist
a referendum supported by all Sloven ian political parties was held
injured Robert Kub ica at Renault after setting the fastest time
to its power train , dri vel ine , traction control
probe test ( tri ple diss ociation | , ( D
services that have traditionally been fre ew he eling forums where
back , winger and first couple of attackers to hold defensive
Par th iv I have fre tted over whether it could
this maj est ical roof fre tted with golden fire ,
low point he drilled 17 dry holes in a row .
Let us remember that the Sloven ian government declared independence in
spect ral response at higher sensit ivities though , which is
a building is constructed . Dri ven by utility , aesthetic
maybe , we should be incentiv izing them to solve them
,' said Jack . ' Sex has never entered my mind
what we can say , see or hear ? Who decides
starch ( which is ground dehyd rated k uz u root
Baldwin 2008 Steve Care ll 2008 Lee
back burner , I was freed up to focus on authentic
Ob amas announced they were cur t ailing ( ban ning

MIN ACTIVATIONS
MIN = -3.237

Manga Award in the Sh ō jo category .[ 16 ]
i emo ko Kal an ial i
You know how Batman is Bruce Wayne ? And that he
he summed up Z t oh oven s larger
ρ π α γ ς (
me ke k ah uk ahu i ka pil ina
Split release with Yam Yam Records 1 .
costs is built upon a widely used methodology introduced in 2010
not signing the mailed out ballot questionnaire at the bottom in
Score esports . You can follow him on Twitter . <|endoftext|>
, which means
due to the 2011 T oh oku Earthquake , and went
last year s ballot initiative that would have made
biological or chemical weapons by Osama bin Laden and Saddam Hussein
ET who have a long standing heritage as a recogn isable
band is led by P oh j ola on piano ,
charge . These " B aghd ad batteries " may have
by the vulnerability of his prog eny , that he began
Hall Collection , replacing Confederate General Edmund Kirby Smith .[ 7

INTERVAL 1.632 - 3.254
CONTAINS 0.428%

AL EM Israeli and Turkish officials have reached a preliminary
. The Blessed Trinity . Creation . The Angels . The
simple tasks that should be handled in a few seconds with
Let us remember that the Sloven ian government declared independence in
Us , Matt el and Ner f . Some of these

INTERVAL 0.009 - 1.632
CONTAINS 49.689%

of the UEFA Championships qualifying tournament in October .
day . What does this mean ? A lot
that can help rejuven ate both the local economy and the
- data units , made modifications to improve the detection of
is possible to live only as long as life intox icates

INTERVAL -1.614 - 0.009
CONTAINS 49.424%

relatively low , but nonetheless a problem . The education sector
the use of an annotation automatically added to all of their
aboard in 2006 once again , in a time of
. B illed as an effort that inv igor
. Her early poems were all elbows and knees

INTERVAL -3.237 - -1.614
CONTAINS 0.460%

political sm earing of a wholly benevolent foundation , due only
bit co int alk . org / index . php ?
appeal to children and can stand the test of time .
$ ($ w path )" break } } else { $
, also known as R ang oon , says MS F
Tokensocial
Token ID14557
Feature activation+2.47e-01

Pos logit contributions
nesday+3.314
mble+3.307
pher+3.008
cream+2.774
displayText+2.607
Neg logit contributions
 Tik-2.774
 viral-2.772
 stride-2.719
 Kik-2.584
 characteristic-2.546
Token justice
Token ID5316
Feature activation-4.54e-01

Pos logit contributions
nesday+1.040
mble+1.031
pher+0.933
cream+0.851
displayText+0.815
Neg logit contributions
 viral-0.799
 Tik-0.798
 stride-0.775
 Kik-0.748
uni-0.733
Token math
Token ID10688
Feature activation+1.25e+00

Pos logit contributions
 viral+1.265
 Tik+1.259
 stride+1.216
 Kik+1.154
 characteristic+1.141
Neg logit contributions
nesday-2.141
mble-2.129
pher-1.929
cream-1.785
displayText-1.731
Token."
Token ID526
Feature activation+4.84e-01

Pos logit contributions
mble+5.696
nesday+5.656
pher+5.175
cream+4.818
displayText+4.522
Neg logit contributions
 Tik-3.433
 viral-3.403
 stride-3.341
 Kik-3.206
uni-3.129
Token (
Token ID357
Feature activation+1.24e+00

Pos logit contributions
nesday+2.164
mble+2.149
pher+1.979
cream+1.819
displayText+1.745
Neg logit contributions
 viral-1.420
 Tik-1.386
 stride-1.384
 characteristic-1.298
 Kik-1.281
TokenFre
Token ID20366
Feature activation+3.25e+00

Pos logit contributions
mble+4.336
nesday+4.290
pher+3.921
cream+3.560
displayText+3.351
Neg logit contributions
 viral-4.761
 Tik-4.714
 stride-4.651
 Kik-4.414
 characteristic-4.403
Tokenire
Token ID557
Feature activation+3.78e-01

Pos logit contributions
nesday+11.052
mble+11.021
pher+9.906
cream+8.536
pel+8.250
Neg logit contributions
 Tik-11.262
 viral-10.946
 Kik-10.640
 stride-10.566
 squid-10.350
Token was
Token ID373
Feature activation+8.50e-01

Pos logit contributions
nesday+1.799
mble+1.788
pher+1.636
cream+1.509
displayText+1.453
Neg logit contributions
 viral-1.019
 Tik-1.016
 stride-0.987
 Kik-0.931
 characteristic-0.917
Token a
Token ID257
Feature activation+2.83e-01

Pos logit contributions
nesday+3.800
mble+3.763
pher+3.460
cream+3.163
displayText+3.061
Neg logit contributions
 Tik-2.445
 viral-2.431
 stride-2.370
 Kik-2.246
uni-2.227
Token Brazilian
Token ID17036
Feature activation+5.23e-01

Pos logit contributions
nesday+1.394
mble+1.388
pher+1.275
cream+1.185
displayText+1.139
Neg logit contributions
 Tik-0.696
 viral-0.683
 stride-0.673
 Kik-0.631
uni-0.624
Token leftist
Token ID28318
Feature activation+1.18e-01

Pos logit contributions
nesday+2.495
mble+2.479
pher+2.292
cream+2.127
displayText+2.026
Neg logit contributions
 Tik-1.338
 viral-1.323
 stride-1.296
 Kik-1.219
uni-1.209
Token a
Token ID257
Feature activation-7.56e-02

Pos logit contributions
 viral+1.325
 Tik+1.319
 stride+1.276
 Kik+1.209
 characteristic+1.188
Neg logit contributions
nesday-2.373
mble-2.363
pher-2.150
cream-1.992
displayText-1.924
Token referendum
Token ID11467
Feature activation-1.22e+00

Pos logit contributions
 Tik+0.192
 viral+0.191
 stride+0.184
 Kik+0.174
uni+0.172
Neg logit contributions
nesday-0.372
mble-0.371
pher-0.337
cream-0.314
displayText-0.303
Token supported
Token ID4855
Feature activation-1.53e-01

Pos logit contributions
 viral+3.106
 Tik+3.064
 stride+2.980
 characteristic+2.828
 Kik+2.824
Neg logit contributions
mble-5.948
nesday-5.933
pher-5.323
cream-5.022
displayText-4.854
Token by
Token ID416
Feature activation+3.65e-01

Pos logit contributions
 viral+0.444
 Tik+0.441
 stride+0.429
 Kik+0.407
 characteristic+0.401
Neg logit contributions
nesday-0.702
mble-0.698
pher-0.632
cream-0.583
displayText-0.563
Token all
Token ID477
Feature activation-1.58e-03

Pos logit contributions
mble+1.727
nesday+1.721
pher+1.568
cream+1.460
displayText+1.380
Neg logit contributions
 viral-0.963
 Tik-0.955
 stride-0.931
uni-0.875
 Kik-0.874
Token Sloven
Token ID30694
Feature activation+3.06e+00

Pos logit contributions
 Tik+0.004
 viral+0.004
 stride+0.004
 Kik+0.004
uni+0.004
Neg logit contributions
mble-0.007
nesday-0.007
pher-0.007
cream-0.006
displayText-0.006
Tokenian
Token ID666
Feature activation+9.46e-01

Pos logit contributions
nesday+8.486
mble+8.202
pher+7.689
cream+6.491
bourg+5.925
Neg logit contributions
 viral-11.963
 Tik-11.803
 stride-11.566
 Kik-11.313
 squid-11.119
Token political
Token ID1964
Feature activation+9.14e-01

Pos logit contributions
mble+4.278
nesday+4.249
pher+3.942
cream+3.629
displayText+3.459
Neg logit contributions
 Tik-2.560
 viral-2.560
 stride-2.493
 Kik-2.359
uni-2.346
Token parties
Token ID4671
Feature activation+5.29e-03

Pos logit contributions
mble+3.445
nesday+3.407
pher+3.095
cream+2.824
displayText+2.624
Neg logit contributions
 Tik-3.241
 viral-3.214
 stride-3.136
 Kik-3.004
uni-2.981
Token was
Token ID373
Feature activation+6.47e-01

Pos logit contributions
nesday+0.025
mble+0.025
pher+0.023
cream+0.021
displayText+0.020
Neg logit contributions
 viral-0.015
 Tik-0.015
 stride-0.014
 Kik-0.013
 characteristic-0.013
Token held
Token ID2714
Feature activation+5.66e-02

Pos logit contributions
nesday+3.197
mble+3.162
pher+2.922
cream+2.695
displayText+2.619
Neg logit contributions
 Tik-1.609
 viral-1.603
 stride-1.547
 Kik-1.470
uni-1.442
Token injured
Token ID6686
Feature activation-1.91e-01

Pos logit contributions
nesday+1.769
mble+1.751
pher+1.603
cream+1.475
displayText+1.408
Neg logit contributions
 Tik-1.110
 viral-1.098
 stride-1.071
 Kik-1.016
uni-1.012
Token Robert
Token ID5199
Feature activation+1.66e+00

Pos logit contributions
 viral+0.611
 Tik+0.609
 stride+0.591
 Kik+0.565
 characteristic+0.559
Neg logit contributions
nesday-0.817
mble-0.812
pher-0.731
cream-0.670
displayText-0.641
Token Kub
Token ID24921
Feature activation+9.56e-01

Pos logit contributions
nesday+7.151
mble+6.915
pher+6.447
cream+5.997
bourg+5.615
Neg logit contributions
 viral-4.794
 stride-4.674
 Tik-4.508
 characteristic-4.398
 sighting-4.235
Tokenica
Token ID3970
Feature activation+4.81e-01

Pos logit contributions
nesday+3.407
mble+3.402
pher+3.017
cream+2.669
displayText+2.489
Neg logit contributions
 viral-3.645
 Tik-3.634
 stride-3.525
 Kik-3.458
 Gujar-3.386
Token at
Token ID379
Feature activation+1.55e-01

Pos logit contributions
nesday+2.310
mble+2.281
pher+2.117
cream+1.951
displayText+1.874
Neg logit contributions
 viral-1.236
 Tik-1.235
 stride-1.184
 Kik-1.133
uni-1.122
Token Renault
Token ID44083
Feature activation+3.04e+00

Pos logit contributions
nesday+0.737
mble+0.732
pher+0.670
cream+0.615
displayText+0.595
Neg logit contributions
 viral-0.413
 Tik-0.411
 stride-0.396
 Kik-0.376
uni-0.375
Token after
Token ID706
Feature activation+7.18e-01

Pos logit contributions
nesday+12.286
mble+12.014
pher+11.381
cream+10.405
onica+9.858
Neg logit contributions
 Tik-8.383
 viral-8.183
 stride-8.052
uni-7.607
 Gujar-7.443
Token setting
Token ID4634
Feature activation+7.27e-01

Pos logit contributions
nesday+3.256
mble+3.196
pher+2.934
cream+2.669
displayText+2.552
Neg logit contributions
 Tik-2.044
 viral-2.032
 stride-1.975
uni-1.908
 Kik-1.872
Token the
Token ID262
Feature activation+1.03e+00

Pos logit contributions
nesday+3.165
mble+3.141
pher+2.843
cream+2.587
displayText+2.443
Neg logit contributions
 Tik-2.214
 viral-2.183
 stride-2.092
 Kik-2.043
uni-2.036
Token fastest
Token ID14162
Feature activation+5.23e-01

Pos logit contributions
mble+4.796
nesday+4.782
pher+4.359
cream+3.990
displayText+3.798
Neg logit contributions
 Tik-2.739
 viral-2.671
 stride-2.567
uni-2.475
 Kik-2.474
Token time
Token ID640
Feature activation+2.05e-01

Pos logit contributions
nesday+2.623
mble+2.612
pher+2.407
cream+2.224
displayText+2.121
Neg logit contributions
 Tik-1.230
 viral-1.204
 stride-1.133
 Kik-1.110
uni-1.105
Token to
Token ID284
Feature activation+1.76e-01

Pos logit contributions
 viral+0.307
 Tik+0.306
 stride+0.296
 Kik+0.282
 characteristic+0.275
Neg logit contributions
nesday-0.531
mble-0.528
pher-0.483
cream-0.446
displayText-0.430
Token its
Token ID663
Feature activation-9.63e-01

Pos logit contributions
nesday+0.803
mble+0.800
pher+0.731
cream+0.670
displayText+0.643
Neg logit contributions
 viral-0.505
 Tik-0.505
 stride-0.485
 Kik-0.465
 characteristic-0.455
Token power
Token ID1176
Feature activation-1.33e+00

Pos logit contributions
 viral+2.539
 Tik+2.527
 stride+2.461
 characteristic+2.321
 Kik+2.303
Neg logit contributions
nesday-4.717
mble-4.653
pher-4.205
cream-3.933
displayText-3.831
Tokentrain
Token ID27432
Feature activation-9.26e-01

Pos logit contributions
 viral+3.750
 Tik+3.733
 stride+3.668
 characteristic+3.491
 Kik+3.414
Neg logit contributions
nesday-6.244
mble-6.115
pher-5.509
cream-5.108
displayText-4.984
Token,
Token ID11
Feature activation-3.76e-01

Pos logit contributions
 viral+2.397
 Tik+2.383
 stride+2.308
 characteristic+2.192
 Kik+2.176
Neg logit contributions
nesday-4.578
mble-4.520
pher-4.077
cream-3.814
displayText-3.730
Token dri
Token ID1454
Feature activation+3.02e+00

Pos logit contributions
 viral+1.037
 Tik+1.033
 stride+0.999
 Kik+0.949
 characteristic+0.935
Neg logit contributions
nesday-1.778
mble-1.768
pher-1.605
cream-1.486
displayText-1.438
Tokenvel
Token ID626
Feature activation+5.80e-01

Pos logit contributions
mble+10.213
nesday+9.840
pher+9.284
cream+8.045
ationally+7.502
Neg logit contributions
 Tik-10.713
 viral-10.575
 stride-10.226
 Kik-10.128
 Hawai-9.959
Tokenine
Token ID500
Feature activation-3.52e-01

Pos logit contributions
nesday+2.454
mble+2.440
pher+2.202
cream+2.012
displayText+1.918
Neg logit contributions
 viral-1.889
 Tik-1.882
 stride-1.790
 Kik-1.749
 characteristic-1.719
Token,
Token ID11
Feature activation-1.28e-01

Pos logit contributions
 viral+0.864
 Tik+0.860
 stride+0.829
 Kik+0.782
 characteristic+0.769
Neg logit contributions
nesday-1.777
mble-1.766
pher-1.614
cream-1.502
displayText-1.458
Token traction
Token ID23692
Feature activation+4.66e-01

Pos logit contributions
 Tik+0.347
 viral+0.346
 stride+0.333
 Kik+0.319
uni+0.313
Neg logit contributions
mble-0.602
nesday-0.601
pher-0.550
cream-0.505
displayText-0.488
Token control
Token ID1630
Feature activation+5.49e-01

Pos logit contributions
mble+2.181
nesday+2.164
pher+2.001
cream+1.833
displayText+1.769
Neg logit contributions
 Tik-1.278
 viral-1.274
 stride-1.216
 Kik-1.168
uni-1.155
Token probe
Token ID12774
Feature activation+3.05e-01

Pos logit contributions
mble+3.034
nesday+3.001
pher+2.770
cream+2.537
displayText+2.477
Neg logit contributions
 Tik-1.610
 viral-1.581
 stride-1.521
 Kik-1.458
uni-1.443
Token test
Token ID1332
Feature activation+5.53e-02

Pos logit contributions
mble+1.442
nesday+1.436
pher+1.313
cream+1.209
displayText+1.170
Neg logit contributions
 Tik-0.818
 viral-0.808
 stride-0.774
 Kik-0.747
uni-0.737
Token (
Token ID357
Feature activation+1.17e+00

Pos logit contributions
mble+0.267
nesday+0.267
pher+0.242
cream+0.224
displayText+0.217
Neg logit contributions
 Tik-0.145
 viral-0.145
 stride-0.139
 Kik-0.133
uni-0.130
Tokentri
Token ID28461
Feature activation-6.28e-01

Pos logit contributions
nesday+4.835
mble+4.831
pher+4.387
cream+4.060
displayText+3.869
Neg logit contributions
 Tik-3.750
 viral-3.708
 stride-3.604
 Kik-3.421
 squid-3.366
Tokenple
Token ID1154
Feature activation-6.50e-01

Pos logit contributions
 viral+2.763
 Tik+2.755
 stride+2.706
 Kik+2.610
uni+2.598
Neg logit contributions
nesday-1.915
mble-1.898
pher-1.625
cream-1.439
displayText-1.375
Token diss
Token ID6249
Feature activation+3.01e+00

Pos logit contributions
 viral+1.675
 Tik+1.657
 stride+1.614
 Kik+1.518
 characteristic+1.497
Neg logit contributions
nesday-3.202
mble-3.178
pher-2.904
cream-2.693
displayText-2.623
Tokenociation
Token ID41003
Feature activation+3.34e-01

Pos logit contributions
nesday+10.613
mble+10.340
pher+9.502
cream+8.430
pel+7.921
Neg logit contributions
 Tik-10.092
 viral-9.639
 stride-9.346
 squid-9.114
uni-9.100
Token|
Token ID91
Feature activation+3.82e-01

Pos logit contributions
mble+1.560
nesday+1.559
pher+1.422
cream+1.306
displayText+1.259
Neg logit contributions
 Tik-0.922
 viral-0.908
 stride-0.873
 Kik-0.840
uni-0.837
Token,
Token ID11
Feature activation-1.77e-01

Pos logit contributions
nesday+1.613
mble+1.611
pher+1.458
cream+1.345
displayText+1.280
Neg logit contributions
 Tik-1.234
 viral-1.223
 stride-1.186
 Kik-1.140
 characteristic-1.116
Token (
Token ID357
Feature activation+7.18e-01

Pos logit contributions
 viral+0.475
 Tik+0.474
 stride+0.457
 Kik+0.434
 characteristic+0.426
Neg logit contributions
nesday-0.847
mble-0.843
pher-0.768
cream-0.711
displayText-0.688
TokenD
Token ID35
Feature activation+8.88e-01

Pos logit contributions
nesday+2.964
mble+2.963
pher+2.668
cream+2.475
displayText+2.346
Neg logit contributions
 Tik-2.377
 viral-2.353
 stride-2.289
 Kik-2.195
 characteristic-2.156
Token services
Token ID2594
Feature activation+2.42e-02

Pos logit contributions
nesday+2.251
mble+2.219
pher+2.062
cream+1.904
displayText+1.800
Neg logit contributions
 Tik-1.234
 viral-1.191
 stride-1.181
uni-1.120
 Kik-1.103
Token that
Token ID326
Feature activation-5.06e-01

Pos logit contributions
nesday+0.112
mble+0.111
pher+0.102
cream+0.094
displayText+0.090
Neg logit contributions
 Tik-0.068
 viral-0.067
 stride-0.066
 Kik-0.062
uni-0.061
Token have
Token ID423
Feature activation-2.43e-02

Pos logit contributions
 viral+1.414
 Tik+1.405
 stride+1.361
 Kik+1.294
 characteristic+1.275
Neg logit contributions
nesday-2.380
mble-2.371
pher-2.141
cream-1.987
displayText-1.924
Token traditionally
Token ID16083
Feature activation-8.67e-01

Pos logit contributions
 viral+0.073
 Tik+0.073
 stride+0.071
 Kik+0.068
 characteristic+0.067
Neg logit contributions
nesday-0.108
mble-0.107
pher-0.097
cream-0.089
displayText-0.086
Token been
Token ID587
Feature activation-3.29e-02

Pos logit contributions
 viral+2.648
 Tik+2.600
 stride+2.547
 characteristic+2.418
 Kik+2.399
Neg logit contributions
nesday-3.892
mble-3.888
pher-3.388
cream-3.195
displayText-3.104
Token fre
Token ID2030
Feature activation+2.98e+00

Pos logit contributions
 viral+0.084
 Tik+0.084
 stride+0.081
 Kik+0.076
 characteristic+0.075
Neg logit contributions
nesday-0.162
mble-0.161
pher-0.147
cream-0.137
displayText-0.132
Tokenew
Token ID413
Feature activation+5.77e-01

Pos logit contributions
nesday+9.380
mble+8.955
pher+8.858
cream+7.547
ationally+7.237
Neg logit contributions
 viral-11.006
 stride-10.828
 Tik-10.792
 sighting-10.718
 characteristic-10.510
Tokenhe
Token ID258
Feature activation-3.61e-01

Pos logit contributions
nesday+2.129
mble+2.115
pher+1.869
cream+1.684
displayText+1.607
Neg logit contributions
 viral-2.187
 Tik-2.180
 stride-2.129
 Kik-2.053
 characteristic-2.030
Tokeneling
Token ID10809
Feature activation+6.42e-01

Pos logit contributions
 viral+1.513
 Tik+1.506
 stride+1.477
 Kik+1.431
 characteristic+1.414
Neg logit contributions
nesday-1.182
mble-1.177
pher-1.011
cream-0.905
displayText-0.873
Token forums
Token ID14216
Feature activation-6.29e-01

Pos logit contributions
mble+2.913
nesday+2.901
pher+2.676
cream+2.446
displayText+2.324
Neg logit contributions
 Tik-1.790
 viral-1.736
 stride-1.702
uni-1.662
 Kik-1.628
Token where
Token ID810
Feature activation-2.92e-01

Pos logit contributions
 viral+1.679
 Tik+1.660
 stride+1.605
 Kik+1.522
 characteristic+1.506
Neg logit contributions
nesday-3.050
mble-3.035
pher-2.743
cream-2.553
displayText-2.486
Token back
Token ID736
Feature activation+8.47e-02

Pos logit contributions
nesday+3.146
mble+3.144
pher+2.871
cream+2.654
displayText+2.526
Neg logit contributions
 viral-1.857
 Tik-1.856
 stride-1.802
 Kik-1.705
uni-1.693
Token,
Token ID11
Feature activation-6.60e-02

Pos logit contributions
nesday+0.391
mble+0.389
pher+0.354
cream+0.327
displayText+0.315
Neg logit contributions
 viral-0.241
 Tik-0.241
 stride-0.233
 Kik-0.222
 characteristic-0.219
Token winger
Token ID31389
Feature activation+4.18e-01

Pos logit contributions
 viral+0.181
 Tik+0.180
 stride+0.174
 Kik+0.166
 characteristic+0.163
Neg logit contributions
nesday-0.312
mble-0.311
pher-0.283
cream-0.262
displayText-0.253
Token and
Token ID290
Feature activation+5.18e-01

Pos logit contributions
nesday+1.975
mble+1.968
pher+1.800
cream+1.670
displayText+1.597
Neg logit contributions
 viral-1.123
 Tik-1.122
 stride-1.072
 Kik-1.035
uni-1.009
Token first
Token ID717
Feature activation+6.72e-01

Pos logit contributions
nesday+2.514
mble+2.508
pher+2.299
cream+2.128
displayText+2.039
Neg logit contributions
 Tik-1.317
 viral-1.309
 stride-1.246
 Kik-1.195
uni-1.176
Token couple
Token ID3155
Feature activation+2.94e+00

Pos logit contributions
mble+3.338
nesday+3.334
pher+3.083
cream+2.873
displayText+2.735
Neg logit contributions
 Tik-1.580
 viral-1.570
 stride-1.489
 Kik-1.439
uni-1.426
Token of
Token ID286
Feature activation+1.35e+00

Pos logit contributions
mble+12.849
nesday+12.771
pher+11.937
cream+10.913
umbledore+9.994
Neg logit contributions
 Tik-7.007
 viral-6.876
 stride-6.523
 Kik-6.428
uni-6.237
Token attackers
Token ID16391
Feature activation+7.35e-01

Pos logit contributions
nesday+6.191
mble+6.190
pher+5.677
cream+5.189
displayText+4.955
Neg logit contributions
 Tik-3.526
 viral-3.501
 stride-3.349
uni-3.239
 Kik-3.213
Token to
Token ID284
Feature activation+5.22e-01

Pos logit contributions
mble+3.429
nesday+3.425
pher+3.134
cream+2.921
displayText+2.763
Neg logit contributions
 Tik-1.975
 viral-1.962
 stride-1.869
 Kik-1.820
uni-1.780
Token hold
Token ID1745
Feature activation-3.31e-01

Pos logit contributions
mble+2.515
nesday+2.512
pher+2.295
cream+2.119
displayText+2.033
Neg logit contributions
 viral-1.351
 Tik-1.346
 stride-1.287
 Kik-1.235
 characteristic-1.211
Token defensive
Token ID6110
Feature activation+2.08e-01

Pos logit contributions
 viral+0.856
 Tik+0.852
 stride+0.821
 Kik+0.779
 characteristic+0.765
Neg logit contributions
nesday-1.618
mble-1.611
pher-1.468
cream-1.363
displayText-1.319
Token Par
Token ID2547
Feature activation-6.72e-02

Pos logit contributions
nesday+0.882
mble+0.876
pher+0.801
cream+0.738
displayText+0.713
Neg logit contributions
 viral-0.490
 Tik-0.488
 stride-0.475
 Kik-0.449
 characteristic-0.443
Tokenth
Token ID400
Feature activation-9.20e-01

Pos logit contributions
 viral+0.209
 Tik+0.208
 stride+0.203
 Kik+0.192
uni+0.191
Neg logit contributions
nesday-0.294
mble-0.293
pher-0.261
cream-0.241
displayText-0.234
Tokeniv
Token ID452
Feature activation-7.29e-01

Pos logit contributions
 viral+2.873
 Tik+2.860
 stride+2.775
uni+2.641
 Kik+2.621
Neg logit contributions
nesday-4.045
mble-3.996
pher-3.493
displayText-3.203
cream-3.191
Token I
Token ID314
Feature activation+2.27e-01

Pos logit contributions
 viral+2.031
 Tik+2.005
 stride+1.922
 Kik+1.833
 characteristic+1.799
Neg logit contributions
mble-3.455
nesday-3.439
pher-3.096
cream-2.868
displayText-2.789
Token have
Token ID423
Feature activation+5.74e-02

Pos logit contributions
nesday+1.002
mble+1.002
pher+0.916
cream+0.837
displayText+0.808
Neg logit contributions
 Tik-0.685
 viral-0.684
 stride-0.660
 Kik-0.641
 characteristic-0.624
Token fre
Token ID2030
Feature activation+2.93e+00

Pos logit contributions
nesday+0.237
mble+0.236
pher+0.213
cream+0.193
displayText+0.186
Neg logit contributions
 viral-0.191
 Tik-0.191
 stride-0.185
 Kik-0.179
 characteristic-0.175
Tokentted
Token ID28734
Feature activation+7.42e-01

Pos logit contributions
nesday+8.908
mble+8.441
pher+8.029
cream+6.676
ationally+6.566
Neg logit contributions
 viral-11.635
 Tik-11.333
 stride-11.307
 Kik-11.189
 characteristic-11.035
Token over
Token ID625
Feature activation+3.27e-01

Pos logit contributions
nesday+3.349
mble+3.345
pher+3.071
cream+2.792
displayText+2.694
Neg logit contributions
 Tik-2.096
 viral-2.085
 stride-2.047
 Kik-1.959
uni-1.939
Token whether
Token ID1771
Feature activation-3.80e-01

Pos logit contributions
nesday+1.480
mble+1.478
pher+1.346
cream+1.227
displayText+1.185
Neg logit contributions
 Tik-0.937
 viral-0.936
 stride-0.915
 Kik-0.876
uni-0.864
Token it
Token ID340
Feature activation-2.93e-01

Pos logit contributions
 viral+0.952
 Tik+0.947
 stride+0.911
 Kik+0.861
 characteristic+0.845
Neg logit contributions
nesday-1.895
mble-1.886
pher-1.719
cream-1.601
displayText-1.555
Token could
Token ID714
Feature activation+4.38e-01

Pos logit contributions
 viral+0.794
 Tik+0.791
 stride+0.764
 Kik+0.725
 characteristic+0.714
Neg logit contributions
nesday-1.400
mble-1.393
pher-1.266
cream-1.173
displayText-1.135
Tokenthis
Token ID5661
Feature activation+8.80e-01

Pos logit contributions
nesday+1.292
mble+1.291
pher+1.158
cream+1.059
displayText+1.007
Neg logit contributions
 viral-1.105
 Tik-1.100
 stride-1.068
 Kik-1.028
 characteristic-1.013
Token maj
Token ID16486
Feature activation-6.46e-01

Pos logit contributions
mble+4.135
nesday+4.072
pher+3.785
cream+3.484
displayText+3.301
Neg logit contributions
 Tik-2.313
 viral-2.274
 stride-2.160
 Kik-2.110
uni-2.088
Tokenest
Token ID395
Feature activation+4.89e-01

Pos logit contributions
 Tik+1.854
 viral+1.851
 stride+1.800
 Kik+1.709
uni+1.689
Neg logit contributions
nesday-2.960
mble-2.935
pher-2.652
cream-2.453
displayText-2.399
Tokenical
Token ID605
Feature activation+7.60e-01

Pos logit contributions
mble+1.947
nesday+1.942
pher+1.740
cream+1.595
displayText+1.493
Neg logit contributions
 viral-1.668
 Tik-1.667
 stride-1.613
 Kik-1.550
 characteristic-1.529
Token roof
Token ID9753
Feature activation+3.74e-01

Pos logit contributions
mble+3.742
nesday+3.668
pher+3.429
cream+3.168
displayText+3.014
Neg logit contributions
 Tik-1.821
 viral-1.818
 stride-1.693
 Kik-1.661
uni-1.655
Token fre
Token ID2030
Feature activation+2.93e+00

Pos logit contributions
mble+1.725
nesday+1.711
pher+1.571
cream+1.452
displayText+1.380
Neg logit contributions
 viral-1.055
 Tik-1.049
 stride-1.001
 Kik-0.973
 characteristic-0.945
Tokentted
Token ID28734
Feature activation+1.47e+00

Pos logit contributions
mble+10.893
nesday+10.721
pher+10.254
cream+8.882
maid+8.230
Neg logit contributions
 viral-9.371
 Tik-9.108
 stride-8.728
 Kik-8.634
 characteristic-8.537
Token with
Token ID351
Feature activation+5.55e-01

Pos logit contributions
mble+6.594
nesday+6.470
pher+5.990
cream+5.535
displayText+5.182
Neg logit contributions
 Tik-3.993
 viral-3.943
 stride-3.748
 Kik-3.704
uni-3.668
Token golden
Token ID10861
Feature activation-1.83e+00

Pos logit contributions
mble+2.629
nesday+2.605
pher+2.403
cream+2.222
displayText+2.116
Neg logit contributions
 Tik-1.470
 viral-1.454
 stride-1.400
 Kik-1.343
uni-1.323
Token fire
Token ID2046
Feature activation+2.91e-01

Pos logit contributions
 viral+5.116
 Tik+5.084
 stride+4.968
 characteristic+4.684
 Kik+4.632
Neg logit contributions
nesday-8.504
mble-8.330
pher-7.421
displayText-6.886
cream-6.800
Token,
Token ID11
Feature activation-2.08e-01

Pos logit contributions
mble+1.388
nesday+1.382
pher+1.268
cream+1.182
displayText+1.123
Neg logit contributions
 Tik-0.776
 viral-0.775
 stride-0.744
 Kik-0.715
 characteristic-0.695
Token low
Token ID1877
Feature activation-3.69e-01

Pos logit contributions
 viral+1.548
 Tik+1.539
 stride+1.492
 Kik+1.398
 characteristic+1.383
Neg logit contributions
nesday-3.031
mble-3.015
pher-2.752
cream-2.556
displayText-2.485
Token point
Token ID966
Feature activation-1.48e-01

Pos logit contributions
 viral+1.028
 Tik+1.023
 stride+0.993
 Kik+0.942
 characteristic+0.929
Neg logit contributions
nesday-1.733
mble-1.723
pher-1.564
cream-1.447
displayText-1.401
Token he
Token ID339
Feature activation-3.07e-01

Pos logit contributions
 viral+0.412
 Tik+0.410
 stride+0.397
 Kik+0.378
 characteristic+0.371
Neg logit contributions
nesday-0.692
mble-0.688
pher-0.625
cream-0.577
displayText-0.559
Token drilled
Token ID34936
Feature activation+1.96e-01

Pos logit contributions
 viral+0.895
 Tik+0.892
 stride+0.865
 Kik+0.820
 characteristic+0.814
Neg logit contributions
nesday-1.414
mble-1.410
pher-1.255
cream-1.170
displayText-1.132
Token 17
Token ID1596
Feature activation+2.58e-01

Pos logit contributions
nesday+0.935
mble+0.929
pher+0.851
cream+0.786
displayText+0.755
Neg logit contributions
 viral-0.522
 Tik-0.518
 stride-0.501
 Kik-0.476
uni-0.468
Token dry
Token ID5894
Feature activation+2.92e+00

Pos logit contributions
nesday+1.095
mble+1.088
pher+0.983
cream+0.895
displayText+0.862
Neg logit contributions
 viral-0.833
 Tik-0.829
 stride-0.807
 Kik-0.774
 characteristic-0.761
Token holes
Token ID10421
Feature activation+3.66e-01

Pos logit contributions
nesday+11.009
mble+10.910
pher+10.342
cream+9.149
pel+8.663
Neg logit contributions
 Tik-8.441
 viral-8.421
 stride-8.026
uni-7.999
 Kik-7.839
Token in
Token ID287
Feature activation-7.22e-01

Pos logit contributions
nesday+1.736
mble+1.713
pher+1.583
cream+1.458
displayText+1.399
Neg logit contributions
 viral-0.984
 Tik-0.979
 stride-0.950
 Kik-0.903
uni-0.890
Token a
Token ID257
Feature activation-3.96e-01

Pos logit contributions
 viral+1.951
 Tik+1.950
 stride+1.881
 Kik+1.785
 characteristic+1.759
Neg logit contributions
nesday-3.465
mble-3.446
pher-3.118
cream-2.903
displayText-2.828
Token row
Token ID5752
Feature activation+1.51e-02

Pos logit contributions
 viral+1.032
 Tik+1.028
 stride+0.992
 Kik+0.940
 characteristic+0.924
Neg logit contributions
nesday-1.931
mble-1.922
pher-1.753
cream-1.625
displayText-1.573
Token.
Token ID13
Feature activation+8.63e-02

Pos logit contributions
nesday+0.073
mble+0.072
pher+0.066
cream+0.061
displayText+0.059
Neg logit contributions
 viral-0.040
 Tik-0.040
 stride-0.039
 Kik-0.037
 characteristic-0.036
Token Let
Token ID3914
Feature activation-6.88e-01

Pos logit contributions
nesday+0.001
mble+0.001
pher+0.001
cream+0.001
displayText+0.001
Neg logit contributions
 viral-0.000
 Tik-0.000
 stride-0.000
 Kik-0.000
 characteristic-0.000
Token us
Token ID514
Feature activation-3.02e-01

Pos logit contributions
 viral+2.034
 Tik+2.032
 stride+1.960
 Kik+1.871
 characteristic+1.853
Neg logit contributions
nesday-3.108
mble-3.095
pher-2.797
cream-2.582
displayText-2.496
Token remember
Token ID3505
Feature activation-5.47e-02

Pos logit contributions
 viral+0.900
 Tik+0.898
 stride+0.865
 Kik+0.833
 characteristic+0.817
Neg logit contributions
nesday-1.360
mble-1.353
pher-1.227
cream-1.125
displayText-1.086
Token that
Token ID326
Feature activation-6.30e-01

Pos logit contributions
 viral+0.155
 Tik+0.154
 stride+0.149
 Kik+0.142
 characteristic+0.139
Neg logit contributions
nesday-0.254
mble-0.253
pher-0.229
cream-0.211
displayText-0.204
Token the
Token ID262
Feature activation-8.25e-02

Pos logit contributions
 viral+1.699
 Tik+1.692
 stride+1.634
 Kik+1.551
 characteristic+1.529
Neg logit contributions
nesday-3.022
mble-3.005
pher-2.734
cream-2.534
displayText-2.457
Token Sloven
Token ID30694
Feature activation+2.89e+00

Pos logit contributions
 viral+0.222
 Tik+0.221
 stride+0.213
 Kik+0.203
 characteristic+0.199
Neg logit contributions
nesday-0.395
mble-0.393
pher-0.357
cream-0.331
displayText-0.320
Tokenian
Token ID666
Feature activation+1.01e+00

Pos logit contributions
nesday+8.973
mble+8.719
pher+7.992
cream+6.983
displayText+6.555
Neg logit contributions
 Tik-10.713
 viral-10.645
 stride-10.331
 Kik-10.136
 Hawai-10.036
Token government
Token ID1230
Feature activation+1.54e-01

Pos logit contributions
nesday+4.628
mble+4.594
pher+4.201
cream+3.884
displayText+3.760
Neg logit contributions
 Tik-2.758
 viral-2.756
 stride-2.651
 Kik-2.527
uni-2.518
Token declared
Token ID6875
Feature activation-8.20e-01

Pos logit contributions
nesday+0.724
mble+0.718
pher+0.658
cream+0.606
displayText+0.587
Neg logit contributions
 viral-0.424
 Tik-0.423
 stride-0.408
 Kik-0.390
 characteristic-0.381
Token independence
Token ID10404
Feature activation-7.08e-01

Pos logit contributions
 viral+2.597
 Tik+2.585
 stride+2.512
 Kik+2.393
 characteristic+2.382
Neg logit contributions
nesday-3.525
mble-3.508
pher-3.162
cream-2.911
displayText-2.815
Token in
Token ID287
Feature activation-5.06e-01

Pos logit contributions
 viral+1.797
 Tik+1.781
 stride+1.724
 Kik+1.618
 characteristic+1.612
Neg logit contributions
mble-3.502
nesday-3.498
pher-3.172
cream-2.949
displayText-2.867
Tokenspect
Token ID4443
Feature activation+8.90e-01

Pos logit contributions
mble+1.812
nesday+1.794
pher+1.668
cream+1.528
displayText+1.431
Neg logit contributions
 Tik-1.331
 viral-1.327
 stride-1.281
 Kik-1.242
 squid-1.205
Tokenral
Token ID1373
Feature activation+2.57e-01

Pos logit contributions
mble+3.210
nesday+3.110
pher+2.870
cream+2.568
displayText+2.370
Neg logit contributions
 viral-3.393
 Tik-3.366
 stride-3.319
 Kik-3.220
 squid-3.130
Token response
Token ID2882
Feature activation-6.26e-01

Pos logit contributions
mble+1.244
nesday+1.231
pher+1.148
cream+1.058
displayText+1.003
Neg logit contributions
 viral-0.665
 Tik-0.660
 stride-0.631
 Kik-0.609
uni-0.597
Token at
Token ID379
Feature activation-6.32e-01

Pos logit contributions
 viral+1.561
 Tik+1.549
 stride+1.503
 Kik+1.407
 characteristic+1.405
Neg logit contributions
nesday-3.135
mble-3.109
pher-2.825
cream-2.631
displayText-2.570
Token higher
Token ID2440
Feature activation-8.26e-01

Pos logit contributions
 viral+1.577
 Tik+1.570
 stride+1.513
 Kik+1.434
 characteristic+1.403
Neg logit contributions
nesday-3.145
mble-3.131
pher-2.868
cream-2.662
displayText-2.572
Token sensit
Token ID44752
Feature activation+2.87e+00

Pos logit contributions
 viral+2.035
 Tik+2.022
 stride+1.948
 Kik+1.835
 characteristic+1.811
Neg logit contributions
nesday-4.172
mble-4.137
pher-3.765
cream-3.513
displayText-3.430
Tokenivities
Token ID28720
Feature activation+6.69e-01

Pos logit contributions
mble+7.271
nesday+7.239
pher+6.920
cream+5.741
ison+5.285
Neg logit contributions
 Tik-12.204
 viral-11.950
 stride-11.908
uni-11.421
 Kik-11.379
Token though
Token ID996
Feature activation-1.28e-01

Pos logit contributions
mble+3.119
nesday+3.103
pher+2.867
cream+2.658
displayText+2.515
Neg logit contributions
 Tik-1.817
 viral-1.792
 stride-1.732
 Kik-1.671
uni-1.637
Token,
Token ID11
Feature activation-8.74e-02

Pos logit contributions
 viral+0.342
 Tik+0.342
 stride+0.330
 Kik+0.315
 characteristic+0.307
Neg logit contributions
mble-0.614
nesday-0.612
pher-0.560
cream-0.518
displayText-0.498
Token which
Token ID543
Feature activation+5.16e-01

Pos logit contributions
 viral+0.227
 Tik+0.227
 stride+0.218
 Kik+0.207
 characteristic+0.202
Neg logit contributions
nesday-0.425
mble-0.423
pher-0.388
cream-0.359
displayText-0.346
Token is
Token ID318
Feature activation+2.95e-01

Pos logit contributions
nesday+2.394
mble+2.384
pher+2.189
cream+2.015
displayText+1.923
Neg logit contributions
 viral-1.426
 Tik-1.423
 stride-1.369
 Kik-1.308
uni-1.276
Token a
Token ID257
Feature activation-2.98e-01

Pos logit contributions
 viral+0.252
 Tik+0.250
 stride+0.241
 Kik+0.229
uni+0.223
Neg logit contributions
nesday-0.492
mble-0.490
pher-0.448
cream-0.415
displayText-0.401
Token building
Token ID2615
Feature activation-7.17e-01

Pos logit contributions
 viral+0.744
 Tik+0.743
 stride+0.715
 Kik+0.678
 characteristic+0.657
Neg logit contributions
nesday-1.483
mble-1.479
pher-1.352
cream-1.254
displayText-1.214
Token is
Token ID318
Feature activation-1.92e-01

Pos logit contributions
 viral+1.788
 Tik+1.781
 stride+1.716
 Kik+1.621
 characteristic+1.593
Neg logit contributions
nesday-3.582
mble-3.564
pher-3.256
cream-3.026
displayText-2.934
Token constructed
Token ID12006
Feature activation+3.39e-01

Pos logit contributions
 viral+0.490
 Tik+0.489
 stride+0.472
 Kik+0.446
 characteristic+0.436
Neg logit contributions
nesday-0.947
mble-0.942
pher-0.862
cream-0.799
displayText-0.774
Token.
Token ID13
Feature activation-3.69e-01

Pos logit contributions
nesday+1.658
mble+1.654
pher+1.518
cream+1.411
displayText+1.356
Neg logit contributions
 Tik-0.858
 viral-0.853
 stride-0.821
 Kik-0.789
 squid-0.756
Token Dri
Token ID5809
Feature activation+2.87e+00

Pos logit contributions
 viral+1.013
 Tik+1.011
 stride+0.975
 Kik+0.928
 characteristic+0.913
Neg logit contributions
nesday-1.752
mble-1.743
pher-1.582
cream-1.464
displayText-1.418
Tokenven
Token ID574
Feature activation+1.45e+00

Pos logit contributions
nesday+8.866
mble+8.726
pher+7.820
cream+6.890
pel+6.480
Neg logit contributions
 Tik-10.634
 viral-10.460
 stride-10.373
 Kik-10.218
 Gujar-9.937
Token by
Token ID416
Feature activation+8.23e-02

Pos logit contributions
nesday+6.018
mble+5.931
pher+5.411
cream+4.927
displayText+4.682
Neg logit contributions
 Tik-4.447
 viral-4.357
 stride-4.336
 Kik-4.253
 Hawai-4.009
Token utility
Token ID10361
Feature activation-2.95e-01

Pos logit contributions
nesday+0.392
mble+0.390
pher+0.357
cream+0.330
displayText+0.317
Neg logit contributions
 Tik-0.219
 viral-0.219
 stride-0.212
 Kik-0.201
uni-0.197
Token,
Token ID11
Feature activation-5.50e-01

Pos logit contributions
 viral+0.758
 Tik+0.755
 stride+0.728
 Kik+0.689
 characteristic+0.677
Neg logit contributions
nesday-1.453
mble-1.446
pher-1.320
cream-1.225
displayText-1.187
Token aesthetic
Token ID19713
Feature activation+7.90e-01

Pos logit contributions
 viral+1.452
 Tik+1.447
 stride+1.397
 Kik+1.325
 characteristic+1.301
Neg logit contributions
nesday-2.665
mble-2.652
pher-2.416
cream-2.240
displayText-2.168
Token maybe
Token ID3863
Feature activation+4.87e-01

Pos logit contributions
 viral+0.082
 Tik+0.082
 stride+0.079
 Kik+0.076
 characteristic+0.074
Neg logit contributions
nesday-0.130
mble-0.130
pher-0.117
cream-0.108
displayText-0.105
Token,
Token ID11
Feature activation+1.82e-01

Pos logit contributions
nesday+2.322
mble+2.312
pher+2.110
cream+1.954
displayText+1.881
Neg logit contributions
 Tik-1.292
 viral-1.282
 stride-1.243
 Kik-1.186
uni-1.159
Token we
Token ID356
Feature activation+8.02e-01

Pos logit contributions
nesday+0.863
mble+0.857
pher+0.781
cream+0.722
displayText+0.696
Neg logit contributions
 Tik-0.496
 viral-0.495
 stride-0.479
 Kik-0.456
 characteristic-0.447
Token should
Token ID815
Feature activation-8.13e-02

Pos logit contributions
mble+3.611
nesday+3.595
pher+3.323
cream+3.034
displayText+2.883
Neg logit contributions
 Tik-2.262
 viral-2.252
 stride-2.164
 Kik-2.115
 characteristic-2.061
Token be
Token ID307
Feature activation+4.98e-02

Pos logit contributions
 viral+0.231
 Tik+0.231
 stride+0.223
 Kik+0.213
 characteristic+0.209
Neg logit contributions
nesday-0.377
mble-0.375
pher-0.340
cream-0.314
displayText-0.304
Token incentiv
Token ID39678
Feature activation+2.87e+00

Pos logit contributions
nesday+0.230
mble+0.228
pher+0.207
cream+0.191
displayText+0.185
Neg logit contributions
 viral-0.143
 Tik-0.142
 stride-0.138
 Kik-0.131
 characteristic-0.129
Tokenizing
Token ID2890
Feature activation+3.28e-01

Pos logit contributions
nesday+7.586
mble+7.159
pher+6.559
cream+5.617
ationally+5.082
Neg logit contributions
 viral-12.355
 Tik-12.192
 stride-12.020
 Gujar-11.541
 Kik-11.486
Token them
Token ID606
Feature activation+2.10e-01

Pos logit contributions
nesday+1.473
mble+1.469
pher+1.326
cream+1.222
displayText+1.176
Neg logit contributions
 Tik-0.974
 viral-0.969
 stride-0.940
 Kik-0.900
 characteristic-0.883
Token to
Token ID284
Feature activation-5.44e-01

Pos logit contributions
nesday+0.926
mble+0.919
pher+0.833
cream+0.764
displayText+0.736
Neg logit contributions
 viral-0.642
 Tik-0.642
 stride-0.621
 Kik-0.595
 characteristic-0.585
Token solve
Token ID8494
Feature activation+5.92e-01

Pos logit contributions
 viral+1.489
 Tik+1.461
 stride+1.443
 Kik+1.351
 characteristic+1.331
Neg logit contributions
nesday-2.598
mble-2.589
pher-2.337
cream-2.176
displayText-2.117
Token them
Token ID606
Feature activation+5.21e-01

Pos logit contributions
nesday+2.673
mble+2.666
pher+2.428
cream+2.233
displayText+2.131
Neg logit contributions
 Tik-1.716
 viral-1.675
 stride-1.647
 Kik-1.574
uni-1.552
Token,'
Token ID4032
Feature activation-5.05e-02

Pos logit contributions
nesday+2.569
mble+2.563
pher+2.328
cream+2.136
displayText+2.065
Neg logit contributions
 Tik-1.676
 viral-1.675
 stride-1.605
 Kik-1.542
 characteristic-1.513
Token said
Token ID531
Feature activation+4.68e-01

Pos logit contributions
 viral+0.138
 Tik+0.137
 stride+0.133
 Kik+0.127
uni+0.125
Neg logit contributions
nesday-0.237
mble-0.236
pher-0.217
cream-0.200
displayText-0.192
Token Jack
Token ID3619
Feature activation-7.82e-01

Pos logit contributions
mble+2.154
nesday+2.147
pher+1.969
cream+1.804
displayText+1.723
Neg logit contributions
 viral-1.304
 Tik-1.284
 stride-1.253
 Kik-1.200
uni-1.186
Token.
Token ID13
Feature activation+3.53e-01

Pos logit contributions
 viral+2.066
 Tik+2.061
 stride+2.007
 Kik+1.887
 characteristic+1.869
Neg logit contributions
nesday-3.807
mble-3.773
pher-3.418
cream-3.174
displayText-3.066
Token '
Token ID705
Feature activation+1.19e+00

Pos logit contributions
nesday+1.727
mble+1.721
pher+1.593
cream+1.479
displayText+1.421
Neg logit contributions
 viral-0.884
 Tik-0.857
 stride-0.842
 Kik-0.788
 characteristic-0.786
TokenSex
Token ID23398
Feature activation+2.87e+00

Pos logit contributions
mble+3.969
nesday+3.935
pher+3.606
cream+3.246
displayText+3.051
Neg logit contributions
 viral-4.690
 Tik-4.602
 stride-4.548
 characteristic-4.357
 Kik-4.315
Token has
Token ID468
Feature activation+4.43e-01

Pos logit contributions
nesday+11.702
mble+11.627
pher+10.969
cream+9.940
displayText+9.243
Neg logit contributions
 Tik-7.874
 viral-7.776
 stride-7.410
 Kik-7.106
 Gujar-7.000
Token never
Token ID1239
Feature activation+8.40e-02

Pos logit contributions
nesday+2.022
mble+2.015
pher+1.838
cream+1.691
displayText+1.618
Neg logit contributions
 Tik-1.271
 viral-1.268
 stride-1.223
 Kik-1.169
uni-1.148
Token entered
Token ID5982
Feature activation-1.34e-01

Pos logit contributions
nesday+0.364
mble+0.362
pher+0.326
cream+0.299
displayText+0.289
Neg logit contributions
 viral-0.265
 Tik-0.264
 stride-0.256
 Kik-0.245
 characteristic-0.242
Token my
Token ID616
Feature activation-1.54e-01

Pos logit contributions
 viral+0.394
 Tik+0.393
 stride+0.379
 Kik+0.363
 characteristic+0.357
Neg logit contributions
nesday-0.607
mble-0.605
pher-0.548
cream-0.504
displayText-0.486
Token mind
Token ID2000
Feature activation-8.06e-02

Pos logit contributions
 Tik+0.394
 viral+0.393
 stride+0.375
 Kik+0.360
uni+0.350
Neg logit contributions
nesday-0.752
mble-0.751
pher-0.684
cream-0.634
displayText-0.612
Token what
Token ID644
Feature activation+1.29e+00

Pos logit contributions
nesday+5.449
mble+5.413
pher+4.957
cream+4.488
displayText+4.220
Neg logit contributions
 Tik-4.382
 stride-4.286
 viral-4.274
 Kik-4.145
uni-4.080
Token we
Token ID356
Feature activation+1.08e+00

Pos logit contributions
nesday+6.063
mble+5.990
pher+5.607
cream+5.091
displayText+4.912
Neg logit contributions
 Tik-3.194
 stride-3.158
 viral-3.134
 Kik-3.062
uni-2.950
Token can
Token ID460
Feature activation+9.10e-01

Pos logit contributions
nesday+5.127
mble+5.083
pher+4.762
cream+4.385
displayText+4.145
Neg logit contributions
 Tik-2.687
 viral-2.675
 stride-2.587
 Kik-2.547
uni-2.444
Token say
Token ID910
Feature activation+6.30e-01

Pos logit contributions
nesday+3.652
mble+3.593
pher+3.310
cream+2.955
displayText+2.766
Neg logit contributions
 Tik-3.025
 viral-2.975
 stride-2.904
 Kik-2.870
uni-2.805
Token,
Token ID11
Feature activation+7.25e-01

Pos logit contributions
nesday+2.864
mble+2.843
pher+2.583
cream+2.377
displayText+2.295
Neg logit contributions
 Tik-1.813
 viral-1.781
 stride-1.747
 Kik-1.690
 characteristic-1.630
Token see
Token ID766
Feature activation+2.86e+00

Pos logit contributions
nesday+3.216
mble+3.197
pher+2.943
cream+2.681
displayText+2.566
Neg logit contributions
 Tik-2.069
 viral-2.045
 stride-2.010
 Kik-1.933
uni-1.927
Token or
Token ID393
Feature activation+1.53e+00

Pos logit contributions
nesday+11.014
mble+10.989
pher+9.971
cream+8.984
displayText+8.780
Neg logit contributions
 Tik-8.189
 viral-8.092
 stride-7.998
 Kik-7.894
 squid-7.644
Token hear
Token ID3285
Feature activation+1.41e+00

Pos logit contributions
nesday+5.845
mble+5.793
pher+5.371
cream+4.722
displayText+4.423
Neg logit contributions
 Tik-5.233
 viral-5.013
 stride-4.942
 Kik-4.899
uni-4.805
Token?
Token ID30
Feature activation+3.74e-01

Pos logit contributions
nesday+5.767
mble+5.710
pher+5.157
cream+4.694
displayText+4.501
Neg logit contributions
 Tik-4.481
 stride-4.385
 viral-4.368
 Kik-4.241
 squid-4.094
Token Who
Token ID5338
Feature activation+5.95e-01

Pos logit contributions
nesday+1.728
mble+1.719
pher+1.580
cream+1.459
displayText+1.408
Neg logit contributions
 viral-1.043
 Tik-1.033
 stride-1.012
 characteristic-0.952
 Kik-0.951
Token decides
Token ID13267
Feature activation+1.57e+00

Pos logit contributions
nesday+2.772
mble+2.756
pher+2.526
cream+2.323
displayText+2.245
Neg logit contributions
 viral-1.650
 Tik-1.647
 stride-1.594
 Kik-1.521
 characteristic-1.498
Token starch
Token ID39515
Feature activation+7.98e-01

Pos logit contributions
 viral+2.544
 Tik+2.525
 stride+2.446
 Kik+2.287
 characteristic+2.277
Neg logit contributions
nesday-4.984
mble-4.973
pher-4.517
cream-4.180
displayText-4.084
Token (
Token ID357
Feature activation+1.08e+00

Pos logit contributions
nesday+3.764
mble+3.738
pher+3.418
cream+3.237
displayText+3.007
Neg logit contributions
 Tik-2.100
 viral-2.081
 stride-2.009
 Kik-1.943
uni-1.897
Tokenwhich
Token ID4758
Feature activation+4.35e-01

Pos logit contributions
nesday+4.387
mble+4.365
pher+4.023
cream+3.785
displayText+3.492
Neg logit contributions
 viral-3.474
 stride-3.421
 Tik-3.419
 Kik-3.164
 sighting-3.153
Token is
Token ID318
Feature activation+1.79e-02

Pos logit contributions
nesday+2.067
mble+2.057
pher+1.892
cream+1.759
displayText+1.680
Neg logit contributions
 viral-1.135
 Tik-1.128
 stride-1.113
 Kik-1.038
 characteristic-1.018
Token ground
Token ID2323
Feature activation+5.04e-01

Pos logit contributions
nesday+0.080
mble+0.079
pher+0.072
cream+0.066
displayText+0.064
Neg logit contributions
 viral-0.053
 Tik-0.053
 stride-0.052
 Kik-0.049
uni-0.048
Token dehyd
Token ID28151
Feature activation+2.86e+00

Pos logit contributions
nesday+2.323
mble+2.308
pher+2.120
cream+1.982
displayText+1.863
Neg logit contributions
 Tik-1.363
 viral-1.358
 stride-1.339
 Kik-1.266
uni-1.246
Tokenrated
Token ID4111
Feature activation+5.90e-01

Pos logit contributions
mble+8.217
nesday+8.182
pher+7.794
cream+6.649
ationally+5.942
Neg logit contributions
 Tik-11.612
 stride-11.337
 viral-11.181
 sighting-10.971
 Kik-10.898
Token k
Token ID479
Feature activation-9.26e-01

Pos logit contributions
mble+2.782
nesday+2.762
pher+2.559
cream+2.384
displayText+2.259
Neg logit contributions
 viral-1.491
 Tik-1.491
 stride-1.487
uni-1.362
 Kik-1.360
Tokenuz
Token ID10277
Feature activation+2.26e-02

Pos logit contributions
 viral+2.656
 Tik+2.642
 stride+2.543
 Kik+2.436
uni+2.427
Neg logit contributions
nesday-4.254
mble-4.242
pher-3.829
cream-3.529
displayText-3.440
Tokenu
Token ID84
Feature activation-1.11e+00

Pos logit contributions
nesday+0.108
mble+0.108
pher+0.099
cream+0.092
displayText+0.087
Neg logit contributions
 viral-0.060
 Tik-0.060
 stride-0.058
 Kik-0.055
 characteristic-0.054
Token root
Token ID6808
Feature activation-6.14e-01

Pos logit contributions
 viral+3.024
 Tik+3.004
 stride+2.897
 characteristic+2.732
 Kik+2.730
Neg logit contributions
nesday-5.280
mble-5.261
pher-4.753
cream-4.376
displayText-4.298
Token Baldwin
Token ID26402
Feature activation+7.58e-01

Pos logit contributions
nesday+3.990
mble+3.979
pher+3.664
cream+3.402
displayText+3.276
Neg logit contributions
 viral-2.022
 Tik-1.995
 stride-1.938
 Kik-1.824
 characteristic-1.802
Token
Token ID198
Feature activation+1.40e-01

Pos logit contributions
nesday+3.762
mble+3.736
pher+3.489
cream+3.244
displayText+3.120
Neg logit contributions
 viral-1.818
 Tik-1.815
 stride-1.752
 Kik-1.650
 characteristic-1.635
Token
Token ID198
Feature activation+1.02e+00

Pos logit contributions
nesday+0.747
mble+0.745
pher+0.676
cream+0.633
displayText+0.616
Neg logit contributions
 viral-0.305
 Tik-0.304
 stride-0.291
 Kik-0.273
 characteristic-0.266
Token2008
Token ID11528
Feature activation+4.35e-01

Pos logit contributions
nesday+4.191
mble+4.149
pher+3.779
cream+3.463
displayText+3.347
Neg logit contributions
 Tik-3.420
 viral-3.386
 stride-3.316
 Kik-3.162
 characteristic-3.137
Token Steve
Token ID6542
Feature activation-1.09e+00

Pos logit contributions
nesday+1.709
mble+1.699
pher+1.537
cream+1.392
displayText+1.312
Neg logit contributions
 viral-1.489
 stride-1.481
 Tik-1.476
uni-1.398
 characteristic-1.388
Token Care
Token ID7276
Feature activation+2.86e+00

Pos logit contributions
 Tik+3.223
 viral+3.188
 stride+3.038
 Kik+3.038
 characteristic+2.874
Neg logit contributions
mble-5.036
nesday-5.033
pher-4.381
cream-3.966
displayText-3.947
Tokenll
Token ID297
Feature activation+1.28e+00

Pos logit contributions
mble+6.918
nesday+6.825
pher+6.466
cream+5.804
bourg+5.071
Neg logit contributions
 Tik-12.989
 viral-12.819
 stride-12.642
 Kik-12.407
 squid-12.385
Token
Token ID198
Feature activation+1.37e-01

Pos logit contributions
nesday+5.887
mble+5.838
pher+5.554
cream+5.149
displayText+4.911
Neg logit contributions
 Tik-3.238
 viral-3.192
 stride-3.165
 characteristic-2.992
 Kik-2.960
Token
Token ID198
Feature activation+1.09e+00

Pos logit contributions
nesday+0.736
mble+0.734
pher+0.666
cream+0.623
displayText+0.606
Neg logit contributions
 viral-0.299
 Tik-0.298
 stride-0.284
 Kik-0.267
 characteristic-0.261
Token2008
Token ID11528
Feature activation+6.78e-01

Pos logit contributions
nesday+4.503
mble+4.456
pher+4.054
cream+3.720
displayText+3.595
Neg logit contributions
 Tik-3.589
 viral-3.565
 stride-3.486
 Kik-3.328
 characteristic-3.295
Token Lee
Token ID5741
Feature activation-4.46e-01

Pos logit contributions
nesday+2.663
mble+2.645
pher+2.399
cream+2.176
displayText+2.047
Neg logit contributions
 stride-2.307
 viral-2.299
 Tik-2.270
uni-2.166
 characteristic-2.153
Token back
Token ID736
Feature activation-1.36e-01

Pos logit contributions
nesday+0.322
mble+0.321
pher+0.294
cream+0.273
displayText+0.264
Neg logit contributions
 Tik-0.159
 viral-0.158
 stride-0.154
 Kik-0.145
uni-0.142
Token burner
Token ID46027
Feature activation+6.74e-01

Pos logit contributions
 Tik+0.450
 viral+0.449
 stride+0.437
 Kik+0.420
 characteristic+0.414
Neg logit contributions
nesday-0.565
mble-0.563
pher-0.506
cream-0.466
displayText-0.444
Token,
Token ID11
Feature activation-8.39e-02

Pos logit contributions
nesday+3.113
mble+3.080
pher+2.822
cream+2.609
displayText+2.507
Neg logit contributions
 Tik-1.886
 viral-1.868
 stride-1.814
 Kik-1.740
uni-1.703
Token I
Token ID314
Feature activation+5.22e-02

Pos logit contributions
 Tik+0.218
 viral+0.217
 stride+0.210
 Kik+0.199
 characteristic+0.195
Neg logit contributions
nesday-0.407
mble-0.405
pher-0.371
cream-0.343
displayText-0.332
Token was
Token ID373
Feature activation+6.81e-01

Pos logit contributions
nesday+0.235
mble+0.234
pher+0.212
cream+0.195
displayText+0.188
Neg logit contributions
 viral-0.156
 Tik-0.155
 stride-0.150
 Kik-0.144
 characteristic-0.141
Token freed
Token ID13459
Feature activation+2.86e+00

Pos logit contributions
nesday+3.074
mble+3.061
pher+2.818
cream+2.573
displayText+2.492
Neg logit contributions
 Tik-1.966
 viral-1.943
 stride-1.872
 Kik-1.802
 characteristic-1.764
Token up
Token ID510
Feature activation+8.08e-01

Pos logit contributions
nesday+10.884
mble+10.759
pher+9.819
cream+9.103
displayText+8.379
Neg logit contributions
 Tik-8.490
 viral-8.018
 Kik-7.845
 Gujar-7.786
 stride-7.743
Token to
Token ID284
Feature activation+7.53e-01

Pos logit contributions
nesday+3.351
mble+3.341
pher+3.017
cream+2.753
displayText+2.647
Neg logit contributions
 Tik-2.607
 viral-2.579
 stride-2.492
 Kik-2.414
uni-2.385
Token focus
Token ID2962
Feature activation+1.97e-01

Pos logit contributions
nesday+3.493
mble+3.455
pher+3.220
cream+2.911
displayText+2.835
Neg logit contributions
 Tik-2.055
 viral-2.028
 stride-1.920
 Kik-1.896
uni-1.846
Token on
Token ID319
Feature activation+5.78e-03

Pos logit contributions
nesday+0.949
mble+0.944
pher+0.864
cream+0.800
displayText+0.773
Neg logit contributions
 Tik-0.519
 viral-0.513
 stride-0.499
 Kik-0.475
 characteristic-0.463
Token authentic
Token ID16425
Feature activation+8.34e-01

Pos logit contributions
nesday+0.027
mble+0.027
pher+0.024
cream+0.022
displayText+0.022
Neg logit contributions
 viral-0.016
 Tik-0.016
 stride-0.016
 Kik-0.015
 characteristic-0.015
Token Ob
Token ID1835
Feature activation-1.08e-01

Pos logit contributions
mble+0.401
nesday+0.401
pher+0.364
cream+0.336
displayText+0.324
Neg logit contributions
 Tik-0.238
 viral-0.237
 stride-0.230
 Kik-0.219
uni-0.215
Tokenamas
Token ID17485
Feature activation-1.02e-01

Pos logit contributions
 viral+0.268
 Tik+0.266
 stride+0.258
 Kik+0.243
uni+0.240
Neg logit contributions
nesday-0.541
mble-0.537
pher-0.486
cream-0.454
displayText-0.443
Token announced
Token ID3414
Feature activation+1.83e-01

Pos logit contributions
 viral+0.308
 Tik+0.307
 stride+0.298
 Kik+0.284
 characteristic+0.280
Neg logit contributions
nesday-0.455
mble-0.452
pher-0.407
cream-0.375
displayText-0.362
Token they
Token ID484
Feature activation-8.57e-02

Pos logit contributions
nesday+0.881
mble+0.876
pher+0.799
cream+0.739
displayText+0.713
Neg logit contributions
 viral-0.485
 Tik-0.485
 stride-0.468
 Kik-0.447
uni-0.436
Token were
Token ID547
Feature activation+4.44e-01

Pos logit contributions
 viral+0.258
 Tik+0.257
 stride+0.250
 Kik+0.239
 characteristic+0.235
Neg logit contributions
nesday-0.383
mble-0.381
pher-0.344
cream-0.317
displayText-0.306
Token cur
Token ID1090
Feature activation+2.84e+00

Pos logit contributions
nesday+2.010
mble+2.005
pher+1.832
cream+1.675
displayText+1.617
Neg logit contributions
 Tik-1.287
 viral-1.281
 stride-1.236
 Kik-1.188
uni-1.166
Tokent
Token ID83
Feature activation+7.71e-01

Pos logit contributions
nesday+9.052
mble+8.565
pher+8.165
cream+7.042
ationally+6.527
Neg logit contributions
 viral-10.812
 Tik-10.609
 stride-10.587
 Kik-10.383
 characteristic-10.037
Tokenailing
Token ID11608
Feature activation+3.71e-01

Pos logit contributions
nesday+3.935
mble+3.903
pher+3.608
cream+3.333
displayText+3.251
Neg logit contributions
 viral-1.822
 Tik-1.819
 stride-1.742
 Kik-1.654
 characteristic-1.607
Token (
Token ID357
Feature activation+1.95e+00

Pos logit contributions
nesday+1.702
mble+1.702
pher+1.541
cream+1.422
displayText+1.357
Neg logit contributions
 Tik-1.045
 viral-1.038
 stride-1.010
 Kik-0.977
uni-0.955
Tokenban
Token ID3820
Feature activation+3.23e-01

Pos logit contributions
mble+7.432
nesday+7.393
pher+6.866
cream+6.421
displayText+5.890
Neg logit contributions
 Tik-6.504
 viral-6.346
 stride-6.294
 Kik-6.042
 characteristic-5.905
Tokenning
Token ID768
Feature activation+1.76e-01

Pos logit contributions
nesday+1.104
mble+1.099
pher+0.963
cream+0.855
displayText+0.805
Neg logit contributions
 viral-1.304
 Tik-1.303
 stride-1.274
 Kik-1.235
 characteristic-1.216
Token Manga
Token ID27024
Feature activation-9.53e-01

Pos logit contributions
 viral+2.547
 Tik+2.541
 stride+2.443
 Kik+2.348
 characteristic+2.298
Neg logit contributions
nesday-4.296
mble-4.275
pher-3.874
cream-3.579
displayText-3.490
Token Award
Token ID11289
Feature activation-8.76e-01

Pos logit contributions
 Tik+2.957
 viral+2.953
 stride+2.847
 Kik+2.748
 characteristic+2.699
Neg logit contributions
nesday-4.172
mble-4.159
pher-3.730
cream-3.427
displayText-3.326
Token in
Token ID287
Feature activation-4.97e-01

Pos logit contributions
 viral+2.179
 Tik+2.173
 stride+2.084
 Kik+1.984
 characteristic+1.952
Neg logit contributions
nesday-4.371
mble-4.347
pher-3.972
cream-3.682
displayText-3.589
Token the
Token ID262
Feature activation-2.46e-01

Pos logit contributions
 viral+1.338
 Tik+1.332
 stride+1.289
 Kik+1.220
 characteristic+1.200
Neg logit contributions
nesday-2.378
mble-2.368
pher-2.156
cream-1.996
displayText-1.926
Token Sh
Token ID911
Feature activation-8.49e-01

Pos logit contributions
 viral+0.642
 Tik+0.639
 stride+0.619
 Kik+0.581
 characteristic+0.573
Neg logit contributions
nesday-1.189
mble-1.186
pher-1.081
cream-1.003
displayText-0.964
Tokenō
Token ID13090
Feature activation-3.24e+00

Pos logit contributions
 viral+2.236
 Tik+2.232
 stride+2.154
 Kik+2.047
 characteristic+2.008
Neg logit contributions
nesday-4.116
mble-4.085
pher-3.716
cream-3.449
displayText-3.345
Tokenjo
Token ID7639
Feature activation-1.88e+00

Pos logit contributions
 Tik+7.309
 viral+7.299
 Kik+7.006
uni+6.877
 stride+6.635
Neg logit contributions
nesday-15.347
mble-14.682
pher-13.426
displayText-12.706
cream-12.443
Token category
Token ID6536
Feature activation-3.06e-01

Pos logit contributions
 Tik+5.194
 viral+5.121
 Kik+4.959
 stride+4.898
uni+4.627
Neg logit contributions
nesday-8.756
mble-8.706
pher-7.824
cream-7.274
displayText-7.113
Token.[
Token ID3693
Feature activation-7.68e-01

Pos logit contributions
 viral+0.708
 Tik+0.706
 stride+0.679
 Kik+0.635
 characteristic+0.620
Neg logit contributions
nesday-1.575
mble-1.568
pher-1.442
cream-1.346
displayText-1.299
Token16
Token ID1433
Feature activation+4.75e-02

Pos logit contributions
 viral+1.957
 Tik+1.944
 stride+1.884
 Kik+1.777
uni+1.755
Neg logit contributions
nesday-3.801
mble-3.762
pher-3.408
cream-3.141
displayText-3.063
Token]
Token ID60
Feature activation-4.59e-01

Pos logit contributions
nesday+0.194
mble+0.193
pher+0.174
cream+0.158
displayText+0.153
Neg logit contributions
 viral-0.160
 Tik-0.160
 stride-0.156
 Kik-0.149
 characteristic-0.147
Token i
Token ID1312
Feature activation-1.73e-01

Pos logit contributions
 viral+0.606
 Tik+0.603
 stride+0.586
 Kik+0.555
 characteristic+0.548
Neg logit contributions
nesday-0.964
mble-0.964
pher-0.873
cream-0.806
displayText-0.776
Token
Token ID220
Feature activation-1.17e+00

Pos logit contributions
 viral+0.304
 Tik+0.300
 stride+0.287
 Kik+0.259
 characteristic+0.257
Neg logit contributions
nesday-0.987
mble-0.986
pher-0.912
cream-0.857
displayText-0.833
Token
Token ID134
Feature activation-8.59e-01

Pos logit contributions
 Tik+1.385
 viral+1.355
 stride+1.219
 Kik+1.135
uni+1.045
Neg logit contributions
nesday-7.317
mble-7.247
pher-6.774
cream-6.392
displayText-6.244
Token
Token ID119
Feature activation-1.78e-01

Pos logit contributions
 viral+2.786
 Tik+2.758
 stride+2.661
 Kik+2.569
 characteristic+2.530
Neg logit contributions
nesday-3.712
mble-3.571
pher-3.236
cream-2.971
displayText-2.849
Tokenemo
Token ID41903
Feature activation-1.14e+00

Pos logit contributions
 viral+0.575
 Tik+0.572
 stride+0.557
 Kik+0.532
 characteristic+0.526
Neg logit contributions
nesday-0.754
mble-0.751
pher-0.676
cream-0.619
displayText-0.594
Token ko
Token ID41727
Feature activation-2.96e+00

Pos logit contributions
 viral+2.932
 Tik+2.924
 stride+2.802
 Kik+2.685
uni+2.606
Neg logit contributions
nesday-5.605
mble-5.558
pher-5.064
cream-4.708
displayText-4.576
Token Kal
Token ID12612
Feature activation-1.38e+00

Pos logit contributions
 Tik+7.503
 viral+7.461
 stride+7.008
 Kik+6.980
uni+6.821
Neg logit contributions
nesday-13.638
mble-13.381
pher-12.142
cream-11.285
displayText-11.061
Tokenan
Token ID272
Feature activation-3.73e-01

Pos logit contributions
 Tik+4.631
 viral+4.600
 stride+4.415
 Kik+4.328
uni+4.312
Neg logit contributions
nesday-5.623
mble-5.603
pher-4.966
cream-4.561
displayText-4.473
Tokenial
Token ID498
Feature activation+4.31e-01

Pos logit contributions
 viral+1.240
 Tik+1.234
 stride+1.206
 Kik+1.150
 characteristic+1.140
Neg logit contributions
nesday-1.554
mble-1.545
pher-1.384
cream-1.265
displayText-1.212
Tokeni
Token ID72
Feature activation-2.07e-01

Pos logit contributions
mble+1.454
nesday+1.453
pher+1.259
cream+1.135
displayText+1.051
Neg logit contributions
 viral-1.741
 Tik-1.718
 stride-1.708
 characteristic-1.630
 Kik-1.617
Token
Token ID134
Feature activation-1.44e-01

Pos logit contributions
 viral+0.251
 Tik+0.248
 stride+0.234
 Kik+0.197
 characteristic+0.196
Neg logit contributions
nesday-1.288
mble-1.287
pher-1.196
cream-1.133
displayText-1.107
Token You
Token ID921
Feature activation+4.72e-01

Pos logit contributions
nesday+0.955
mble+0.948
pher+0.864
cream+0.793
displayText+0.765
Neg logit contributions
 viral-0.641
 Tik-0.635
 stride-0.620
 Kik-0.589
 characteristic-0.584
Token know
Token ID760
Feature activation+9.83e-01

Pos logit contributions
nesday+2.162
mble+2.160
pher+1.969
cream+1.812
displayText+1.734
Neg logit contributions
 viral-1.343
 Tik-1.341
 stride-1.292
 Kik-1.248
 characteristic-1.224
Token how
Token ID703
Feature activation+7.28e-01

Pos logit contributions
nesday+4.154
mble+4.129
pher+3.753
cream+3.417
displayText+3.284
Neg logit contributions
 viral-3.061
 Tik-3.030
 stride-2.976
 Kik-2.881
uni-2.827
Token Batman
Token ID9827
Feature activation-1.13e+00

Pos logit contributions
nesday+3.460
mble+3.437
pher+3.191
cream+2.900
displayText+2.778
Neg logit contributions
 Tik-1.874
 viral-1.865
 stride-1.820
 Kik-1.755
uni-1.705
Token is
Token ID318
Feature activation-3.68e-01

Pos logit contributions
 viral+3.096
 Tik+3.073
 stride+2.979
 Kik+2.771
 characteristic+2.771
Neg logit contributions
mble-5.351
nesday-5.345
pher-4.784
cream-4.414
displayText-4.384
Token Bruce
Token ID11088
Feature activation-2.96e+00

Pos logit contributions
 viral+1.104
 Tik+1.095
 stride+1.062
 Kik+1.009
 characteristic+1.005
Neg logit contributions
nesday-1.667
mble-1.653
pher-1.483
cream-1.367
displayText-1.331
Token Wayne
Token ID13329
Feature activation-9.61e-01

Pos logit contributions
 Tik+6.130
 viral+6.028
 stride+5.932
 characteristic+5.468
 Kik+5.345
Neg logit contributions
mble-15.319
nesday-14.925
pher-13.458
cream-12.751
displayText-12.545
Token?
Token ID30
Feature activation-6.19e-01

Pos logit contributions
 viral+2.864
 Tik+2.834
 stride+2.767
 characteristic+2.608
 Kik+2.604
Neg logit contributions
nesday-4.316
mble-4.293
pher-3.853
cream-3.545
displayText-3.479
Token And
Token ID843
Feature activation+8.00e-02

Pos logit contributions
 Tik+1.896
 viral+1.873
 stride+1.805
 Kik+1.751
 characteristic+1.695
Neg logit contributions
nesday-2.776
mble-2.764
pher-2.453
cream-2.264
displayText-2.202
Token that
Token ID326
Feature activation-3.81e-01

Pos logit contributions
nesday+0.382
mble+0.380
pher+0.346
cream+0.320
displayText+0.309
Neg logit contributions
 viral-0.216
 Tik-0.215
 stride-0.208
 Kik-0.198
 characteristic-0.194
Token he
Token ID339
Feature activation-8.38e-01

Pos logit contributions
 viral+0.983
 Tik+0.977
 stride+0.944
 Kik+0.890
 characteristic+0.880
Neg logit contributions
nesday-1.872
mble-1.863
pher-1.694
cream-1.577
displayText-1.530
Token he
Token ID339
Feature activation-1.81e-01

Pos logit contributions
 viral+0.574
 Tik+0.567
 stride+0.556
uni+0.515
 Kik+0.514
Neg logit contributions
nesday-1.213
mble-1.208
pher-1.112
cream-1.033
displayText-0.997
Token summed
Token ID32794
Feature activation-2.27e-01

Pos logit contributions
 viral+0.538
 Tik+0.536
 stride+0.520
 Kik+0.496
 characteristic+0.489
Neg logit contributions
nesday-0.815
mble-0.810
pher-0.732
cream-0.675
displayText-0.652
Token up
Token ID510
Feature activation+2.84e-01

Pos logit contributions
 viral+0.659
 Tik+0.657
 stride+0.638
 Kik+0.607
 characteristic+0.598
Neg logit contributions
nesday-1.040
mble-1.036
pher-0.938
cream-0.866
displayText-0.834
Token Z
Token ID1168
Feature activation-3.29e-01

Pos logit contributions
mble+1.311
nesday+1.305
pher+1.189
cream+1.098
displayText+1.052
Neg logit contributions
 viral-0.783
 Tik-0.779
 stride-0.759
uni-0.722
 Kik-0.717
Tokent
Token ID83
Feature activation-1.02e+00

Pos logit contributions
 viral+1.052
 Tik+1.047
 stride+1.017
 Kik+0.976
 characteristic+0.961
Neg logit contributions
nesday-1.412
mble-1.410
pher-1.273
cream-1.163
displayText-1.112
Tokenoh
Token ID1219
Feature activation-2.95e+00

Pos logit contributions
 viral+3.195
 Tik+3.187
 stride+3.090
 Kik+2.958
 characteristic+2.913
Neg logit contributions
nesday-4.453
mble-4.417
pher-3.982
cream-3.661
displayText-3.537
Tokenoven
Token ID16206
Feature activation-3.31e-01

Pos logit contributions
 Tik+9.544
 viral+9.402
 stride+9.024
 Kik+8.668
uni+8.648
Neg logit contributions
nesday-11.532
mble-11.391
pher-9.836
cream-9.183
displayText-9.109
Token
Token ID447
Feature activation+6.03e-02

Pos logit contributions
 viral+0.777
 Tik+0.772
 stride+0.743
 Kik+0.697
 characteristic+0.685
Neg logit contributions
nesday-1.700
mble-1.692
pher-1.548
cream-1.442
displayText-1.403
Token
Token ID247
Feature activation+4.24e-02

Pos logit contributions
nesday+0.269
mble+0.269
pher+0.243
cream+0.223
displayText+0.216
Neg logit contributions
 Tik-0.181
 viral-0.180
 stride-0.173
 Kik-0.167
 characteristic-0.164
Tokens
Token ID82
Feature activation-9.48e-01

Pos logit contributions
nesday+0.207
mble+0.206
pher+0.188
cream+0.175
displayText+0.168
Neg logit contributions
 viral-0.110
 Tik-0.110
 stride-0.106
 Kik-0.101
 characteristic-0.098
Token larger
Token ID4025
Feature activation-6.64e-01

Pos logit contributions
 viral+2.407
 Tik+2.382
 stride+2.318
 Kik+2.174
 characteristic+2.161
Neg logit contributions
nesday-4.718
mble-4.686
pher-4.271
cream-3.970
displayText-3.881
Token
Token ID120
Feature activation-9.96e-01

Pos logit contributions
 viral+6.454
 Tik+6.279
 stride+6.032
 characteristic+5.706
 Kik+5.590
Neg logit contributions
nesday-12.007
mble-11.286
pher-10.288
displayText-9.477
cream-9.431
Token
Token ID223
Feature activation-1.71e+00

Pos logit contributions
 viral+3.525
 Tik+3.493
 stride+3.366
 Kik+3.267
 characteristic+3.233
Neg logit contributions
nesday-3.911
mble-3.886
pher-3.429
cream-3.136
displayText-3.026
Tokenρ
Token ID33643
Feature activation-1.76e+00

Pos logit contributions
 viral+5.153
 Tik+5.131
 stride+4.869
 Kik+4.748
 characteristic+4.661
Neg logit contributions
mble-7.533
nesday-7.447
pher-6.569
cream-6.112
displayText-6.031
Tokenπ
Token ID46582
Feature activation-1.75e+00

Pos logit contributions
 Tik+4.761
 viral+4.757
 stride+4.470
 Kik+4.388
 characteristic+4.268
Neg logit contributions
mble-8.221
nesday-8.162
pher-7.227
cream-6.783
displayText-6.605
Tokenα
Token ID17394
Feature activation-1.73e+00

Pos logit contributions
 viral+4.612
 Tik+4.599
 stride+4.264
 Kik+4.233
 characteristic+4.118
Neg logit contributions
nesday-8.334
mble-8.288
pher-7.361
cream-6.864
displayText-6.694
Tokenγ
Token ID42063
Feature activation-2.95e+00

Pos logit contributions
 viral+5.338
 Tik+5.261
 stride+5.045
 Kik+4.925
 characteristic+4.833
Neg logit contributions
mble-7.552
nesday-7.520
pher-6.623
cream-6.126
displayText-5.983
Token
Token ID157
Feature activation-2.52e+00

Pos logit contributions
 viral+7.529
 Tik+7.420
 stride+6.970
 Kik+6.881
 Gujar+6.786
Neg logit contributions
nesday-13.437
mble-13.331
pher-11.556
cream-10.965
displayText-10.808
Token
Token ID123
Feature activation-7.47e-01

Pos logit contributions
 viral+7.246
 Tik+7.076
 stride+6.682
 Gujar+6.446
uni+6.400
Neg logit contributions
nesday-10.997
mble-10.392
pher-9.384
displayText-8.757
cream-8.598
Token
Token ID228
Feature activation-1.18e+00

Pos logit contributions
 viral+2.540
 Tik+2.518
 stride+2.446
 Kik+2.363
 characteristic+2.326
Neg logit contributions
nesday-3.059
mble-3.026
pher-2.700
cream-2.474
displayText-2.389
Tokenς
Token ID35558
Feature activation-2.11e+00

Pos logit contributions
 viral+4.305
 Tik+4.295
 stride+4.125
 Kik+4.030
 characteristic+3.976
Neg logit contributions
mble-4.511
nesday-4.504
pher-3.906
cream-3.584
displayText-3.469
Token (
Token ID357
Feature activation-4.75e-03

Pos logit contributions
 viral+5.076
 Tik+5.028
 stride+4.661
 Kik+4.585
 characteristic+4.500
Neg logit contributions
mble-10.544
nesday-10.495
pher-9.395
cream-8.812
displayText-8.610
Token me
Token ID502
Feature activation+5.04e-01

Pos logit contributions
 viral+0.243
 Tik+0.241
 stride+0.235
 Kik+0.219
 characteristic+0.217
Neg logit contributions
nesday-0.475
mble-0.474
pher-0.434
cream-0.402
displayText-0.388
Token ke
Token ID885
Feature activation+3.69e-01

Pos logit contributions
mble+1.723
nesday+1.702
pher+1.513
cream+1.338
displayText+1.245
Neg logit contributions
 viral-2.010
 Tik-1.997
 stride-1.967
 Kik-1.879
 characteristic-1.878
Token k
Token ID479
Feature activation-1.31e+00

Pos logit contributions
mble+1.891
nesday+1.889
pher+1.743
cream+1.614
displayText+1.549
Neg logit contributions
 viral-0.834
 Tik-0.821
 stride-0.811
 characteristic-0.739
 Kik-0.735
Tokenah
Token ID993
Feature activation-1.70e+00

Pos logit contributions
 Tik+3.752
 viral+3.719
 stride+3.567
 Kik+3.473
uni+3.471
Neg logit contributions
nesday-5.977
mble-5.925
pher-5.347
cream-4.946
displayText-4.834
Tokenuk
Token ID2724
Feature activation-1.22e+00

Pos logit contributions
 Tik+5.181
 viral+5.118
 stride+4.905
 Kik+4.781
uni+4.776
Neg logit contributions
nesday-7.450
mble-7.331
pher-6.585
cream-6.085
displayText-5.973
Tokenahu
Token ID12196
Feature activation-2.94e+00

Pos logit contributions
 Tik+3.715
 viral+3.702
 stride+3.557
 Kik+3.446
uni+3.445
Neg logit contributions
nesday-5.335
mble-5.285
pher-4.758
cream-4.390
displayText-4.280
Token i
Token ID1312
Feature activation-4.55e-01

Pos logit contributions
 Tik+8.103
 viral+7.958
 Kik+7.591
 Hawai+7.457
 stride+7.443
Neg logit contributions
nesday-12.945
mble-12.762
pher-11.472
cream-10.721
displayText-10.574
Token ka
Token ID38387
Feature activation-1.57e+00

Pos logit contributions
 viral+0.907
 Tik+0.901
 stride+0.863
 Kik+0.798
 characteristic+0.784
Neg logit contributions
nesday-2.492
mble-2.483
pher-2.289
cream-2.143
displayText-2.082
Token pil
Token ID5560
Feature activation+1.17e-01

Pos logit contributions
 Tik+3.773
 viral+3.755
 stride+3.551
 Kik+3.438
uni+3.305
Neg logit contributions
nesday-7.953
mble-7.898
pher-7.196
cream-6.724
displayText-6.572
Tokenina
Token ID1437
Feature activation-4.43e-01

Pos logit contributions
mble+0.542
nesday+0.541
pher+0.494
cream+0.454
displayText+0.435
Neg logit contributions
 viral-0.327
 Tik-0.323
 stride-0.317
 Kik-0.298
 characteristic-0.295
Token
Token ID220
Feature activation-9.97e-01

Pos logit contributions
 viral+1.131
 Tik+1.124
 stride+1.088
 Kik+1.025
 characteristic+1.010
Neg logit contributions
nesday-2.182
mble-2.173
pher-1.984
cream-1.841
displayText-1.782
Token
Token ID198
Feature activation+1.96e-01

Pos logit contributions
 viral+0.779
 Tik+0.774
 stride+0.734
 Kik+0.687
 characteristic+0.661
Neg logit contributions
nesday-2.237
mble-2.236
pher-1.983
cream-1.868
displayText-1.826
TokenSplit
Token ID41205
Feature activation+1.43e+00

Pos logit contributions
nesday+0.828
mble+0.826
pher+0.744
cream+0.684
displayText+0.657
Neg logit contributions
 viral-0.637
 Tik-0.636
 stride-0.619
 Kik-0.590
 characteristic-0.583
Token release
Token ID2650
Feature activation+1.50e-01

Pos logit contributions
nesday+6.625
mble+6.576
pher+5.990
cream+5.540
displayText+5.309
Neg logit contributions
 viral-3.705
 Tik-3.693
 stride-3.597
uni-3.407
 Kik-3.376
Token with
Token ID351
Feature activation+1.91e-01

Pos logit contributions
nesday+0.732
mble+0.731
pher+0.664
cream+0.618
displayText+0.597
Neg logit contributions
 Tik-0.384
 viral-0.383
 stride-0.372
 Kik-0.349
uni-0.345
Token Yam
Token ID14063
Feature activation-2.08e+00

Pos logit contributions
nesday+0.912
mble+0.908
pher+0.826
cream+0.767
displayText+0.739
Neg logit contributions
 viral-0.504
 Tik-0.502
 stride-0.489
 Kik-0.460
uni-0.456
Token Yam
Token ID14063
Feature activation-2.90e+00

Pos logit contributions
 Tik+6.236
 viral+6.205
 stride+5.898
 Kik+5.777
uni+5.764
Neg logit contributions
nesday-8.990
mble-8.883
pher-7.904
cream-7.356
displayText-7.239
Token Records
Token ID13407
Feature activation-1.43e-01

Pos logit contributions
 Tik+8.694
 viral+8.472
 Kik+8.146
 stride+8.016
 Yam+7.815
Neg logit contributions
nesday-11.938
mble-11.736
pher-10.480
cream-9.594
displayText-9.561
Token
Token ID198
Feature activation-4.98e-01

Pos logit contributions
 viral+0.365
 Tik+0.363
 stride+0.352
 Kik+0.330
 characteristic+0.325
Neg logit contributions
nesday-0.702
mble-0.700
pher-0.637
cream-0.594
displayText-0.572
Token
Token ID198
Feature activation+4.50e-03

Pos logit contributions
 viral+0.968
 Tik+0.963
 stride+0.909
 Kik+0.852
 doi+0.822
Neg logit contributions
nesday-2.825
mble-2.822
pher-2.498
cream-2.356
displayText-2.301
Token1
Token ID16
Feature activation+1.41e-01

Pos logit contributions
nesday+0.018
mble+0.018
pher+0.016
cream+0.015
displayText+0.014
Neg logit contributions
 viral-0.016
 Tik-0.016
 stride-0.015
 Kik-0.015
 characteristic-0.014
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
mble+0.664
nesday+0.663
pher+0.602
cream+0.557
displayText+0.539
Neg logit contributions
 viral-0.387
 Tik-0.385
 stride-0.375
 Kik-0.354
 characteristic-0.349
Token costs
Token ID3484
Feature activation+4.08e-01

Pos logit contributions
mble+2.499
nesday+2.498
pher+2.289
cream+2.114
displayText+2.017
Neg logit contributions
 Tik-1.604
 viral-1.571
 stride-1.548
 Kik-1.488
uni-1.458
Token is
Token ID318
Feature activation+4.00e-01

Pos logit contributions
nesday+1.935
mble+1.926
pher+1.770
cream+1.633
displayText+1.573
Neg logit contributions
 Tik-1.092
 viral-1.091
 stride-1.051
 Kik-1.008
uni-0.981
Token built
Token ID3170
Feature activation+4.41e-01

Pos logit contributions
nesday+1.851
mble+1.841
pher+1.682
cream+1.556
displayText+1.493
Neg logit contributions
 Tik-1.105
 viral-1.104
 stride-1.073
 Kik-1.019
uni-1.000
Token upon
Token ID2402
Feature activation-1.25e-01

Pos logit contributions
nesday+2.102
mble+2.097
pher+1.918
cream+1.770
displayText+1.712
Neg logit contributions
 Tik-1.171
 viral-1.154
 stride-1.121
 Kik-1.079
uni-1.037
Token a
Token ID257
Feature activation-4.46e-01

Pos logit contributions
 viral+0.348
 Tik+0.347
 stride+0.336
 Kik+0.319
 characteristic+0.313
Neg logit contributions
nesday-0.585
mble-0.583
pher-0.530
cream-0.490
displayText-0.473
Token widely
Token ID6768
Feature activation-2.89e+00

Pos logit contributions
 viral+1.097
 Tik+1.091
 stride+1.050
 Kik+0.992
 characteristic+0.975
Neg logit contributions
nesday-2.242
mble-2.230
pher-2.039
cream-1.897
displayText-1.841
Token used
Token ID973
Feature activation-6.18e-01

Pos logit contributions
 viral+6.708
 Tik+6.030
 characteristic+6.016
 stride+5.806
 search+5.706
Neg logit contributions
nesday-14.479
mble-14.470
pher-12.376
cream-12.083
displayText-12.078
Token methodology
Token ID20411
Feature activation-1.83e-01

Pos logit contributions
 viral+1.572
 Tik+1.555
 stride+1.502
 Kik+1.419
 characteristic+1.406
Neg logit contributions
nesday-3.077
mble-3.050
pher-2.786
cream-2.588
displayText-2.511
Token introduced
Token ID5495
Feature activation+2.85e-01

Pos logit contributions
 viral+0.501
 Tik+0.499
 stride+0.482
 Kik+0.458
 characteristic+0.452
Neg logit contributions
nesday-0.869
mble-0.864
pher-0.785
cream-0.726
displayText-0.703
Token in
Token ID287
Feature activation-3.12e-01

Pos logit contributions
nesday+1.325
mble+1.316
pher+1.198
cream+1.104
displayText+1.066
Neg logit contributions
 viral-0.800
 Tik-0.799
 stride-0.775
 Kik-0.738
 characteristic-0.723
Token 2010
Token ID3050
Feature activation-6.39e-01

Pos logit contributions
 viral+0.806
 Tik+0.803
 stride+0.774
 Kik+0.734
 characteristic+0.720
Neg logit contributions
nesday-1.524
mble-1.517
pher-1.384
cream-1.284
displayText-1.243
Token not
Token ID407
Feature activation-2.93e-02

Pos logit contributions
 viral+1.753
 Tik+1.736
 stride+1.675
 Kik+1.584
 characteristic+1.561
Neg logit contributions
nesday-3.416
mble-3.398
pher-3.091
cream-2.874
displayText-2.794
Token signing
Token ID8415
Feature activation-3.95e-01

Pos logit contributions
 viral+0.083
 Tik+0.083
 stride+0.080
 Kik+0.076
 characteristic+0.075
Neg logit contributions
nesday-0.136
mble-0.136
pher-0.123
cream-0.114
displayText-0.110
Token the
Token ID262
Feature activation-1.21e-02

Pos logit contributions
 viral+1.099
 Tik+1.095
 stride+1.060
 Kik+1.008
 characteristic+0.992
Neg logit contributions
nesday-1.857
mble-1.847
pher-1.678
cream-1.551
displayText-1.500
Token mailed
Token ID37789
Feature activation+6.42e-02

Pos logit contributions
 Tik+0.033
 viral+0.033
 stride+0.032
 Kik+0.031
 characteristic+0.030
Neg logit contributions
nesday-0.057
mble-0.056
pher-0.051
cream-0.047
displayText-0.046
Token out
Token ID503
Feature activation+3.31e-01

Pos logit contributions
nesday+0.305
mble+0.304
pher+0.278
cream+0.257
displayText+0.247
Neg logit contributions
 Tik-0.172
 viral-0.171
 stride-0.167
 Kik-0.158
uni-0.156
Token ballot
Token ID11100
Feature activation-2.84e+00

Pos logit contributions
mble+1.586
nesday+1.586
pher+1.454
cream+1.346
displayText+1.294
Neg logit contributions
 Tik-0.856
 viral-0.850
 stride-0.833
 Kik-0.784
uni-0.777
Token questionnaire
Token ID28301
Feature activation-6.60e-01

Pos logit contributions
 viral+7.004
 Tik+6.755
 stride+6.476
 characteristic+6.245
 Kik+6.200
Neg logit contributions
mble-13.530
nesday-13.339
pher-12.017
cream-11.080
displayText-11.070
Token at
Token ID379
Feature activation+7.65e-02

Pos logit contributions
 viral+1.773
 Tik+1.757
 stride+1.697
 Kik+1.610
 characteristic+1.590
Neg logit contributions
nesday-3.173
mble-3.162
pher-2.871
cream-2.665
displayText-2.587
Token the
Token ID262
Feature activation-1.73e-01

Pos logit contributions
nesday+0.351
mble+0.349
pher+0.316
cream+0.291
displayText+0.280
Neg logit contributions
 viral-0.219
 Tik-0.219
 stride-0.211
 Kik-0.202
uni-0.198
Token bottom
Token ID4220
Feature activation+1.05e-02

Pos logit contributions
 viral+0.473
 Tik+0.472
 stride+0.456
 Kik+0.434
 characteristic+0.425
Neg logit contributions
nesday-0.824
mble-0.820
pher-0.745
cream-0.688
displayText-0.668
Token in
Token ID287
Feature activation-3.45e-01

Pos logit contributions
nesday+0.050
mble+0.050
pher+0.046
cream+0.042
displayText+0.041
Neg logit contributions
 Tik-0.028
 viral-0.027
 stride-0.027
 Kik-0.025
uni-0.025
TokenScore
Token ID26595
Feature activation-6.34e-01

Pos logit contributions
nesday+0.043
mble+0.043
pher+0.039
cream+0.036
displayText+0.035
Neg logit contributions
 viral-0.022
 Tik-0.022
 stride-0.021
 Kik-0.020
 characteristic-0.020
Token esports
Token ID37407
Feature activation-7.51e-01

Pos logit contributions
 viral+1.400
 Tik+1.382
 stride+1.312
 Kik+1.254
 characteristic+1.222
Neg logit contributions
nesday-3.347
mble-3.317
pher-3.046
cream-2.840
displayText-2.771
Token.
Token ID13
Feature activation-7.65e-01

Pos logit contributions
 viral+1.748
 Tik+1.738
 stride+1.669
 Kik+1.577
 characteristic+1.544
Neg logit contributions
nesday-3.867
mble-3.848
pher-3.533
cream-3.288
displayText-3.203
Token You
Token ID921
Feature activation-6.75e-01

Pos logit contributions
 Tik+1.928
 viral+1.912
 stride+1.823
 Kik+1.772
 characteristic+1.706
Neg logit contributions
nesday-3.810
mble-3.780
pher-3.430
cream-3.204
displayText-3.114
Token can
Token ID460
Feature activation-1.65e+00

Pos logit contributions
 viral+1.451
 Tik+1.441
 stride+1.379
 Kik+1.296
 characteristic+1.267
Neg logit contributions
nesday-3.606
mble-3.589
pher-3.297
cream-3.081
displayText-3.002
Token follow
Token ID1061
Feature activation-2.80e+00

Pos logit contributions
 viral+3.083
 Tik+2.932
 stride+2.894
 characteristic+2.644
 Kik+2.637
Neg logit contributions
mble-9.194
nesday-9.158
pher-8.468
cream-7.932
displayText-7.787
Token him
Token ID683
Feature activation-1.50e+00

Pos logit contributions
 Tik+9.883
 viral+9.806
 stride+9.423
 Kik+9.108
 characteristic+9.102
Neg logit contributions
mble-9.982
nesday-9.957
pher-8.956
cream-8.144
displayText-7.608
Token on
Token ID319
Feature activation-2.37e+00

Pos logit contributions
 viral+3.293
 Tik+3.242
 stride+3.107
 Kik+2.911
 characteristic+2.892
Neg logit contributions
mble-7.876
nesday-7.866
pher-7.136
cream-6.689
displayText-6.523
Token Twitter
Token ID3009
Feature activation-1.89e+00

Pos logit contributions
 viral+4.571
 Tik+4.416
 stride+4.232
 Kik+4.230
 ".+3.822
Neg logit contributions
mble-12.809
nesday-12.710
pher-11.703
cream-11.139
displayText-10.826
Token.
Token ID13
Feature activation-7.66e-01

Pos logit contributions
 viral+3.920
 Tik+3.895
 stride+3.625
 Kik+3.620
 characteristic+3.409
Neg logit contributions
mble-9.837
nesday-9.836
pher-9.060
cream-8.414
displayText-8.157
Token<|endoftext|>
Token ID50256
Feature activation-2.84e-02

Pos logit contributions
 viral+1.730
 Tik+1.729
 stride+1.640
 Kik+1.562
 characteristic+1.519
Neg logit contributions
nesday-4.006
mble-3.979
pher-3.644
cream-3.402
displayText-3.300
Token
Token ID25001
Feature activation-1.77e+00

Pos logit contributions
 viral+7.354
 Tik+7.192
 stride+6.949
 Kik+6.887
 characteristic+6.802
Neg logit contributions
nesday-11.876
mble-11.636
pher-10.536
cream-9.606
displayText-9.562
Token
Token ID245
Feature activation-1.76e+00

Pos logit contributions
 viral+5.139
 Tik+5.064
 stride+4.884
 Kik+4.736
 characteristic+4.701
Neg logit contributions
nesday-7.769
mble-7.669
pher-6.939
cream-6.412
displayText-6.271
Token
Token ID165
Feature activation-1.35e+00

Pos logit contributions
 viral+5.036
 Tik+4.945
 stride+4.811
 Kik+4.694
 characteristic+4.612
Neg logit contributions
nesday-7.916
mble-7.860
pher-7.095
cream-6.510
displayText-6.322
Token
Token ID246
Feature activation-6.09e-01

Pos logit contributions
 viral+4.592
 Tik+4.556
 stride+4.425
 Kik+4.264
 characteristic+4.223
Neg logit contributions
nesday-5.404
mble-5.279
pher-4.770
cream-4.350
displayText-4.226
Token
Token ID253
Feature activation-1.80e+00

Pos logit contributions
 viral+2.025
 Tik+2.017
 stride+1.959
 Kik+1.886
 characteristic+1.857
Neg logit contributions
nesday-2.541
mble-2.517
pher-2.257
cream-2.061
displayText-1.992
Token
Token ID17312
Feature activation-2.80e+00

Pos logit contributions
 viral+5.050
 Tik+4.942
 stride+4.826
 Kik+4.699
 characteristic+4.601
Neg logit contributions
nesday-8.127
mble-8.122
pher-7.336
cream-6.669
displayText-6.576
Token
Token ID235
Feature activation-1.94e+00

Pos logit contributions
 Tik+8.685
 viral+8.583
 stride+8.527
 Kik+8.084
 characteristic+8.026
Neg logit contributions
nesday-11.050
mble-10.959
pher-9.791
cream-8.842
displayText-8.611
Token,
Token ID11
Feature activation-8.89e-01

Pos logit contributions
 viral+5.455
 Tik+5.348
 stride+5.229
 Kik+5.110
 characteristic+4.991
Neg logit contributions
nesday-8.706
mble-8.618
pher-7.790
cream-7.114
displayText-6.946
Token which
Token ID543
Feature activation+1.38e-01

Pos logit contributions
 viral+2.327
 Tik+2.306
 stride+2.223
 Kik+2.134
 characteristic+2.096
Neg logit contributions
nesday-4.317
mble-4.302
pher-3.906
cream-3.624
displayText-3.540
Token means
Token ID1724
Feature activation-1.01e+00

Pos logit contributions
nesday+0.630
mble+0.626
pher+0.569
cream+0.523
displayText+0.502
Neg logit contributions
 Tik-0.400
 viral-0.399
 stride-0.388
 Kik-0.367
 characteristic-0.362
Token
Token ID564
Feature activation-1.29e+00

Pos logit contributions
 viral+2.461
 Tik+2.425
 stride+2.350
 Kik+2.227
 characteristic+2.188
Neg logit contributions
nesday-5.104
mble-5.063
pher-4.647
cream-4.305
displayText-4.230
Token due
Token ID2233
Feature activation+7.10e-01

Pos logit contributions
 viral+0.299
 Tik+0.297
 stride+0.286
 Kik+0.270
 characteristic+0.266
Neg logit contributions
nesday-0.610
mble-0.608
pher-0.554
cream-0.516
displayText-0.501
Token to
Token ID284
Feature activation+3.01e-01

Pos logit contributions
nesday+2.988
mble+2.968
pher+2.677
cream+2.445
displayText+2.354
Neg logit contributions
 Tik-2.303
 viral-2.302
 stride-2.237
 Kik-2.145
 characteristic-2.113
Token the
Token ID262
Feature activation+2.60e-02

Pos logit contributions
mble+1.382
nesday+1.382
pher+1.252
cream+1.158
displayText+1.109
Neg logit contributions
 Tik-0.845
 viral-0.833
 stride-0.821
 Kik-0.775
uni-0.774
Token 2011
Token ID2813
Feature activation-1.02e+00

Pos logit contributions
nesday+0.125
mble+0.125
pher+0.114
cream+0.106
displayText+0.102
Neg logit contributions
 Tik-0.067
 viral-0.067
 stride-0.065
 Kik-0.061
uni-0.061
Token T
Token ID309
Feature activation-5.50e-01

Pos logit contributions
 viral+2.796
 Tik+2.758
 stride+2.650
 Kik+2.547
 characteristic+2.492
Neg logit contributions
nesday-4.857
mble-4.802
pher-4.373
cream-4.061
displayText-3.934
Tokenoh
Token ID1219
Feature activation-2.79e+00

Pos logit contributions
 viral+1.670
 Tik+1.666
 stride+1.614
 Kik+1.541
 characteristic+1.520
Neg logit contributions
nesday-2.447
mble-2.436
pher-2.199
cream-2.023
displayText-1.952
Tokenoku
Token ID11601
Feature activation-2.02e+00

Pos logit contributions
 Tik+4.107
 viral+3.711
 Kik+3.372
 stride+3.355
uni+3.183
Neg logit contributions
nesday-16.170
mble-15.946
pher-14.382
displayText-13.809
cream-13.609
Token Earthquake
Token ID45591
Feature activation+4.49e-01

Pos logit contributions
 viral+5.654
 Tik+5.645
 Kik+5.426
 stride+5.280
 squid+5.074
Neg logit contributions
mble-9.256
nesday-9.099
pher-8.272
cream-7.699
displayText-7.544
Token,
Token ID11
Feature activation-4.15e-01

Pos logit contributions
nesday+2.109
mble+2.090
pher+1.920
cream+1.778
displayText+1.708
Neg logit contributions
 Tik-1.200
 viral-1.191
 stride-1.166
uni-1.101
 Kik-1.090
Token and
Token ID290
Feature activation-4.31e-01

Pos logit contributions
 viral+0.951
 Tik+0.947
 stride+0.910
 Kik+0.855
 characteristic+0.838
Neg logit contributions
nesday-2.152
mble-2.141
pher-1.964
cream-1.831
displayText-1.778
Token went
Token ID1816
Feature activation-8.86e-01

Pos logit contributions
 viral+1.199
 Tik+1.194
 stride+1.153
 Kik+1.099
 characteristic+1.080
Neg logit contributions
nesday-2.033
mble-2.023
pher-1.837
cream-1.700
displayText-1.644
Token last
Token ID938
Feature activation-6.10e-01

Pos logit contributions
 viral+1.385
 Tik+1.377
 stride+1.330
 Kik+1.267
 characteristic+1.249
Neg logit contributions
nesday-2.271
mble-2.260
pher-2.042
cream-1.892
displayText-1.826
Token year
Token ID614
Feature activation-9.11e-01

Pos logit contributions
 viral+1.390
 Tik+1.383
 stride+1.328
 Kik+1.245
 characteristic+1.222
Neg logit contributions
nesday-3.181
mble-3.168
pher-2.904
cream-2.709
displayText-2.629
Token
Token ID447
Feature activation+2.43e-01

Pos logit contributions
 viral+1.937
 Tik+1.911
 stride+1.821
 Kik+1.695
 characteristic+1.661
Neg logit contributions
mble-4.896
nesday-4.889
pher-4.449
cream-4.200
displayText-4.056
Token
Token ID247
Feature activation+5.07e-01

Pos logit contributions
nesday+1.186
mble+1.174
pher+1.067
cream+0.989
displayText+0.956
Neg logit contributions
 viral-0.646
 Tik-0.636
 stride-0.620
 Kik-0.584
 characteristic-0.575
Tokens
Token ID82
Feature activation-5.00e-01

Pos logit contributions
nesday+2.312
mble+2.284
pher+2.102
cream+1.927
displayText+1.865
Neg logit contributions
 Tik-1.452
 viral-1.450
 stride-1.412
 Kik-1.351
 characteristic-1.322
Token ballot
Token ID11100
Feature activation-2.77e+00

Pos logit contributions
 viral+1.374
 Tik+1.368
 stride+1.322
 Kik+1.255
 characteristic+1.236
Neg logit contributions
nesday-2.369
mble-2.357
pher-2.140
cream-1.982
displayText-1.916
Token initiative
Token ID10219
Feature activation-9.94e-01

Pos logit contributions
 viral+7.340
 stride+7.099
 Tik+7.062
 characteristic+6.634
 Kik+6.595
Neg logit contributions
mble-12.846
nesday-12.651
pher-11.252
cream-10.561
displayText-9.953
Token that
Token ID326
Feature activation-1.57e-01

Pos logit contributions
 viral+2.899
 Tik+2.868
 stride+2.758
 Kik+2.655
 characteristic+2.615
Neg logit contributions
mble-4.564
nesday-4.551
pher-4.043
cream-3.794
displayText-3.633
Token would
Token ID561
Feature activation+1.60e-01

Pos logit contributions
 viral+0.471
 Tik+0.469
 stride+0.455
 Kik+0.434
 characteristic+0.428
Neg logit contributions
nesday-0.705
mble-0.701
pher-0.632
cream-0.583
displayText-0.562
Token have
Token ID423
Feature activation+8.10e-01

Pos logit contributions
mble+0.706
nesday+0.706
pher+0.642
cream+0.584
displayText+0.567
Neg logit contributions
 Tik-0.486
 viral-0.485
 stride-0.467
 Kik-0.451
 characteristic-0.442
Token made
Token ID925
Feature activation+8.44e-02

Pos logit contributions
mble+3.329
nesday+3.318
pher+3.070
cream+2.714
displayText+2.656
Neg logit contributions
 Tik-2.603
 viral-2.602
 stride-2.543
 Kik-2.429
uni-2.404
Token biological
Token ID10685
Feature activation-5.61e-01

Pos logit contributions
mble+1.890
nesday+1.880
pher+1.743
cream+1.612
displayText+1.543
Neg logit contributions
 Tik-0.884
 viral-0.869
 stride-0.860
 Kik-0.806
uni-0.802
Token or
Token ID393
Feature activation-9.28e-02

Pos logit contributions
 viral+1.697
 Tik+1.689
 stride+1.639
 Kik+1.565
 characteristic+1.544
Neg logit contributions
nesday-2.506
mble-2.491
pher-2.247
cream-2.070
displayText-2.001
Token chemical
Token ID5931
Feature activation+1.41e+00

Pos logit contributions
 Tik+0.200
 viral+0.196
 stride+0.192
 Kik+0.180
uni+0.173
Neg logit contributions
mble-0.489
nesday-0.488
pher-0.451
cream-0.420
displayText-0.407
Token weapons
Token ID3777
Feature activation-3.28e-01

Pos logit contributions
mble+5.378
nesday+5.336
pher+4.975
cream+4.411
ationally+4.107
Neg logit contributions
 Tik-4.633
 stride-4.498
 viral-4.487
uni-4.386
 Kik-4.317
Token by
Token ID416
Feature activation+1.13e-01

Pos logit contributions
 viral+0.886
 Tik+0.882
 stride+0.853
 Kik+0.810
 characteristic+0.796
Neg logit contributions
nesday-1.569
mble-1.561
pher-1.421
cream-1.316
displayText-1.273
Token Osama
Token ID29236
Feature activation-2.76e+00

Pos logit contributions
mble+0.531
nesday+0.530
pher+0.487
cream+0.448
displayText+0.428
Neg logit contributions
 viral-0.293
 Tik-0.293
 stride-0.290
uni-0.269
 Kik-0.268
Token bin
Token ID9874
Feature activation-1.53e+00

Pos logit contributions
 Tik+4.385
 viral+4.154
 stride+4.019
 Kik+3.808
 mu+3.596
Neg logit contributions
mble-16.188
nesday-15.788
pher-14.240
cream-13.725
displayText-13.545
Token Laden
Token ID19402
Feature activation+4.51e-02

Pos logit contributions
 Tik+3.683
 viral+3.592
 stride+3.465
 Kik+3.289
 characteristic+3.208
Neg logit contributions
mble-7.935
nesday-7.862
pher-7.051
cream-6.630
displayText-6.459
Token and
Token ID290
Feature activation-1.85e-01

Pos logit contributions
nesday+0.221
mble+0.219
pher+0.203
cream+0.188
displayText+0.181
Neg logit contributions
 viral-0.113
 Tik-0.113
 stride-0.109
 Kik-0.104
 characteristic-0.101
Token Saddam
Token ID24277
Feature activation-4.97e-01

Pos logit contributions
 viral+0.538
 Tik+0.535
 stride+0.521
 Kik+0.494
 characteristic+0.487
Neg logit contributions
nesday-0.844
mble-0.837
pher-0.761
cream-0.702
displayText-0.675
Token Hussein
Token ID22983
Feature activation-5.16e-01

Pos logit contributions
 viral+1.034
 Tik+1.025
 stride+0.987
 Kik+0.917
 characteristic+0.897
Neg logit contributions
nesday-2.683
mble-2.665
pher-2.460
cream-2.298
displayText-2.233
TokenET
Token ID2767
Feature activation+2.26e-01

Pos logit contributions
 Tik+0.873
 viral+0.866
 stride+0.831
 Kik+0.813
uni+0.784
Neg logit contributions
nesday-1.318
mble-1.304
pher-1.157
cream-1.069
displayText-1.025
Token who
Token ID508
Feature activation-2.48e-01

Pos logit contributions
nesday+1.123
mble+1.118
pher+1.019
cream+0.949
displayText+0.911
Neg logit contributions
 Tik-0.565
 viral-0.564
 stride-0.538
 Kik-0.513
uni-0.506
Token have
Token ID423
Feature activation-1.05e-01

Pos logit contributions
 viral+0.675
 Tik+0.673
 stride+0.649
 Kik+0.618
 characteristic+0.607
Neg logit contributions
nesday-1.177
mble-1.172
pher-1.067
cream-0.986
displayText-0.954
Token a
Token ID257
Feature activation-5.38e-01

Pos logit contributions
 viral+0.316
 Tik+0.315
 stride+0.306
 Kik+0.292
 characteristic+0.288
Neg logit contributions
nesday-0.471
mble-0.468
pher-0.422
cream-0.390
displayText-0.377
Token long
Token ID890
Feature activation-1.96e+00

Pos logit contributions
 viral+1.377
 Tik+1.364
 stride+1.322
 Kik+1.244
 characteristic+1.232
Neg logit contributions
nesday-2.659
mble-2.642
pher-2.410
cream-2.240
displayText-2.180
Token standing
Token ID5055
Feature activation-2.74e+00

Pos logit contributions
 viral+3.948
 stride+3.912
 Tik+3.775
 characteristic+3.467
 Kik+3.409
Neg logit contributions
nesday-10.533
mble-10.352
pher-9.578
cream-8.998
displayText-8.978
Token heritage
Token ID15012
Feature activation-1.41e+00

Pos logit contributions
 viral+6.057
 stride+5.958
 Tik+5.722
 characteristic+5.614
 search+5.388
Neg logit contributions
nesday-13.644
mble-13.375
pher-12.294
displayText-11.655
cream-11.551
Token as
Token ID355
Feature activation-1.11e-01

Pos logit contributions
 viral+3.386
 Tik+3.318
 stride+3.251
 characteristic+3.046
 Kik+3.020
Neg logit contributions
nesday-7.118
mble-7.056
pher-6.411
cream-5.992
displayText-5.911
Token a
Token ID257
Feature activation-2.65e-01

Pos logit contributions
 viral+0.317
 Tik+0.316
 stride+0.306
 Kik+0.292
 characteristic+0.286
Neg logit contributions
nesday-0.515
mble-0.512
pher-0.465
cream-0.429
displayText-0.414
Token recogn
Token ID3018
Feature activation+4.83e-01

Pos logit contributions
 viral+0.706
 Tik+0.704
 stride+0.680
 Kik+0.646
 characteristic+0.633
Neg logit contributions
nesday-1.273
mble-1.268
pher-1.155
cream-1.069
displayText-1.034
Tokenisable
Token ID43942
Feature activation-2.11e-01

Pos logit contributions
nesday+1.975
mble+1.963
pher+1.783
cream+1.622
displayText+1.547
Neg logit contributions
 viral-1.618
 Tik-1.615
 stride-1.568
 Kik-1.502
 characteristic-1.480
Token band
Token ID4097
Feature activation-8.85e-01

Pos logit contributions
mble+4.254
nesday+4.253
pher+3.861
cream+3.550
displayText+3.458
Neg logit contributions
 Tik-2.289
 viral-2.232
 stride-2.186
uni-2.111
 Kik-2.110
Token is
Token ID318
Feature activation-6.48e-01

Pos logit contributions
 viral+2.324
 Tik+2.307
 stride+2.239
 Kik+2.104
 characteristic+2.101
Neg logit contributions
nesday-4.270
mble-4.249
pher-3.856
cream-3.582
displayText-3.488
Token led
Token ID2957
Feature activation+8.42e-01

Pos logit contributions
 viral+1.781
 Tik+1.761
 stride+1.704
 Kik+1.619
 characteristic+1.608
Neg logit contributions
nesday-3.092
mble-3.061
pher-2.778
cream-2.579
displayText-2.508
Token by
Token ID416
Feature activation-2.19e-01

Pos logit contributions
nesday+3.640
mble+3.616
pher+3.285
cream+2.985
displayText+2.875
Neg logit contributions
 Tik-2.580
 viral-2.544
 stride-2.510
 Kik-2.420
 squid-2.339
Token P
Token ID350
Feature activation-1.48e+00

Pos logit contributions
 viral+0.630
 Tik+0.629
 stride+0.610
 Kik+0.580
 characteristic+0.572
Neg logit contributions
nesday-1.001
mble-0.998
pher-0.903
cream-0.832
displayText-0.803
Tokenoh
Token ID1219
Feature activation-2.73e+00

Pos logit contributions
 viral+4.683
 Tik+4.646
 stride+4.505
 Kik+4.348
uni+4.295
Neg logit contributions
nesday-6.269
mble-6.198
pher-5.564
cream-5.123
displayText-5.008
Tokenj
Token ID73
Feature activation-1.32e+00

Pos logit contributions
 Tik+9.385
 viral+9.273
 Kik+8.750
 stride+8.735
uni+8.586
Neg logit contributions
nesday-10.171
mble-10.001
pher-8.717
displayText-8.153
cream-7.922
Tokenola
Token ID5708
Feature activation-8.69e-01

Pos logit contributions
 Tik+4.199
 viral+4.185
 stride+4.002
 Kik+3.919
uni+3.867
Neg logit contributions
nesday-5.532
mble-5.492
pher-4.892
cream-4.527
displayText-4.401
Token on
Token ID319
Feature activation-1.09e+00

Pos logit contributions
 viral+2.307
 Tik+2.306
 stride+2.217
 Kik+2.122
 characteristic+2.068
Neg logit contributions
nesday-4.201
mble-4.174
pher-3.796
cream-3.526
displayText-3.423
Token piano
Token ID19132
Feature activation+5.40e-01

Pos logit contributions
 viral+2.901
 Tik+2.879
 stride+2.789
 Kik+2.654
 characteristic+2.612
Neg logit contributions
nesday-5.220
mble-5.185
pher-4.724
cream-4.388
displayText-4.280
Token,
Token ID11
Feature activation-3.30e-01

Pos logit contributions
mble+2.647
nesday+2.626
pher+2.425
cream+2.246
displayText+2.133
Neg logit contributions
 viral-1.368
 Tik-1.356
 stride-1.296
uni-1.238
 Kik-1.228
Token
Token ID239
Feature activation-4.04e-01

Pos logit contributions
 viral+3.634
 Tik+3.616
 stride+3.491
 Kik+3.360
uni+3.330
Neg logit contributions
nesday-4.916
mble-4.788
pher-4.360
cream-3.967
displayText-3.842
Token
Token ID46349
Feature activation-2.24e+00

Pos logit contributions
 viral+1.114
 Tik+1.109
 stride+1.072
 Kik+1.022
 characteristic+1.004
Neg logit contributions
nesday-1.912
mble-1.902
pher-1.728
cream-1.598
displayText-1.547
Token
Token ID111
Feature activation-1.83e+00

Pos logit contributions
 viral+6.084
 Tik+6.062
 stride+5.747
 Kik+5.548
uni+5.471
Neg logit contributions
nesday-10.315
mble-9.878
pher-9.213
cream-8.414
displayText-8.206
Token
Token ID17358
Feature activation-1.08e+00

Pos logit contributions
 viral+5.248
 Tik+5.170
 stride+4.981
 Kik+4.929
 characteristic+4.825
Neg logit contributions
nesday-8.117
mble-8.035
pher-7.273
cream-6.696
displayText-6.535
Token
Token ID223
Feature activation-1.10e+00

Pos logit contributions
 viral+3.841
 Tik+3.805
 stride+3.702
 Kik+3.585
 characteristic+3.560
Neg logit contributions
nesday-4.180
mble-4.159
pher-3.725
cream-3.366
displayText-3.242
Token
Token ID31660
Feature activation-2.73e+00

Pos logit contributions
 viral+3.042
 Tik+3.001
 stride+2.915
 Kik+2.822
 characteristic+2.766
Neg logit contributions
nesday-5.177
mble-5.152
pher-4.669
cream-4.309
displayText-4.186
Token
Token ID25001
Feature activation-1.77e+00

Pos logit contributions
 viral+7.354
 Tik+7.192
 stride+6.949
 Kik+6.887
 characteristic+6.802
Neg logit contributions
nesday-11.876
mble-11.636
pher-10.536
cream-9.606
displayText-9.562
Token
Token ID245
Feature activation-1.76e+00

Pos logit contributions
 viral+5.139
 Tik+5.064
 stride+4.884
 Kik+4.736
 characteristic+4.701
Neg logit contributions
nesday-7.769
mble-7.669
pher-6.939
cream-6.412
displayText-6.271
Token
Token ID165
Feature activation-1.35e+00

Pos logit contributions
 viral+5.036
 Tik+4.945
 stride+4.811
 Kik+4.694
 characteristic+4.612
Neg logit contributions
nesday-7.916
mble-7.860
pher-7.095
cream-6.510
displayText-6.322
Token
Token ID246
Feature activation-6.09e-01

Pos logit contributions
 viral+4.592
 Tik+4.556
 stride+4.425
 Kik+4.264
 characteristic+4.223
Neg logit contributions
nesday-5.404
mble-5.279
pher-4.770
cream-4.350
displayText-4.226
Token
Token ID253
Feature activation-1.80e+00

Pos logit contributions
 viral+2.025
 Tik+2.017
 stride+1.959
 Kik+1.886
 characteristic+1.857
Neg logit contributions
nesday-2.541
mble-2.517
pher-2.257
cream-2.061
displayText-1.992
Token charge
Token ID3877
Feature activation-2.00e-01

Pos logit contributions
mble+5.057
nesday+5.022
pher+4.692
cream+4.303
displayText+4.122
Neg logit contributions
 Tik-2.702
 viral-2.632
 stride-2.584
uni-2.546
 Kik-2.462
Token.
Token ID13
Feature activation+2.12e-03

Pos logit contributions
 Tik+0.512
 viral+0.509
 stride+0.490
 Kik+0.467
uni+0.458
Neg logit contributions
nesday-0.976
mble-0.971
pher-0.891
cream-0.827
displayText-0.794
Token These
Token ID2312
Feature activation+2.15e-01

Pos logit contributions
nesday+0.010
mble+0.010
pher+0.009
cream+0.009
displayText+0.008
Neg logit contributions
 viral-0.006
 Tik-0.006
 stride-0.005
 characteristic-0.005
 Kik-0.005
Token "
Token ID366
Feature activation+3.82e-01

Pos logit contributions
nesday+1.002
mble+0.999
pher+0.908
cream+0.838
displayText+0.805
Neg logit contributions
 Tik-0.587
 viral-0.583
 stride-0.574
 Kik-0.543
uni-0.534
TokenB
Token ID33
Feature activation-1.45e+00

Pos logit contributions
nesday+1.570
mble+1.564
pher+1.412
cream+1.296
displayText+1.232
Neg logit contributions
 Tik-1.276
 viral-1.274
 stride-1.246
 Kik-1.187
 characteristic-1.171
Tokenaghd
Token ID16650
Feature activation-2.71e+00

Pos logit contributions
 viral+3.842
 Tik+3.810
 stride+3.626
uni+3.492
 Kik+3.486
Neg logit contributions
nesday-6.850
mble-6.821
pher-6.150
cream-5.744
displayText-5.609
Tokenad
Token ID324
Feature activation-3.15e-01

Pos logit contributions
 Tik+6.726
 viral+6.626
uni+6.414
 stride+6.100
 characteristic+5.865
Neg logit contributions
mble-12.824
nesday-12.758
pher-11.361
cream-10.773
displayText-10.370
Token batteries
Token ID13591
Feature activation+4.47e-03

Pos logit contributions
 viral+0.946
 Tik+0.942
 stride+0.916
 Kik+0.873
 characteristic+0.860
Neg logit contributions
nesday-1.409
mble-1.402
pher-1.268
cream-1.166
displayText-1.124
Token"
Token ID1
Feature activation-2.98e-01

Pos logit contributions
nesday+0.021
mble+0.021
pher+0.019
cream+0.017
displayText+0.017
Neg logit contributions
 viral-0.013
 Tik-0.013
 stride-0.012
 Kik-0.012
 characteristic-0.011
Token may
Token ID743
Feature activation-6.49e-01

Pos logit contributions
 viral+0.827
 Tik+0.824
 stride+0.797
 Kik+0.759
 characteristic+0.745
Neg logit contributions
nesday-1.401
mble-1.393
pher-1.268
cream-1.172
displayText-1.130
Token have
Token ID423
Feature activation-2.74e-02

Pos logit contributions
 viral+1.881
 Tik+1.863
 stride+1.822
 Kik+1.714
 characteristic+1.713
Neg logit contributions
nesday-2.979
mble-2.965
pher-2.674
cream-2.479
displayText-2.407
Token by
Token ID416
Feature activation+8.04e-02

Pos logit contributions
nesday+4.715
mble+4.690
pher+4.301
cream+3.905
displayText+3.671
Neg logit contributions
 Tik-3.258
 viral-3.233
 stride-3.159
uni-3.034
 Kik-3.010
Token the
Token ID262
Feature activation-8.82e-02

Pos logit contributions
nesday+0.370
mble+0.368
pher+0.334
cream+0.309
displayText+0.295
Neg logit contributions
 Tik-0.228
 viral-0.227
 stride-0.222
 Kik-0.210
uni-0.208
Token vulnerability
Token ID15131
Feature activation+2.32e-02

Pos logit contributions
 Tik+0.231
 viral+0.230
 stride+0.223
 Kik+0.211
uni+0.207
Neg logit contributions
nesday-0.426
mble-0.424
pher-0.386
cream-0.359
displayText-0.346
Token of
Token ID286
Feature activation+5.90e-01

Pos logit contributions
nesday+0.113
mble+0.113
pher+0.103
cream+0.096
displayText+0.092
Neg logit contributions
 Tik-0.059
 viral-0.059
 stride-0.057
 Kik-0.054
uni-0.053
Token his
Token ID465
Feature activation-7.41e-01

Pos logit contributions
nesday+2.490
mble+2.485
pher+2.251
cream+2.048
displayText+1.920
Neg logit contributions
 Tik-1.848
 viral-1.846
 stride-1.802
uni-1.712
 Kik-1.709
Token prog
Token ID1172
Feature activation-2.70e+00

Pos logit contributions
 viral+1.738
 Tik+1.717
 stride+1.666
 Kik+1.562
 characteristic+1.545
Neg logit contributions
nesday-3.829
mble-3.801
pher-3.476
cream-3.243
displayText-3.169
Tokeneny
Token ID28558
Feature activation-6.15e-01

Pos logit contributions
 viral+8.129
 Tik+7.819
 stride+7.798
uni+7.691
 Kik+7.626
Neg logit contributions
nesday-10.938
mble-10.597
pher-9.330
displayText-8.967
cream-8.685
Token,
Token ID11
Feature activation-1.17e-01

Pos logit contributions
 viral+1.655
 Tik+1.647
 stride+1.587
 Kik+1.512
 characteristic+1.496
Neg logit contributions
nesday-2.961
mble-2.944
pher-2.665
cream-2.473
displayText-2.414
Token that
Token ID326
Feature activation-2.17e-03

Pos logit contributions
 viral+0.328
 Tik+0.327
 stride+0.317
 Kik+0.299
uni+0.296
Neg logit contributions
nesday-0.548
mble-0.544
pher-0.496
cream-0.457
displayText-0.439
Token he
Token ID339
Feature activation-6.28e-01

Pos logit contributions
 viral+0.006
 Tik+0.006
 stride+0.006
 Kik+0.006
uni+0.005
Neg logit contributions
nesday-0.010
mble-0.010
pher-0.009
cream-0.008
displayText-0.008
Token began
Token ID2540
Feature activation+6.91e-01

Pos logit contributions
 viral+1.911
 Tik+1.897
 stride+1.849
 characteristic+1.756
 Kik+1.755
Neg logit contributions
nesday-2.808
mble-2.804
pher-2.476
cream-2.307
displayText-2.240
Token Hall
Token ID4789
Feature activation-1.26e+00

Pos logit contributions
 viral+0.626
 Tik+0.622
 stride+0.606
 Kik+0.577
 characteristic+0.567
Neg logit contributions
nesday-0.962
mble-0.957
pher-0.868
cream-0.798
displayText-0.771
Token Collection
Token ID12251
Feature activation+6.77e-01

Pos logit contributions
 Tik+3.037
 viral+3.032
 stride+2.879
 Kik+2.737
 characteristic+2.727
Neg logit contributions
nesday-6.368
mble-6.321
pher-5.773
cream-5.383
displayText-5.229
Token,
Token ID11
Feature activation+1.78e-01

Pos logit contributions
nesday+3.408
mble+3.378
pher+3.115
cream+2.902
displayText+2.840
Neg logit contributions
 viral-1.560
 Tik-1.539
 stride-1.521
 Kik-1.422
 squid-1.364
Token replacing
Token ID13586
Feature activation-8.37e-02

Pos logit contributions
nesday+0.852
mble+0.841
pher+0.773
cream+0.713
displayText+0.688
Neg logit contributions
 viral-0.474
 Tik-0.469
 stride-0.458
 Kik-0.433
uni-0.422
Token Confederate
Token ID21900
Feature activation+1.53e-02

Pos logit contributions
 viral+0.245
 Tik+0.244
 stride+0.238
 Kik+0.225
 characteristic+0.222
Neg logit contributions
nesday-0.380
mble-0.377
pher-0.343
cream-0.315
displayText-0.303
Token General
Token ID3611
Feature activation-2.69e+00

Pos logit contributions
nesday+0.073
mble+0.072
pher+0.066
cream+0.061
displayText+0.059
Neg logit contributions
 viral-0.041
 Tik-0.041
 stride-0.039
 Kik-0.037
uni-0.037
Token Edmund
Token ID35646
Feature activation+4.68e-01

Pos logit contributions
 Tik+8.310
 viral+8.022
 stride+7.950
 Kik+7.553
 characteristic+7.441
Neg logit contributions
mble-11.370
nesday-11.279
pher-9.864
cream-9.204
displayText-9.103
Token Kirby
Token ID23965
Feature activation+9.02e-02

Pos logit contributions
nesday+2.088
mble+2.011
pher+1.888
cream+1.711
displayText+1.625
Neg logit contributions
 viral-1.395
 Tik-1.356
 stride-1.346
 characteristic-1.259
uni-1.259
Token Smith
Token ID4176
Feature activation-4.82e-01

Pos logit contributions
nesday+0.442
mble+0.440
pher+0.406
cream+0.377
displayText+0.364
Neg logit contributions
 viral-0.227
 Tik-0.223
 stride-0.218
 Kik-0.202
uni-0.200
Token.[
Token ID3693
Feature activation+1.31e-02

Pos logit contributions
 viral+1.127
 Tik+1.120
 stride+1.078
 Kik+1.013
 characteristic+0.993
Neg logit contributions
nesday-2.478
mble-2.465
pher-2.262
cream-2.109
displayText-2.046
Token7
Token ID22
Feature activation-2.06e-02

Pos logit contributions
nesday+0.060
mble+0.060
pher+0.054
cream+0.050
displayText+0.048
Neg logit contributions
 viral-0.038
 Tik-0.038
 stride-0.036
 Kik-0.035
 characteristic-0.034
TokenAL
Token ID1847
Feature activation+4.30e-01

Pos logit contributions
nesday+0.273
mble+0.272
pher+0.236
cream+0.213
displayText+0.203
Neg logit contributions
 Tik-0.316
 viral-0.314
 stride-0.308
 Kik-0.298
uni-0.295
TokenEM
Token ID3620
Feature activation+4.46e-01

Pos logit contributions
nesday+1.814
mble+1.781
pher+1.614
cream+1.494
displayText+1.441
Neg logit contributions
 Tik-1.384
 viral-1.361
 stride-1.341
uni-1.266
 Kik-1.261
Token
Token ID851
Feature activation-4.88e-01

Pos logit contributions
nesday+1.988
mble+1.964
pher+1.802
cream+1.659
displayText+1.606
Neg logit contributions
 viral-1.315
 Tik-1.294
 stride-1.283
 Kik-1.209
 characteristic-1.204
Token Israeli
Token ID6085
Feature activation+3.22e-01

Pos logit contributions
 Tik+1.326
 viral+1.323
 stride+1.272
 Kik+1.215
 characteristic+1.189
Neg logit contributions
nesday-2.326
mble-2.321
pher-2.102
cream-1.949
displayText-1.886
Token and
Token ID290
Feature activation+4.90e-01

Pos logit contributions
nesday+1.447
mble+1.423
pher+1.303
cream+1.198
displayText+1.155
Neg logit contributions
 viral-0.950
 Tik-0.941
 stride-0.918
 Kik-0.879
uni-0.864
Token Turkish
Token ID9663
Feature activation+1.75e+00

Pos logit contributions
nesday+2.425
mble+2.391
pher+2.213
cream+2.046
displayText+1.985
Neg logit contributions
 Tik-1.191
 viral-1.183
 stride-1.162
 Kik-1.088
uni-1.079
Token officials
Token ID2828
Feature activation+1.58e-01

Pos logit contributions
nesday+6.966
mble+6.767
pher+6.339
cream+5.759
displayText+5.583
Neg logit contributions
 Tik-5.261
 viral-5.201
 stride-5.075
uni-4.973
 Kik-4.949
Token have
Token ID423
Feature activation+6.04e-02

Pos logit contributions
nesday+0.714
mble+0.708
pher+0.645
cream+0.592
displayText+0.571
Neg logit contributions
 viral-0.470
 Tik-0.468
 stride-0.453
 Kik-0.435
 characteristic-0.426
Token reached
Token ID4251
Feature activation-1.10e-01

Pos logit contributions
nesday+0.254
mble+0.253
pher+0.227
cream+0.208
displayText+0.200
Neg logit contributions
 viral-0.198
 Tik-0.197
 stride-0.192
 Kik-0.184
 characteristic-0.181
Token a
Token ID257
Feature activation+3.41e-01

Pos logit contributions
 viral+0.332
 Tik+0.331
 stride+0.321
 Kik+0.306
 characteristic+0.302
Neg logit contributions
nesday-0.495
mble-0.492
pher-0.444
cream-0.409
displayText-0.395
Token preliminary
Token ID15223
Feature activation+4.59e-01

Pos logit contributions
nesday+1.510
mble+1.503
pher+1.362
cream+1.250
displayText+1.208
Neg logit contributions
 Tik-1.024
 viral-1.021
 stride-0.988
 Kik-0.954
uni-0.934
Token.
Token ID13
Feature activation-9.35e-02

Pos logit contributions
 viral+1.097
 Tik+1.093
 stride+1.056
 Kik+1.003
 characteristic+0.988
Neg logit contributions
nesday-1.940
mble-1.929
pher-1.753
cream-1.625
displayText-1.574
Token The
Token ID383
Feature activation+4.30e-01

Pos logit contributions
 viral+0.249
 Tik+0.247
 stride+0.240
 Kik+0.227
 characteristic+0.222
Neg logit contributions
nesday-0.448
mble-0.447
pher-0.409
cream-0.377
displayText-0.365
Token Blessed
Token ID33398
Feature activation+5.29e-02

Pos logit contributions
mble+1.970
nesday+1.959
pher+1.792
cream+1.647
displayText+1.575
Neg logit contributions
 viral-1.209
 Tik-1.201
 stride-1.170
 Kik-1.119
uni-1.077
Token Trinity
Token ID22844
Feature activation+6.15e-02

Pos logit contributions
nesday+0.228
mble+0.226
pher+0.206
cream+0.189
displayText+0.180
Neg logit contributions
 viral-0.167
 Tik-0.165
 stride-0.162
 Kik-0.154
 characteristic-0.151
Token.
Token ID13
Feature activation-1.93e-01

Pos logit contributions
nesday+0.298
mble+0.297
pher+0.274
cream+0.252
displayText+0.244
Neg logit contributions
 viral-0.160
 Tik-0.159
 stride-0.154
 Kik-0.145
 characteristic-0.141
Token Creation
Token ID21582
Feature activation+1.91e+00

Pos logit contributions
 viral+0.520
 Tik+0.515
 stride+0.500
 Kik+0.474
 characteristic+0.465
Neg logit contributions
nesday-0.924
mble-0.920
pher-0.840
cream-0.776
displayText-0.750
Token.
Token ID13
Feature activation+7.60e-02

Pos logit contributions
nesday+8.472
mble+8.428
pher+7.849
cream+7.147
displayText+6.875
Neg logit contributions
 viral-5.000
 Tik-4.914
 stride-4.809
 Kik-4.642
 squid-4.523
Token The
Token ID383
Feature activation+2.33e-01

Pos logit contributions
nesday+0.345
mble+0.344
pher+0.314
cream+0.289
displayText+0.277
Neg logit contributions
 viral-0.220
 Tik-0.217
 stride-0.213
 Kik-0.201
 characteristic-0.198
Token Angels
Token ID17654
Feature activation-2.16e-01

Pos logit contributions
mble+1.062
nesday+1.060
pher+0.963
cream+0.887
displayText+0.846
Neg logit contributions
 viral-0.672
 Tik-0.669
 stride-0.653
 Kik-0.621
 characteristic-0.604
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
 viral+0.537
 Tik+0.533
 stride+0.513
 Kik+0.485
 characteristic+0.475
Neg logit contributions
nesday-1.081
mble-1.077
pher-0.986
cream-0.917
displayText-0.887
Token The
Token ID383
Feature activation+2.24e-02

Pos logit contributions
 viral+0.739
 Tik+0.733
 stride+0.714
 Kik+0.677
 characteristic+0.668
Neg logit contributions
nesday-1.192
mble-1.186
pher-1.079
cream-0.995
displayText-0.959
Token simple
Token ID2829
Feature activation+1.80e-01

Pos logit contributions
 viral+1.904
 Tik+1.881
 stride+1.818
 Kik+1.723
 characteristic+1.707
Neg logit contributions
nesday-3.316
mble-3.288
pher-2.980
cream-2.763
displayText-2.688
Token tasks
Token ID8861
Feature activation+2.11e-01

Pos logit contributions
mble+0.800
nesday+0.799
pher+0.727
cream+0.668
displayText+0.642
Neg logit contributions
 Tik-0.529
 viral-0.525
 stride-0.514
 Kik-0.492
uni-0.484
Token that
Token ID326
Feature activation-3.67e-01

Pos logit contributions
nesday+0.961
mble+0.955
pher+0.872
cream+0.806
displayText+0.773
Neg logit contributions
 Tik-0.606
 viral-0.600
 stride-0.583
 Kik-0.559
uni-0.547
Token should
Token ID815
Feature activation-5.28e-01

Pos logit contributions
 viral+0.967
 Tik+0.963
 stride+0.930
 Kik+0.882
 characteristic+0.867
Neg logit contributions
nesday-1.779
mble-1.770
pher-1.612
cream-1.495
displayText-1.448
Token be
Token ID307
Feature activation-2.77e-01

Pos logit contributions
 viral+1.535
 Tik+1.517
 stride+1.486
 Kik+1.404
 characteristic+1.393
Neg logit contributions
nesday-2.425
mble-2.417
pher-2.175
cream-2.016
displayText-1.959
Token handled
Token ID12118
Feature activation+1.79e+00

Pos logit contributions
 viral+0.921
 Tik+0.915
 stride+0.891
 Kik+0.854
 characteristic+0.845
Neg logit contributions
nesday-1.157
mble-1.151
pher-1.027
cream-0.940
displayText-0.908
Token in
Token ID287
Feature activation-3.02e-01

Pos logit contributions
nesday+7.340
mble+7.214
pher+6.847
cream+6.231
displayText+5.722
Neg logit contributions
 Tik-5.395
 viral-5.145
 Kik-5.022
 stride-4.998
uni-4.963
Token a
Token ID257
Feature activation-3.19e-01

Pos logit contributions
 viral+0.856
 Tik+0.853
 stride+0.826
 Kik+0.786
 characteristic+0.774
Neg logit contributions
nesday-1.405
mble-1.397
pher-1.267
cream-1.170
displayText-1.133
Token few
Token ID1178
Feature activation+3.46e-01

Pos logit contributions
 viral+0.867
 Tik+0.865
 stride+0.835
 Kik+0.793
 characteristic+0.780
Neg logit contributions
nesday-1.516
mble-1.508
pher-1.373
cream-1.270
displayText-1.228
Token seconds
Token ID4201
Feature activation+4.41e-01

Pos logit contributions
nesday+1.466
mble+1.462
pher+1.329
cream+1.211
displayText+1.159
Neg logit contributions
 Tik-1.088
 viral-1.083
 stride-1.052
 Kik-1.007
uni-0.995
Token with
Token ID351
Feature activation+5.52e-01

Pos logit contributions
nesday+1.982
mble+1.981
pher+1.805
cream+1.668
displayText+1.591
Neg logit contributions
 Tik-1.284
 viral-1.263
 stride-1.224
 Kik-1.182
uni-1.164
Token Let
Token ID3914
Feature activation-6.88e-01

Pos logit contributions
nesday+0.001
mble+0.001
pher+0.001
cream+0.001
displayText+0.001
Neg logit contributions
 viral-0.000
 Tik-0.000
 stride-0.000
 Kik-0.000
 characteristic-0.000
Token us
Token ID514
Feature activation-3.02e-01

Pos logit contributions
 viral+2.034
 Tik+2.032
 stride+1.960
 Kik+1.871
 characteristic+1.853
Neg logit contributions
nesday-3.108
mble-3.095
pher-2.797
cream-2.582
displayText-2.496
Token remember
Token ID3505
Feature activation-5.47e-02

Pos logit contributions
 viral+0.900
 Tik+0.898
 stride+0.865
 Kik+0.833
 characteristic+0.817
Neg logit contributions
nesday-1.360
mble-1.353
pher-1.227
cream-1.125
displayText-1.086
Token that
Token ID326
Feature activation-6.30e-01

Pos logit contributions
 viral+0.155
 Tik+0.154
 stride+0.149
 Kik+0.142
 characteristic+0.139
Neg logit contributions
nesday-0.254
mble-0.253
pher-0.229
cream-0.211
displayText-0.204
Token the
Token ID262
Feature activation-8.25e-02

Pos logit contributions
 viral+1.699
 Tik+1.692
 stride+1.634
 Kik+1.551
 characteristic+1.529
Neg logit contributions
nesday-3.022
mble-3.005
pher-2.734
cream-2.534
displayText-2.457
Token Sloven
Token ID30694
Feature activation+2.89e+00

Pos logit contributions
 viral+0.222
 Tik+0.221
 stride+0.213
 Kik+0.203
 characteristic+0.199
Neg logit contributions
nesday-0.395
mble-0.393
pher-0.357
cream-0.331
displayText-0.320
Tokenian
Token ID666
Feature activation+1.01e+00

Pos logit contributions
nesday+8.973
mble+8.719
pher+7.992
cream+6.983
displayText+6.555
Neg logit contributions
 Tik-10.713
 viral-10.645
 stride-10.331
 Kik-10.136
 Hawai-10.036
Token government
Token ID1230
Feature activation+1.54e-01

Pos logit contributions
nesday+4.628
mble+4.594
pher+4.201
cream+3.884
displayText+3.760
Neg logit contributions
 Tik-2.758
 viral-2.756
 stride-2.651
 Kik-2.527
uni-2.518
Token declared
Token ID6875
Feature activation-8.20e-01

Pos logit contributions
nesday+0.724
mble+0.718
pher+0.658
cream+0.606
displayText+0.587
Neg logit contributions
 viral-0.424
 Tik-0.423
 stride-0.408
 Kik-0.390
 characteristic-0.381
Token independence
Token ID10404
Feature activation-7.08e-01

Pos logit contributions
 viral+2.597
 Tik+2.585
 stride+2.512
 Kik+2.393
 characteristic+2.382
Neg logit contributions
nesday-3.525
mble-3.508
pher-3.162
cream-2.911
displayText-2.815
Token in
Token ID287
Feature activation-5.06e-01

Pos logit contributions
 viral+1.797
 Tik+1.781
 stride+1.724
 Kik+1.618
 characteristic+1.612
Neg logit contributions
mble-3.502
nesday-3.498
pher-3.172
cream-2.949
displayText-2.867
Token Us
Token ID4021
Feature activation+4.06e-01

Pos logit contributions
nesday+0.631
mble+0.626
pher+0.575
cream+0.533
displayText+0.511
Neg logit contributions
 viral-0.367
 Tik-0.364
 stride-0.359
 Kik-0.334
 characteristic-0.331
Token,
Token ID11
Feature activation-4.83e-01

Pos logit contributions
mble+1.828
nesday+1.821
pher+1.650
cream+1.539
displayText+1.468
Neg logit contributions
 viral-1.182
 Tik-1.161
 stride-1.150
 Kik-1.081
uni-1.074
Token Matt
Token ID4705
Feature activation+3.94e-01

Pos logit contributions
 viral+1.367
 Tik+1.365
 stride+1.315
 Kik+1.258
 characteristic+1.234
Neg logit contributions
nesday-2.250
mble-2.238
pher-2.028
cream-1.872
displayText-1.814
Tokenel
Token ID417
Feature activation+9.42e-01

Pos logit contributions
nesday+1.614
mble+1.613
pher+1.447
cream+1.311
displayText+1.248
Neg logit contributions
 viral-1.326
 Tik-1.306
 stride-1.283
 Kik-1.218
 characteristic-1.217
Token and
Token ID290
Feature activation-1.19e-01

Pos logit contributions
mble+4.106
nesday+4.085
pher+3.711
cream+3.467
displayText+3.269
Neg logit contributions
 viral-2.778
 stride-2.707
 Tik-2.684
 characteristic-2.551
 Kik-2.533
Token Ner
Token ID21783
Feature activation+1.80e+00

Pos logit contributions
 viral+0.330
 Tik+0.328
 stride+0.319
 Kik+0.301
 characteristic+0.298
Neg logit contributions
nesday-0.557
mble-0.554
pher-0.504
cream-0.466
displayText-0.449
Tokenf
Token ID69
Feature activation+5.62e-01

Pos logit contributions
mble+7.006
nesday+6.744
pher+6.374
cream+6.039
onica+5.423
Neg logit contributions
 Tik-5.966
 viral-5.962
 stride-5.852
 characteristic-5.559
 Kik-5.466
Token.
Token ID13
Feature activation-1.13e-01

Pos logit contributions
nesday+2.650
mble+2.642
pher+2.397
cream+2.267
displayText+2.119
Neg logit contributions
 viral-1.491
 Tik-1.456
 stride-1.450
 characteristic-1.346
 Kik-1.343
Token Some
Token ID2773
Feature activation+6.44e-01

Pos logit contributions
 viral+0.323
 Tik+0.319
 stride+0.313
 Kik+0.295
 characteristic+0.293
Neg logit contributions
nesday-0.521
mble-0.518
pher-0.473
cream-0.437
displayText-0.421
Token of
Token ID286
Feature activation+5.48e-01

Pos logit contributions
mble+2.956
nesday+2.939
pher+2.691
cream+2.482
displayText+2.355
Neg logit contributions
 Tik-1.761
 viral-1.747
 stride-1.728
uni-1.639
 Kik-1.635
Token these
Token ID777
Feature activation+3.09e-01

Pos logit contributions
nesday+2.465
mble+2.459
pher+2.235
cream+2.074
displayText+1.972
Neg logit contributions
 viral-1.546
 stride-1.535
 Tik-1.535
uni-1.440
 Kik-1.430
Token of
Token ID286
Feature activation+5.97e-01

Pos logit contributions
 Tik+0.195
 viral+0.195
 stride+0.189
 Kik+0.179
uni+0.176
Neg logit contributions
nesday-0.363
mble-0.361
pher-0.327
cream-0.305
displayText-0.295
Token the
Token ID262
Feature activation+2.03e-01

Pos logit contributions
nesday+2.663
mble+2.654
pher+2.368
cream+2.169
displayText+2.068
Neg logit contributions
 viral-1.739
 Tik-1.721
 stride-1.664
uni-1.637
 Kik-1.600
Token UEFA
Token ID40858
Feature activation+1.10e+00

Pos logit contributions
nesday+1.008
mble+1.005
pher+0.911
cream+0.847
displayText+0.819
Neg logit contributions
 Tik-0.506
 viral-0.505
 stride-0.484
 Kik-0.459
uni-0.456
Token Championships
Token ID24782
Feature activation-4.27e-02

Pos logit contributions
nesday+4.367
mble+4.319
pher+3.811
cream+3.476
displayText+3.245
Neg logit contributions
 Tik-3.691
 viral-3.669
 stride-3.576
 Kik-3.455
uni-3.436
Token qualifying
Token ID18677
Feature activation+1.49e-01

Pos logit contributions
 Tik+0.108
 viral+0.108
 stride+0.104
 Kik+0.099
 characteristic+0.096
Neg logit contributions
nesday-0.211
mble-0.210
pher-0.191
cream-0.178
displayText-0.171
Token tournament
Token ID7756
Feature activation+1.86e-01

Pos logit contributions
nesday+0.726
mble+0.724
pher+0.658
cream+0.611
displayText+0.588
Neg logit contributions
 Tik-0.382
 viral-0.382
 stride-0.365
 Kik-0.348
uni-0.344
Token in
Token ID287
Feature activation-7.29e-02

Pos logit contributions
nesday+0.899
mble+0.893
pher+0.809
cream+0.752
displayText+0.721
Neg logit contributions
 Tik-0.490
 viral-0.489
 stride-0.470
 Kik-0.448
uni-0.441
Token October
Token ID3267
Feature activation-5.02e-03

Pos logit contributions
 viral+0.196
 Tik+0.195
 stride+0.188
 Kik+0.179
uni+0.176
Neg logit contributions
nesday-0.349
mble-0.346
pher-0.315
cream-0.291
displayText-0.281
Token.
Token ID13
Feature activation+6.84e-01

Pos logit contributions
 viral+0.012
 Tik+0.012
 stride+0.012
 Kik+0.011
 characteristic+0.011
Neg logit contributions
nesday-0.025
mble-0.025
pher-0.023
cream-0.021
displayText-0.021
Token
Token ID447
Feature activation+1.60e-01

Pos logit contributions
nesday+3.211
mble+3.179
pher+2.928
cream+2.733
displayText+2.627
Neg logit contributions
 viral-1.829
 stride-1.770
 Tik-1.747
 characteristic-1.664
 squid-1.631
Token
Token ID251
Feature activation-2.11e-01

Pos logit contributions
mble+0.525
nesday+0.523
pher+0.454
cream+0.401
displayText+0.378
Neg logit contributions
 Tik-0.673
 viral-0.671
 stride-0.657
 Kik-0.637
 characteristic-0.630
Token day
Token ID1110
Feature activation-9.16e-01

Pos logit contributions
 Tik+1.322
 viral+1.321
 stride+1.259
 Kik+1.181
 characteristic+1.155
Neg logit contributions
nesday-3.352
mble-3.335
pher-3.068
cream-2.864
displayText-2.781
Token.
Token ID13
Feature activation-1.09e-01

Pos logit contributions
 viral+2.649
 Tik+2.623
 stride+2.543
 Kik+2.432
 characteristic+2.392
Neg logit contributions
nesday-4.235
mble-4.212
pher-3.796
cream-3.512
displayText-3.415
Token
Token ID198
Feature activation-3.87e-01

Pos logit contributions
 viral+0.310
 Tik+0.309
 stride+0.300
 Kik+0.284
 characteristic+0.281
Neg logit contributions
nesday-0.509
mble-0.506
pher-0.460
cream-0.424
displayText-0.410
Token
Token ID198
Feature activation+2.33e-01

Pos logit contributions
 Tik+0.763
 viral+0.762
 stride+0.715
 Kik+0.677
 characteristic+0.647
Neg logit contributions
mble-2.179
nesday-2.179
pher-1.931
cream-1.817
displayText-1.779
TokenWhat
Token ID2061
Feature activation+1.26e+00

Pos logit contributions
nesday+0.862
mble+0.858
pher+0.763
cream+0.688
displayText+0.656
Neg logit contributions
 viral-0.876
 Tik-0.873
 stride-0.854
 Kik-0.820
 characteristic-0.813
Token does
Token ID857
Feature activation+1.52e-01

Pos logit contributions
nesday+5.604
mble+5.560
pher+5.112
cream+4.621
displayText+4.467
Neg logit contributions
 Tik-3.377
 viral-3.359
 stride-3.349
uni-3.202
 squid-3.140
Token this
Token ID428
Feature activation+5.58e-01

Pos logit contributions
nesday+0.709
mble+0.702
pher+0.640
cream+0.589
displayText+0.562
Neg logit contributions
 Tik-0.421
 viral-0.419
 stride-0.407
 Kik-0.386
uni-0.383
Token mean
Token ID1612
Feature activation-3.25e-02

Pos logit contributions
nesday+2.346
mble+2.333
pher+2.095
cream+1.917
displayText+1.817
Neg logit contributions
 Tik-1.779
 viral-1.759
 stride-1.711
 Kik-1.672
uni-1.636
Token?
Token ID30
Feature activation-4.95e-01

Pos logit contributions
 Tik+0.097
 viral+0.097
 stride+0.094
 Kik+0.090
 characteristic+0.088
Neg logit contributions
nesday-0.146
mble-0.145
pher-0.131
cream-0.121
displayText-0.116
Token A
Token ID317
Feature activation-2.71e-01

Pos logit contributions
 Tik+1.407
 viral+1.407
 stride+1.350
 Kik+1.298
 characteristic+1.265
Neg logit contributions
nesday-2.311
mble-2.300
pher-2.073
cream-1.918
displayText-1.861
Token lot
Token ID1256
Feature activation+7.39e-01

Pos logit contributions
 Tik+0.669
 viral+0.669
 stride+0.643
 Kik+0.608
 characteristic+0.596
Neg logit contributions
nesday-1.354
mble-1.347
pher-1.231
cream-1.144
displayText-1.106
Token that
Token ID326
Feature activation-6.33e-01

Pos logit contributions
 viral+0.353
 Tik+0.352
 stride+0.339
 Kik+0.324
 characteristic+0.314
Neg logit contributions
nesday-0.666
mble-0.664
pher-0.608
cream-0.566
displayText-0.544
Token can
Token ID460
Feature activation-1.84e-01

Pos logit contributions
 viral+1.655
 Tik+1.650
 stride+1.587
 Kik+1.508
 characteristic+1.484
Neg logit contributions
nesday-3.089
mble-3.072
pher-2.794
cream-2.596
displayText-2.515
Token help
Token ID1037
Feature activation+6.63e-02

Pos logit contributions
 viral+0.511
 Tik+0.510
 stride+0.492
 Kik+0.470
 characteristic+0.461
Neg logit contributions
nesday-0.863
mble-0.858
pher-0.782
cream-0.722
displayText-0.697
Token rejuven
Token ID46834
Feature activation+8.36e-01

Pos logit contributions
mble+0.308
nesday+0.307
pher+0.281
cream+0.258
displayText+0.248
Neg logit contributions
 viral-0.184
 Tik-0.184
 stride-0.177
 Kik-0.169
 characteristic-0.167
Tokenate
Token ID378
Feature activation-1.44e-01

Pos logit contributions
mble+2.814
nesday+2.797
pher+2.472
cream+2.200
displayText+2.054
Neg logit contributions
 Tik-3.409
 viral-3.397
 stride-3.293
 Kik-3.211
 characteristic-3.192
Token both
Token ID1111
Feature activation+8.11e-01

Pos logit contributions
 viral+0.385
 Tik+0.384
 stride+0.374
 Kik+0.353
 characteristic+0.349
Neg logit contributions
mble-0.685
nesday-0.679
pher-0.624
cream-0.578
displayText-0.551
Token the
Token ID262
Feature activation+3.43e-01

Pos logit contributions
mble+3.714
nesday+3.645
pher+3.412
cream+3.154
displayText+2.960
Neg logit contributions
 viral-2.125
 Tik-2.123
 stride-2.104
uni-1.996
 Kik-1.957
Token local
Token ID1957
Feature activation+6.65e-01

Pos logit contributions
mble+1.672
nesday+1.644
pher+1.526
cream+1.431
displayText+1.352
Neg logit contributions
 viral-0.837
 Tik-0.831
 stride-0.819
uni-0.754
 Kik-0.751
Token economy
Token ID3773
Feature activation+4.53e-01

Pos logit contributions
mble+2.832
nesday+2.764
pher+2.587
cream+2.362
displayText+2.197
Neg logit contributions
 Tik-2.007
 viral-2.005
 stride-1.991
 Kik-1.868
uni-1.847
Token and
Token ID290
Feature activation+2.20e-01

Pos logit contributions
mble+2.322
nesday+2.321
pher+2.149
cream+2.010
displayText+1.930
Neg logit contributions
 Tik-1.011
 viral-1.011
 stride-0.962
 Kik-0.940
uni-0.894
Token the
Token ID262
Feature activation+3.71e-01

Pos logit contributions
mble+1.027
nesday+1.023
pher+0.938
cream+0.862
displayText+0.825
Neg logit contributions
 Tik-0.601
 viral-0.599
 stride-0.581
 Kik-0.557
 characteristic-0.546
Token-
Token ID12
Feature activation-1.87e-01

Pos logit contributions
mble+3.471
nesday+3.424
pher+3.206
cream+2.999
displayText+2.778
Neg logit contributions
 Tik-1.894
 viral-1.851
 stride-1.803
 Kik-1.728
 characteristic-1.660
Tokendata
Token ID7890
Feature activation+8.46e-01

Pos logit contributions
 Tik+0.658
 viral+0.658
 stride+0.641
 Kik+0.616
 characteristic+0.606
Neg logit contributions
nesday-0.738
mble-0.734
pher-0.659
cream-0.604
displayText-0.574
Token units
Token ID4991
Feature activation-3.74e-01

Pos logit contributions
mble+4.318
nesday+4.293
pher+3.983
cream+3.708
displayText+3.498
Neg logit contributions
 Tik-1.868
 viral-1.848
 stride-1.827
uni-1.675
 Kik-1.674
Token,
Token ID11
Feature activation+6.67e-01

Pos logit contributions
 viral+1.042
 Tik+1.038
 stride+1.003
 Kik+0.955
 characteristic+0.942
Neg logit contributions
nesday-1.757
mble-1.749
pher-1.582
cream-1.464
displayText-1.419
Token made
Token ID925
Feature activation+4.19e-01

Pos logit contributions
nesday+2.942
mble+2.896
pher+2.661
cream+2.436
displayText+2.342
Neg logit contributions
 viral-1.999
 Tik-1.993
 stride-1.935
 Kik-1.854
 characteristic-1.821
Token modifications
Token ID19008
Feature activation+9.17e-01

Pos logit contributions
nesday+1.878
mble+1.866
pher+1.687
cream+1.562
displayText+1.502
Neg logit contributions
 Tik-1.212
 viral-1.212
 stride-1.179
 Kik-1.128
uni-1.115
Token to
Token ID284
Feature activation+2.81e-01

Pos logit contributions
nesday+3.893
mble+3.813
pher+3.555
cream+3.256
displayText+3.073
Neg logit contributions
 viral-2.800
 Tik-2.796
 stride-2.732
 Kik-2.624
uni-2.577
Token improve
Token ID2987
Feature activation-4.25e-01

Pos logit contributions
nesday+1.296
mble+1.285
pher+1.175
cream+1.077
displayText+1.030
Neg logit contributions
 Tik-0.790
 viral-0.787
 stride-0.756
 Kik-0.728
 characteristic-0.717
Token the
Token ID262
Feature activation-3.56e-02

Pos logit contributions
 Tik+1.136
 viral+1.135
 stride+1.092
 Kik+1.040
 characteristic+1.020
Neg logit contributions
nesday-2.038
mble-2.032
pher-1.852
cream-1.712
displayText-1.654
Token detection
Token ID13326
Feature activation+8.80e-02

Pos logit contributions
 Tik+0.091
 viral+0.091
 stride+0.087
 Kik+0.083
uni+0.081
Neg logit contributions
nesday-0.175
mble-0.174
pher-0.159
cream-0.147
displayText-0.142
Token of
Token ID286
Feature activation+9.25e-02

Pos logit contributions
nesday+0.433
mble+0.432
pher+0.398
cream+0.368
displayText+0.354
Neg logit contributions
 Tik-0.219
 viral-0.219
 stride-0.209
 Kik-0.200
uni-0.197
Token is
Token ID318
Feature activation-1.34e-01

Pos logit contributions
 viral+0.499
 Tik+0.497
 stride+0.479
 Kik+0.454
 characteristic+0.446
Neg logit contributions
nesday-0.956
mble-0.951
pher-0.868
cream-0.806
displayText-0.781
Token possible
Token ID1744
Feature activation-1.83e-01

Pos logit contributions
 viral+0.392
 Tik+0.391
 stride+0.379
 Kik+0.361
 characteristic+0.355
Neg logit contributions
nesday-0.612
mble-0.609
pher-0.552
cream-0.509
displayText-0.491
Token to
Token ID284
Feature activation-1.20e-01

Pos logit contributions
 viral+0.537
 Tik+0.535
 stride+0.518
 Kik+0.494
 characteristic+0.486
Neg logit contributions
nesday-0.830
mble-0.826
pher-0.749
cream-0.690
displayText-0.665
Token live
Token ID2107
Feature activation+2.33e-01

Pos logit contributions
 viral+0.316
 Tik+0.315
 stride+0.304
 Kik+0.289
 characteristic+0.283
Neg logit contributions
nesday-0.580
mble-0.577
pher-0.527
cream-0.487
displayText-0.472
Token only
Token ID691
Feature activation+5.62e-01

Pos logit contributions
nesday+1.122
mble+1.119
pher+1.028
cream+0.949
displayText+0.908
Neg logit contributions
 Tik-0.608
 viral-0.602
 stride-0.581
 Kik-0.555
uni-0.545
Token as
Token ID355
Feature activation+8.63e-01

Pos logit contributions
nesday+2.614
mble+2.600
pher+2.393
cream+2.195
displayText+2.097
Neg logit contributions
 Tik-1.542
 viral-1.524
 stride-1.488
 Kik-1.413
uni-1.401
Token long
Token ID890
Feature activation-1.08e+00

Pos logit contributions
nesday+3.878
mble+3.875
pher+3.607
cream+3.244
displayText+3.073
Neg logit contributions
 Tik-2.437
 viral-2.419
 stride-2.362
 Kik-2.236
uni-2.228
Token as
Token ID355
Feature activation-4.34e-01

Pos logit contributions
 viral+2.239
 Tik+2.198
 stride+2.131
 characteristic+1.974
 Kik+1.961
Neg logit contributions
nesday-5.870
mble-5.826
pher-5.308
cream-4.983
displayText-4.918
Token life
Token ID1204
Feature activation+2.49e-01

Pos logit contributions
 viral+1.021
 Tik+1.017
 stride+0.977
 Kik+0.920
 characteristic+0.903
Neg logit contributions
nesday-2.228
mble-2.217
pher-2.031
cream-1.892
displayText-1.837
Token intox
Token ID21275
Feature activation+7.86e-01

Pos logit contributions
nesday+1.163
mble+1.159
pher+1.071
cream+0.981
displayText+0.939
Neg logit contributions
 Tik-0.692
 viral-0.687
 stride-0.661
 Kik-0.631
uni-0.619
Tokenicates
Token ID16856
Feature activation+6.71e-01

Pos logit contributions
nesday+1.383
mble+1.330
pher+1.054
cream+0.814
displayText+0.631
Neg logit contributions
 viral-4.480
 Tik-4.457
 stride-4.421
 Kik-4.278
 characteristic-4.223
Token relatively
Token ID5365
Feature activation+1.34e-01

Pos logit contributions
 viral+0.487
 Tik+0.484
 stride+0.468
 Kik+0.443
 characteristic+0.438
Neg logit contributions
nesday-0.889
mble-0.884
pher-0.804
cream-0.746
displayText-0.724
Token low
Token ID1877
Feature activation-2.91e-01

Pos logit contributions
nesday+0.727
mble+0.725
pher+0.672
cream+0.628
displayText+0.606
Neg logit contributions
 Tik-0.271
 viral-0.269
 stride-0.258
 Kik-0.241
uni-0.234
Token,
Token ID11
Feature activation-2.97e-01

Pos logit contributions
 viral+0.764
 Tik+0.761
 stride+0.734
 Kik+0.697
 characteristic+0.684
Neg logit contributions
nesday-1.415
mble-1.408
pher-1.284
cream-1.190
displayText-1.152
Token but
Token ID475
Feature activation-3.94e-01

Pos logit contributions
 viral+0.745
 Tik+0.742
 stride+0.715
 Kik+0.676
 characteristic+0.663
Neg logit contributions
nesday-1.475
mble-1.468
pher-1.342
cream-1.246
displayText-1.207
Token nonetheless
Token ID19018
Feature activation-1.12e+00

Pos logit contributions
 viral+1.016
 Tik+1.012
 stride+0.977
 Kik+0.925
 characteristic+0.908
Neg logit contributions
nesday-1.934
mble-1.926
pher-1.757
cream-1.630
displayText-1.578
Token a
Token ID257
Feature activation-7.00e-01

Pos logit contributions
 viral+2.854
 Tik+2.802
 stride+2.714
 characteristic+2.594
 Kik+2.555
Neg logit contributions
nesday-5.597
mble-5.500
pher-4.968
cream-4.666
displayText-4.581
Token problem
Token ID1917
Feature activation-2.34e-01

Pos logit contributions
 viral+1.979
 Tik+1.957
 stride+1.905
 characteristic+1.805
 Kik+1.804
Neg logit contributions
nesday-3.286
mble-3.252
pher-2.951
cream-2.730
displayText-2.659
Token.
Token ID13
Feature activation-2.30e-01

Pos logit contributions
 viral+0.606
 Tik+0.605
 stride+0.583
 Kik+0.555
uni+0.538
Neg logit contributions
nesday-1.138
mble-1.136
pher-1.040
cream-0.963
displayText-0.929
Token The
Token ID383
Feature activation+1.97e-01

Pos logit contributions
 Tik+0.669
 viral+0.665
 stride+0.641
 Kik+0.617
 characteristic+0.602
Neg logit contributions
nesday-1.058
mble-1.052
pher-0.947
cream-0.874
displayText-0.848
Token education
Token ID3707
Feature activation+5.34e-01

Pos logit contributions
nesday+0.954
mble+0.952
pher+0.867
cream+0.807
displayText+0.775
Neg logit contributions
 viral-0.508
 Tik-0.505
 stride-0.490
 Kik-0.463
 characteristic-0.451
Token sector
Token ID6567
Feature activation+7.60e-01

Pos logit contributions
mble+2.463
nesday+2.448
pher+2.243
cream+2.064
displayText+1.973
Neg logit contributions
 Tik-1.472
 viral-1.471
 stride-1.413
 Kik-1.366
uni-1.332
Token the
Token ID262
Feature activation-3.20e-01

Pos logit contributions
 viral+1.041
 Tik+1.033
 stride+0.996
 Kik+0.942
 characteristic+0.925
Neg logit contributions
nesday-2.095
mble-2.084
pher-1.905
cream-1.771
displayText-1.720
Token use
Token ID779
Feature activation+1.90e-01

Pos logit contributions
 viral+0.743
 Tik+0.741
 stride+0.711
 Kik+0.669
 characteristic+0.656
Neg logit contributions
nesday-1.654
mble-1.647
pher-1.509
cream-1.406
displayText-1.364
Token of
Token ID286
Feature activation+2.92e-01

Pos logit contributions
nesday+0.952
mble+0.947
pher+0.864
cream+0.803
displayText+0.780
Neg logit contributions
 viral-0.472
 Tik-0.469
 stride-0.453
 Kik-0.428
 characteristic-0.420
Token an
Token ID281
Feature activation-1.13e-01

Pos logit contributions
nesday+1.463
mble+1.460
pher+1.337
cream+1.242
displayText+1.191
Neg logit contributions
 Tik-0.707
 viral-0.687
 stride-0.674
 Kik-0.629
uni-0.625
Token annotation
Token ID23025
Feature activation-5.38e-01

Pos logit contributions
 viral+0.246
 Tik+0.244
 stride+0.234
 Kik+0.220
 characteristic+0.215
Neg logit contributions
nesday-0.597
mble-0.594
pher-0.546
cream-0.510
displayText-0.495
Token automatically
Token ID6338
Feature activation-4.22e-01

Pos logit contributions
 viral+1.164
 Tik+1.159
 stride+1.110
 Kik+1.039
 characteristic+1.017
Neg logit contributions
nesday-2.859
mble-2.847
pher-2.616
cream-2.444
displayText-2.373
Token added
Token ID2087
Feature activation+1.66e-01

Pos logit contributions
 viral+0.918
 Tik+0.913
 stride+0.875
 Kik+0.819
 characteristic+0.804
Neg logit contributions
nesday-2.240
mble-2.229
pher-2.047
cream-1.912
displayText-1.858
Token to
Token ID284
Feature activation-2.21e-01

Pos logit contributions
nesday+0.723
mble+0.717
pher+0.645
cream+0.594
displayText+0.569
Neg logit contributions
 Tik-0.516
 viral-0.513
 stride-0.501
 Kik-0.480
 characteristic-0.469
Token all
Token ID477
Feature activation-8.17e-01

Pos logit contributions
 Tik+0.568
 viral+0.566
 stride+0.548
 Kik+0.517
 characteristic+0.509
Neg logit contributions
nesday-1.081
mble-1.077
pher-0.981
cream-0.911
displayText-0.878
Token of
Token ID286
Feature activation+2.04e-01

Pos logit contributions
 viral+1.989
 Tik+1.958
 stride+1.884
 Kik+1.789
 characteristic+1.753
Neg logit contributions
nesday-4.147
mble-4.124
pher-3.777
cream-3.513
displayText-3.424
Token their
Token ID511
Feature activation-7.98e-01

Pos logit contributions
nesday+0.960
mble+0.954
pher+0.864
cream+0.798
displayText+0.766
Neg logit contributions
 Tik-0.556
 viral-0.554
 stride-0.541
 Kik-0.508
uni-0.505
Token aboard
Token ID15500
Feature activation-1.05e-01

Pos logit contributions
nesday+3.804
mble+3.799
pher+3.539
cream+3.259
displayText+3.101
Neg logit contributions
 Tik-1.847
 viral-1.797
 stride-1.729
uni-1.661
 Kik-1.645
Token in
Token ID287
Feature activation+8.32e-02

Pos logit contributions
 viral+0.276
 Tik+0.274
 stride+0.265
 Kik+0.251
 characteristic+0.246
Neg logit contributions
nesday-0.514
mble-0.512
pher-0.465
cream-0.431
displayText-0.419
Token 2006
Token ID4793
Feature activation+3.64e-01

Pos logit contributions
nesday+0.410
mble+0.407
pher+0.373
cream+0.345
displayText+0.334
Neg logit contributions
 viral-0.209
 Tik-0.208
 stride-0.200
 Kik-0.190
uni-0.188
Token
Token ID960
Feature activation-1.35e-01

Pos logit contributions
nesday+1.740
mble+1.731
pher+1.588
cream+1.466
displayText+1.419
Neg logit contributions
 Tik-0.968
 viral-0.965
 stride-0.931
 Kik-0.889
 characteristic-0.872
Tokenonce
Token ID27078
Feature activation+1.30e+00

Pos logit contributions
 viral+0.461
 Tik+0.459
 stride+0.447
 Kik+0.429
 characteristic+0.424
Neg logit contributions
nesday-0.553
mble-0.550
pher-0.489
cream-0.445
displayText-0.430
Token again
Token ID757
Feature activation-1.32e-01

Pos logit contributions
mble+5.469
nesday+5.410
pher+5.032
cream+4.503
displayText+4.299
Neg logit contributions
 Tik-3.856
 viral-3.834
 stride-3.726
uni-3.571
 Kik-3.567
Token,
Token ID11
Feature activation-9.68e-02

Pos logit contributions
 viral+0.367
 Tik+0.366
 stride+0.354
 Kik+0.337
 characteristic+0.331
Neg logit contributions
nesday-0.616
mble-0.613
pher-0.558
cream-0.515
displayText-0.498
Token in
Token ID287
Feature activation+2.89e-02

Pos logit contributions
 viral+0.251
 Tik+0.250
 stride+0.241
 Kik+0.229
 characteristic+0.225
Neg logit contributions
nesday-0.473
mble-0.471
pher-0.430
cream-0.398
displayText-0.386
Token a
Token ID257
Feature activation+1.19e-01

Pos logit contributions
nesday+0.133
mble+0.133
pher+0.121
cream+0.111
displayText+0.107
Neg logit contributions
 viral-0.082
 Tik-0.082
 stride-0.079
 Kik-0.076
 characteristic-0.074
Token time
Token ID640
Feature activation+3.00e-02

Pos logit contributions
nesday+0.574
mble+0.572
pher+0.523
cream+0.484
displayText+0.465
Neg logit contributions
 Tik-0.309
 viral-0.307
 stride-0.295
 Kik-0.282
uni-0.276
Token of
Token ID286
Feature activation+7.25e-01

Pos logit contributions
nesday+0.146
mble+0.145
pher+0.133
cream+0.123
displayText+0.119
Neg logit contributions
 Tik-0.078
 viral-0.078
 stride-0.075
 Kik-0.072
 characteristic-0.070
Token.
Token ID13
Feature activation+2.39e-01

Pos logit contributions
 viral+0.063
 Tik+0.063
 stride+0.061
 Kik+0.057
 characteristic+0.056
Neg logit contributions
nesday-0.129
mble-0.127
pher-0.117
cream-0.109
displayText-0.105
Token B
Token ID347
Feature activation-6.52e-01

Pos logit contributions
nesday+1.164
mble+1.151
pher+1.065
cream+0.985
displayText+0.957
Neg logit contributions
 viral-0.616
 Tik-0.605
 stride-0.598
 Kik-0.556
 characteristic-0.553
Tokenilled
Token ID2967
Feature activation+9.56e-01

Pos logit contributions
 viral+2.097
 Tik+2.093
 stride+2.030
 Kik+1.938
 characteristic+1.915
Neg logit contributions
nesday-2.776
mble-2.765
pher-2.477
cream-2.273
displayText-2.190
Token as
Token ID355
Feature activation+9.79e-01

Pos logit contributions
nesday+4.626
mble+4.578
pher+4.244
cream+3.873
displayText+3.813
Neg logit contributions
 viral-2.375
 Tik-2.336
 stride-2.302
 Kik-2.195
uni-2.144
Token an
Token ID281
Feature activation+2.40e-01

Pos logit contributions
nesday+4.321
mble+4.314
pher+3.936
cream+3.544
displayText+3.468
Neg logit contributions
 viral-2.868
 Tik-2.839
 stride-2.753
 Kik-2.658
uni-2.613
Token effort
Token ID3626
Feature activation-1.97e-01

Pos logit contributions
nesday+1.248
mble+1.245
pher+1.141
cream+1.063
displayText+1.037
Neg logit contributions
 viral-0.540
 Tik-0.540
 stride-0.513
 Kik-0.487
 characteristic-0.473
Token that
Token ID326
Feature activation-7.14e-02

Pos logit contributions
 viral+0.630
 Tik+0.630
 stride+0.611
 Kik+0.586
 characteristic+0.576
Neg logit contributions
nesday-0.845
mble-0.838
pher-0.755
cream-0.690
displayText-0.665
Token
Token ID564
Feature activation-1.85e-01

Pos logit contributions
 viral+0.184
 Tik+0.184
 stride+0.178
 Kik+0.168
 characteristic+0.165
Neg logit contributions
nesday-0.349
mble-0.347
pher-0.318
cream-0.293
displayText-0.285
Token
Token ID250
Feature activation-2.18e-01

Pos logit contributions
 viral+0.608
 Tik+0.605
 stride+0.588
 Kik+0.564
 characteristic+0.557
Neg logit contributions
nesday-0.777
mble-0.771
pher-0.690
cream-0.630
displayText-0.607
Tokeninv
Token ID16340
Feature activation+1.78e-01

Pos logit contributions
 viral+0.689
 Tik+0.688
 stride+0.666
 Kik+0.637
 characteristic+0.630
Neg logit contributions
nesday-0.942
mble-0.937
pher-0.840
cream-0.771
displayText-0.747
Tokenigor
Token ID36274
Feature activation+5.55e-01

Pos logit contributions
nesday+0.497
mble+0.485
pher+0.417
cream+0.353
displayText+0.332
Neg logit contributions
 viral-0.840
 Tik-0.837
 stride-0.823
 Kik-0.796
 characteristic-0.792
Token.
Token ID13
Feature activation-4.06e-01

Pos logit contributions
mble+2.529
nesday+2.514
pher+2.329
cream+2.135
displayText+2.054
Neg logit contributions
 Tik-1.260
 viral-1.244
 stride-1.202
 Kik-1.130
uni-1.129
Token
Token ID198
Feature activation-5.45e-01

Pos logit contributions
 Tik+1.109
 viral+1.108
 stride+1.065
 Kik+1.018
 characteristic+0.996
Neg logit contributions
nesday-1.934
mble-1.925
pher-1.742
cream-1.613
displayText-1.564
Token
Token ID198
Feature activation+2.09e-01

Pos logit contributions
 Tik+1.038
 viral+1.031
 stride+0.971
 Kik+0.924
uni+0.884
Neg logit contributions
nesday-3.125
mble-3.119
pher-2.743
cream-2.584
displayText-2.531
TokenHer
Token ID9360
Feature activation+2.37e-01

Pos logit contributions
nesday+0.796
mble+0.793
pher+0.707
cream+0.640
displayText+0.612
Neg logit contributions
 viral-0.767
 Tik-0.765
 stride-0.746
 Kik-0.718
 characteristic-0.710
Token early
Token ID1903
Feature activation-5.81e-01

Pos logit contributions
nesday+1.157
mble+1.155
pher+1.060
cream+0.979
displayText+0.943
Neg logit contributions
 Tik-0.597
 viral-0.591
 stride-0.567
 Kik-0.544
uni-0.529
Token poems
Token ID31888
Feature activation-3.73e-01

Pos logit contributions
 viral+1.528
 Tik+1.523
 stride+1.470
 Kik+1.395
 characteristic+1.368
Neg logit contributions
nesday-2.812
mble-2.800
pher-2.553
cream-2.366
displayText-2.292
Token were
Token ID547
Feature activation+5.14e-01

Pos logit contributions
 viral+1.045
 Tik+1.040
 stride+1.011
 Kik+0.956
 characteristic+0.948
Neg logit contributions
nesday-1.753
mble-1.741
pher-1.576
cream-1.459
displayText-1.415
Token all
Token ID477
Feature activation+3.69e-01

Pos logit contributions
mble+2.354
nesday+2.349
pher+2.168
cream+1.988
displayText+1.919
Neg logit contributions
 Tik-1.414
 viral-1.397
 stride-1.363
 Kik-1.298
uni-1.287
Token elbows
Token ID37076
Feature activation+1.20e+00

Pos logit contributions
mble+1.635
nesday+1.629
pher+1.490
cream+1.360
displayText+1.305
Neg logit contributions
 Tik-1.096
 viral-1.084
 stride-1.061
 Kik-1.012
uni-0.997
Token and
Token ID290
Feature activation+1.80e-01

Pos logit contributions
nesday+5.468
mble+5.343
pher+5.160
cream+4.718
displayText+4.428
Neg logit contributions
 Tik-3.142
 viral-3.130
 stride-3.019
 Kik-2.941
uni-2.889
Token knees
Token ID14475
Feature activation+2.37e-01

Pos logit contributions
nesday+0.818
mble+0.814
pher+0.745
cream+0.685
displayText+0.653
Neg logit contributions
 Tik-0.520
 viral-0.520
 stride-0.499
 Kik-0.480
uni-0.473
Token political
Token ID1964
Feature activation+2.32e-01

Pos logit contributions
 Tik+0.037
 viral+0.037
 stride+0.035
 Kik+0.034
 characteristic+0.033
Neg logit contributions
nesday-0.068
mble-0.068
pher-0.061
cream-0.057
displayText-0.055
Token sm
Token ID895
Feature activation+1.33e+00

Pos logit contributions
nesday+1.126
mble+1.120
pher+1.022
cream+0.948
displayText+0.917
Neg logit contributions
 Tik-0.602
 viral-0.601
 stride-0.579
 Kik-0.551
 characteristic-0.538
Tokenearing
Token ID6648
Feature activation-1.68e-01

Pos logit contributions
nesday+5.570
mble+5.513
pher+5.059
cream+4.585
umbledore+4.252
Neg logit contributions
 viral-4.294
 Tik-4.264
 stride-4.221
 squid-3.962
 Kik-3.953
Token of
Token ID286
Feature activation+5.95e-02

Pos logit contributions
 Tik+0.437
 viral+0.435
 stride+0.421
 Kik+0.401
uni+0.395
Neg logit contributions
nesday-0.813
mble-0.807
pher-0.739
cream-0.685
displayText-0.658
Token a
Token ID257
Feature activation-1.67e-01

Pos logit contributions
nesday+0.271
mble+0.269
pher+0.244
cream+0.224
displayText+0.216
Neg logit contributions
 viral-0.171
 Tik-0.171
 stride-0.167
 Kik-0.158
uni-0.156
Token wholly
Token ID18174
Feature activation-2.15e+00

Pos logit contributions
 Tik+0.425
 viral+0.420
 stride+0.410
 Kik+0.387
uni+0.380
Neg logit contributions
nesday-0.816
mble-0.811
pher-0.744
cream-0.688
displayText-0.665
Token benevolent
Token ID45599
Feature activation-2.80e-01

Pos logit contributions
 viral+5.659
 Tik+5.342
 stride+5.195
 characteristic+5.144
 Kik+4.911
Neg logit contributions
nesday-10.444
mble-10.404
pher-9.382
cream-8.660
displayText-8.413
Token foundation
Token ID8489
Feature activation+2.43e-01

Pos logit contributions
 Tik+0.698
 viral+0.698
 stride+0.672
 Kik+0.637
uni+0.629
Neg logit contributions
nesday-1.380
mble-1.377
pher-1.258
cream-1.171
displayText-1.127
Token,
Token ID11
Feature activation-9.60e-02

Pos logit contributions
nesday+1.149
mble+1.143
pher+1.056
cream+0.972
displayText+0.929
Neg logit contributions
 Tik-0.650
 viral-0.649
 stride-0.624
 Kik-0.598
uni-0.592
Token due
Token ID2233
Feature activation+1.29e+00

Pos logit contributions
 viral+0.250
 Tik+0.249
 stride+0.241
 Kik+0.229
uni+0.225
Neg logit contributions
nesday-0.464
mble-0.462
pher-0.424
cream-0.392
displayText-0.378
Token only
Token ID691
Feature activation+6.18e-01

Pos logit contributions
mble+5.283
nesday+5.269
pher+4.782
cream+4.353
displayText+4.169
Neg logit contributions
 viral-4.097
 Tik-4.092
 stride-3.973
 Kik-3.880
uni-3.766
Tokenbit
Token ID2545
Feature activation-8.29e-02

Pos logit contributions
 viral+1.579
 Tik+1.568
 stride+1.527
 Kik+1.463
 characteristic+1.444
Neg logit contributions
nesday-2.080
mble-2.071
pher-1.848
cream-1.695
displayText-1.642
Tokenco
Token ID1073
Feature activation-4.94e-01

Pos logit contributions
 viral+0.366
 Tik+0.365
 stride+0.357
 Kik+0.346
 characteristic+0.343
Neg logit contributions
nesday-0.255
mble-0.253
pher-0.217
cream-0.191
displayText-0.180
Tokenint
Token ID600
Feature activation-3.07e-01

Pos logit contributions
 viral+1.481
 Tik+1.459
 stride+1.437
uni+1.364
 Kik+1.358
Neg logit contributions
mble-2.206
nesday-2.203
pher-1.957
cream-1.805
displayText-1.778
Tokenalk
Token ID971
Feature activation-8.86e-01

Pos logit contributions
 viral+0.588
 Tik+0.584
 stride+0.558
 Kik+0.519
 characteristic+0.505
Neg logit contributions
nesday-1.710
mble-1.695
pher-1.565
cream-1.463
displayText-1.435
Token.
Token ID13
Feature activation-3.77e-01

Pos logit contributions
 viral+1.826
 Tik+1.801
 stride+1.725
uni+1.649
 Kik+1.612
Neg logit contributions
nesday-4.803
mble-4.776
pher-4.298
cream-4.019
displayText-3.989
Tokenorg
Token ID2398
Feature activation-1.86e+00

Pos logit contributions
 viral+0.866
 Tik+0.845
 stride+0.810
 Kik+0.779
uni+0.770
Neg logit contributions
nesday-1.981
mble-1.952
pher-1.776
cream-1.668
displayText-1.621
Token/
Token ID14
Feature activation-4.30e-01

Pos logit contributions
 viral+3.930
 Tik+3.741
 stride+3.549
 Kik+3.473
 search+3.420
Neg logit contributions
mble-9.787
nesday-9.684
pher-8.566
displayText-8.115
cream-8.102
Tokenindex
Token ID9630
Feature activation+7.87e-01

Pos logit contributions
 viral+0.991
 Tik+0.988
 stride+0.941
 Kik+0.906
uni+0.884
Neg logit contributions
nesday-2.230
mble-2.208
pher-2.003
cream-1.876
displayText-1.834
Token.
Token ID13
Feature activation-9.85e-02

Pos logit contributions
nesday+3.954
mble+3.934
pher+3.620
cream+3.365
displayText+3.243
Neg logit contributions
 viral-1.924
 Tik-1.917
 stride-1.841
 Kik-1.736
 characteristic-1.709
Tokenphp
Token ID10121
Feature activation-1.97e+00

Pos logit contributions
 Tik+0.145
 viral+0.145
 stride+0.133
 Kik+0.122
uni+0.122
Neg logit contributions
nesday-0.590
mble-0.588
pher-0.540
cream-0.511
displayText-0.502
Token?
Token ID30
Feature activation-1.30e+00

Pos logit contributions
 viral+5.329
 Tik+5.131
 stride+4.941
uni+4.932
 Kik+4.887
Neg logit contributions
mble-9.025
nesday-8.848
pher-7.631
displayText-7.098
cream-7.082
Token appeal
Token ID5198
Feature activation-3.43e-01

Pos logit contributions
 viral+0.616
 Tik+0.614
 stride+0.592
 Kik+0.562
 characteristic+0.551
Neg logit contributions
nesday-1.171
mble-1.165
pher-1.065
cream-0.988
displayText-0.955
Token to
Token ID284
Feature activation-5.67e-01

Pos logit contributions
 viral+1.095
 Tik+1.093
 stride+1.063
 Kik+1.018
 characteristic+1.002
Neg logit contributions
nesday-1.466
mble-1.458
pher-1.312
cream-1.203
displayText-1.157
Token children
Token ID1751
Feature activation-2.97e-01

Pos logit contributions
 viral+1.474
 Tik+1.468
 stride+1.417
 Kik+1.342
 characteristic+1.320
Neg logit contributions
nesday-2.770
mble-2.755
pher-2.511
cream-2.330
displayText-2.259
Token and
Token ID290
Feature activation-4.67e-03

Pos logit contributions
 viral+0.725
 Tik+0.723
 stride+0.695
 Kik+0.659
 characteristic+0.643
Neg logit contributions
nesday-1.493
mble-1.486
pher-1.362
cream-1.267
displayText-1.226
Token can
Token ID460
Feature activation+2.29e-02

Pos logit contributions
 Tik+0.012
 viral+0.012
 stride+0.012
 Kik+0.011
 characteristic+0.011
Neg logit contributions
nesday-0.022
mble-0.022
pher-0.020
cream-0.019
displayText-0.018
Token stand
Token ID1302
Feature activation-1.78e+00

Pos logit contributions
nesday+0.103
mble+0.102
pher+0.093
cream+0.086
displayText+0.082
Neg logit contributions
 viral-0.068
 Tik-0.068
 stride-0.065
 Kik-0.063
 characteristic-0.061
Token the
Token ID262
Feature activation-3.62e-01

Pos logit contributions
 viral+4.633
 Tik+4.514
 stride+4.323
 characteristic+4.032
 Hawai+3.905
Neg logit contributions
nesday-8.677
mble-8.557
pher-7.770
displayText-7.196
cream-7.159
Token test
Token ID1332
Feature activation-3.11e-01

Pos logit contributions
 viral+0.673
 Tik+0.671
 stride+0.636
 Kik+0.592
 characteristic+0.574
Neg logit contributions
nesday-2.027
mble-2.020
pher-1.864
cream-1.750
displayText-1.701
Token of
Token ID286
Feature activation+6.07e-01

Pos logit contributions
 Tik+0.800
 viral+0.798
 stride+0.766
 Kik+0.729
uni+0.712
Neg logit contributions
nesday-1.527
mble-1.523
pher-1.386
cream-1.291
displayText-1.245
Token time
Token ID640
Feature activation+2.99e-01

Pos logit contributions
nesday+2.517
mble+2.478
pher+2.249
cream+2.045
displayText+1.917
Neg logit contributions
 Tik-1.942
 viral-1.917
 stride-1.847
uni-1.826
 Kik-1.823
Token.
Token ID13
Feature activation-1.45e-01

Pos logit contributions
nesday+1.449
mble+1.447
pher+1.330
cream+1.241
displayText+1.187
Neg logit contributions
 Tik-0.761
 viral-0.754
 stride-0.724
 Kik-0.700
uni-0.683
Token $
Token ID720
Feature activation+6.58e-02

Pos logit contributions
nesday+1.913
mble+1.890
pher+1.742
cream+1.614
displayText+1.555
Neg logit contributions
 viral-1.006
 Tik-0.998
 stride-0.959
 Kik-0.933
uni-0.904
Token($
Token ID16763
Feature activation+2.99e-01

Pos logit contributions
nesday+0.285
mble+0.285
pher+0.258
cream+0.236
displayText+0.229
Neg logit contributions
 viral-0.206
 Tik-0.206
 stride-0.199
 Kik-0.193
 characteristic-0.188
Tokenw
Token ID86
Feature activation-5.88e-01

Pos logit contributions
nesday+1.275
mble+1.271
pher+1.150
cream+1.053
displayText+1.018
Neg logit contributions
 Tik-0.959
 viral-0.958
 stride-0.924
 Kik-0.898
 characteristic-0.877
Tokenpath
Token ID6978
Feature activation-6.99e-01

Pos logit contributions
 viral+1.251
 Tik+1.236
 stride+1.219
uni+1.127
 characteristic+1.114
Neg logit contributions
mble-3.117
nesday-3.114
pher-2.788
cream-2.616
displayText-2.555
Token)"
Token ID16725
Feature activation-1.29e+00

Pos logit contributions
 Tik+2.150
 viral+2.143
 stride+2.074
 Kik+1.982
 characteristic+1.958
Neg logit contributions
nesday-3.098
mble-3.074
pher-2.763
cream-2.542
displayText-2.442
Token break
Token ID2270
Feature activation-2.52e+00

Pos logit contributions
 viral+3.437
 Tik+3.422
 stride+3.301
 Kik+3.129
 characteristic+3.083
Neg logit contributions
nesday-6.240
mble-6.193
pher-5.593
cream-5.243
displayText-5.038
Token }
Token ID1782
Feature activation-1.05e+00

Pos logit contributions
 Tik+5.901
 viral+5.887
 stride+5.758
 Kik+5.273
 characteristic+5.258
Neg logit contributions
nesday-12.395
mble-12.204
pher-11.053
cream-10.527
displayText-9.944
Token }
Token ID1782
Feature activation-9.56e-01

Pos logit contributions
 viral+2.773
 Tik+2.763
 stride+2.669
 Kik+2.512
 characteristic+2.489
Neg logit contributions
nesday-5.106
mble-5.067
pher-4.592
cream-4.277
displayText-4.129
Token else
Token ID2073
Feature activation-7.60e-01

Pos logit contributions
 viral+2.585
 Tik+2.575
 stride+2.488
 Kik+2.347
 characteristic+2.327
Neg logit contributions
nesday-4.577
mble-4.539
pher-4.118
cream-3.824
displayText-3.705
Token {
Token ID1391
Feature activation-8.66e-01

Pos logit contributions
 viral+1.791
 Tik+1.778
 stride+1.717
 Kik+1.608
 characteristic+1.583
Neg logit contributions
nesday-3.897
mble-3.860
pher-3.527
cream-3.287
displayText-3.191
Token $
Token ID720
Feature activation+2.09e-01

Pos logit contributions
 viral+2.773
 Tik+2.768
 stride+2.686
 Kik+2.567
 characteristic+2.539
Neg logit contributions
nesday-3.716
mble-3.689
pher-3.301
cream-3.040
displayText-2.919
Token,
Token ID11
Feature activation+1.28e-01

Pos logit contributions
 Tik+1.896
 viral+1.893
 stride+1.809
 Kik+1.728
 characteristic+1.703
Neg logit contributions
mble-3.270
nesday-3.259
pher-2.940
cream-2.734
displayText-2.666
Token also
Token ID635
Feature activation+1.30e-01

Pos logit contributions
nesday+0.628
mble+0.623
pher+0.570
cream+0.528
displayText+0.505
Neg logit contributions
 viral-0.324
 Tik-0.322
 stride-0.317
 Kik-0.294
uni-0.292
Token known
Token ID1900
Feature activation+5.86e-01

Pos logit contributions
nesday+0.620
mble+0.616
pher+0.563
cream+0.519
displayText+0.503
Neg logit contributions
 viral-0.353
 Tik-0.352
 stride-0.341
 Kik-0.324
 characteristic-0.318
Token as
Token ID355
Feature activation+1.80e-01

Pos logit contributions
nesday+2.935
mble+2.910
pher+2.674
cream+2.489
displayText+2.420
Neg logit contributions
 viral-1.411
 Tik-1.406
 stride-1.382
 Kik-1.298
 characteristic-1.263
Token R
Token ID371
Feature activation-5.03e-01

Pos logit contributions
nesday+0.877
mble+0.873
pher+0.796
cream+0.736
displayText+0.710
Neg logit contributions
 viral-0.463
 Tik-0.457
 stride-0.451
 Kik-0.418
 characteristic-0.416
Tokenang
Token ID648
Feature activation-1.72e+00

Pos logit contributions
 viral+1.656
 Tik+1.650
 stride+1.610
 Kik+1.537
 characteristic+1.520
Neg logit contributions
nesday-2.109
mble-2.098
pher-1.883
cream-1.721
displayText-1.653
Tokenoon
Token ID2049
Feature activation-4.45e-01

Pos logit contributions
 Tik+4.006
 viral+3.890
 stride+3.649
 Kik+3.608
uni+3.594
Neg logit contributions
mble-8.680
nesday-8.639
pher-7.939
cream-7.419
displayText-7.323
Token,
Token ID11
Feature activation-1.21e-02

Pos logit contributions
 viral+1.246
 Tik+1.245
 stride+1.198
 Kik+1.147
 characteristic+1.123
Neg logit contributions
nesday-2.085
mble-2.076
pher-1.884
cream-1.742
displayText-1.691
Token says
Token ID1139
Feature activation-4.01e-01

Pos logit contributions
 viral+0.033
 Tik+0.033
 stride+0.032
 Kik+0.031
 characteristic+0.030
Neg logit contributions
nesday-0.057
mble-0.057
pher-0.052
cream-0.048
displayText-0.046
Token MS
Token ID6579
Feature activation-8.76e-01

Pos logit contributions
 viral+1.044
 Tik+1.042
 stride+1.008
 Kik+0.952
 characteristic+0.936
Neg logit contributions
nesday-1.951
mble-1.942
pher-1.771
cream-1.641
displayText-1.585
TokenF
Token ID37
Feature activation-5.61e-01

Pos logit contributions
 viral+2.083
 Tik+2.067
 stride+1.987
 Kik+1.927
uni+1.894
Neg logit contributions
nesday-4.541
mble-4.509
pher-3.957
cream-3.705
displayText-3.614