TOP ACTIVATIONS
MAX = 5.692

Donald Trump Donald John Trump READ : Cohen testimony alleges Trump
64 406 Mem c py Reading 55 80 953 16 27
Donald Trump Donald John Trump House committee believes it has evidence
Donald Trump Donald John Trump House committee believes it has evidence
. Article Continued Below The T PA
) that tore the country apart . Likewise , the neoliberal
President Trump Donald John Trump House committee believes it has evidence
seriously Article Continued Below Tax
. forms . text rend erer ] :: Measure Text ($
He took apart some elements of the mechanism
away from Kirby 's bomb astic style of storytelling . According
) Mem c py In Memory 4 66 284 4 64
nat ut u wa na ang kan il ang an ak
re . kov id g oyal . net ) or Stan
ong Ch oya Week end T ear V oid Ray J
args [" images "] ): # load the image , resize
Trump s sal vo ran counter to efforts this
things . See | aut oc omm and | . 3
. parse _ args ()) # initialize a rectangular and square
make it through the g auntlet of the Oregon State voter

MIN ACTIVATIONS
MIN = -7.329

impl Board { pub fn copy _ board ( &
< T > { pub fn new ( t : T
< T > { pub fn load < ' a >
null atomic pointer . pub fn null () -> Atomic <
Guard { ... } pub fn pin () -> Guard ;
172 games and two Super Bowl s in the NFL :
wrap ()) } } pub fn apply _ move ( &
the space let ob b = fit ( space ); //
this public sculpture by Eld on Garn et uses just a
state ); ... } pub fn undo _ move ( &
active : pub struct Guard { ... } pub
. Fine cut the 4 garlic cloves and the ginger .
of Sciences . Explore further : New Insight Into
only within the subject areas enumer ated under section 51 .
( path , 4 ) = '. cl j ' OR
to images directory ") args = v ars ( ap .
ulse period ", Float ) = 1 // seconds 1 2
| 2 | struct Board { | ^ ^^^^ ^^^^ ^^
out at http :// w ashington beer . com / w
component const float TA U = 6 . 283 185 307

INTERVAL 2.437 - 5.692
CONTAINS 0.475%

had come on a P IL by Raj endra S ont
Han Solo in his classic delivery stride . Cricket nerd os
just make K essel go away . You even went as
meet government commitments without added borrowing , those " extra ordinary
than 60 percent of our gross domestic product and possess enormous

INTERVAL -0.818 - 2.437
CONTAINS 84.643%

hiring for entry - level HR positions . We have our
six financial institutions in this country own assets equal to more
about differing interpretation of the words in the statements , or
Carter re run is probably a best - case scenario .
. But Fox News / O pin ion Dynamics did a

INTERVAL -4.074 - -0.818
CONTAINS 14.873%

, by building up their military and asking the United States
has remained so elusive , physicists have turned their sights to
ence of office , and the sp urn s
dB m Ret ry short limit : 7 R TS thr
web browser , saw its 2016 revenue increase 24 percent to

INTERVAL -7.329 - -4.074
CONTAINS 0.009%

uring kernel rect K ernel = c v 2 . get
open new store at Five Corn ers in Bur ien
only within the subject areas enumer ated under section 51 .
of improvement that values defect prevention over defect detection . It
in the presence of a TSA agent . Maybe you acted
Token Donald
Token ID3759
Feature activation-1.60e+00

Pos logit contributions
ASC+0.640
 Agric+0.565
eur+0.564
 Ribbon+0.558
PLA+0.556
Neg logit contributions
anasia-0.505
 vas-0.464
 Bengals-0.446
 [*-0.442
cius-0.436
Token Trump
Token ID1301
Feature activation-1.05e+00

Pos logit contributions
anasia+0.953
 vas+0.875
 Bengals+0.847
 [*+0.830
cius+0.806
Neg logit contributions
ASC-1.415
eur-1.256
 Agric-1.251
PLA-1.243
 Ribbon-1.239
Token Donald
Token ID3759
Feature activation-6.64e-03

Pos logit contributions
anasia+0.684
 vas+0.632
 Bengals+0.612
 [*+0.603
cius+0.591
Neg logit contributions
ASC-0.871
eur-0.768
 Agric-0.766
PLA-0.757
 Ribbon-0.757
Token John
Token ID1757
Feature activation+1.82e+00

Pos logit contributions
anasia+0.003
 vas+0.003
 Bengals+0.003
 [*+0.003
cius+0.003
Neg logit contributions
ASC-0.007
 Agric-0.006
eur-0.006
PLA-0.006
 Ribbon-0.006
Token Trump
Token ID1301
Feature activation+2.11e+00

Pos logit contributions
ASC+1.544
eur+1.370
 Agric+1.363
 Ribbon+1.349
orate+1.347
Neg logit contributions
anasia-1.152
 vas-1.054
 Bengals-1.020
 [*-1.007
cius-0.994
TokenREAD
Token ID15675
Feature activation+5.69e+00

Pos logit contributions
ASC+1.707
eur+1.494
PLA+1.486
 Agric+1.477
 Ribbon+1.456
Neg logit contributions
anasia-1.441
 vas-1.345
 Bengals-1.301
 [*-1.286
cius-1.265
Token:
Token ID25
Feature activation-3.14e-01

Pos logit contributions
ASC+3.916
orate+3.347
 Ribbon+3.304
PLA+3.289
 parity+3.263
Neg logit contributions
anasia-4.578
 vas-4.200
cius-4.114
 Bengals-4.022
 [*-4.016
Token Cohen
Token ID17154
Feature activation+5.14e-02

Pos logit contributions
anasia+0.211
 vas+0.198
 Bengals+0.192
 [*+0.189
cius+0.183
Neg logit contributions
ASC-0.253
eur-0.223
 Agric-0.221
orate-0.219
 Ribbon-0.218
Token testimony
Token ID9709
Feature activation-7.30e-01

Pos logit contributions
ASC+0.042
eur+0.037
 Agric+0.037
 Ribbon+0.036
PLA+0.036
Neg logit contributions
anasia-0.034
 vas-0.032
 Bengals-0.031
 [*-0.030
cius-0.030
Token alleges
Token ID24763
Feature activation-4.08e-01

Pos logit contributions
anasia+0.454
 vas+0.421
 Bengals+0.411
 [*+0.402
cius+0.391
Neg logit contributions
ASC-0.623
eur-0.555
 Agric-0.553
 Ribbon-0.543
orate-0.543
Token Trump
Token ID1301
Feature activation+6.86e-01

Pos logit contributions
anasia+0.286
 vas+0.262
 Bengals+0.255
 [*+0.252
cius+0.247
Neg logit contributions
ASC-0.323
eur-0.281
 Agric-0.281
 Ribbon-0.278
PLA-0.277
Token64
Token ID2414
Feature activation+2.17e+00

Pos logit contributions
ASC+0.177
eur+0.152
 Agric+0.152
 Ribbon+0.150
PLA+0.150
Neg logit contributions
anasia-0.193
 vas-0.181
 Bengals-0.176
 [*-0.174
cius-0.171
Token406
Token ID29703
Feature activation+1.26e+00

Pos logit contributions
ASC+1.440
eur+1.220
 Agric+1.214
 Ribbon+1.199
PLA+1.197
Neg logit contributions
anasia-1.785
 vas-1.673
 Bengals-1.627
 [*-1.613
cius-1.602
Token Mem
Token ID4942
Feature activation+2.16e+00

Pos logit contributions
ASC+0.985
eur+0.856
 Agric+0.854
 Ribbon+0.846
PLA+0.844
Neg logit contributions
anasia-0.897
 vas-0.829
 Bengals-0.801
 [*-0.793
cius-0.787
Tokenc
Token ID66
Feature activation+1.62e+00

Pos logit contributions
ASC+1.453
eur+1.246
 Agric+1.224
PLA+1.213
orate+1.212
Neg logit contributions
anasia-1.758
 vas-1.654
 Bengals-1.610
 [*-1.580
cius-1.554
Tokenpy
Token ID9078
Feature activation-1.13e-01

Pos logit contributions
ASC+1.111
eur+0.955
 Agric+0.947
PLA+0.938
orate+0.935
Neg logit contributions
anasia-1.294
 vas-1.215
 Bengals-1.184
 [*-1.167
cius-1.149
TokenReading
Token ID36120
Feature activation+5.44e+00

Pos logit contributions
anasia+0.091
 vas+0.085
 Bengals+0.083
 [*+0.082
cius+0.081
Neg logit contributions
ASC-0.077
eur-0.066
 Agric-0.066
 Ribbon-0.065
PLA-0.065
Token 55
Token ID5996
Feature activation+2.56e+00

Pos logit contributions
ASC+4.126
 Ribbon+3.521
eur+3.517
 Agric+3.511
orate+3.496
Neg logit contributions
anasia-3.899
 vas-3.624
 Bengals-3.502
cius-3.433
 [*-3.421
Token80
Token ID1795
Feature activation+1.80e+00

Pos logit contributions
ASC+1.741
eur+1.478
 Agric+1.475
 Ribbon+1.459
PLA+1.456
Neg logit contributions
anasia-2.058
 vas-1.924
 Bengals-1.861
 [*-1.851
cius-1.841
Token953
Token ID49649
Feature activation+9.73e-01

Pos logit contributions
ASC+1.165
eur+0.983
 Agric+0.982
 Ribbon+0.967
PLA+0.966
Neg logit contributions
anasia-1.505
 vas-1.414
 Bengals-1.372
 [*-1.361
cius-1.352
Token 16
Token ID1467
Feature activation+3.49e-01

Pos logit contributions
ASC+0.750
eur+0.654
 Agric+0.654
 Ribbon+0.645
PLA+0.643
Neg logit contributions
anasia-0.696
 vas-0.645
 Bengals-0.623
 [*-0.615
cius-0.609
Token27
Token ID1983
Feature activation+1.44e+00

Pos logit contributions
ASC+0.223
eur+0.189
 Agric+0.188
 Ribbon+0.185
PLA+0.185
Neg logit contributions
anasia-0.296
 vas-0.278
 Bengals-0.272
 [*-0.268
cius-0.265
Token Donald
Token ID3759
Feature activation-3.61e-01

Pos logit contributions
anasia+0.124
 vas+0.109
 Bengals+0.103
 [*+0.101
cius+0.098
Neg logit contributions
ASC-0.313
eur-0.284
 Agric-0.283
 Ribbon-0.281
PLA-0.281
Token Trump
Token ID1301
Feature activation+2.34e-01

Pos logit contributions
anasia+0.219
 vas+0.201
 Bengals+0.195
 [*+0.192
cius+0.186
Neg logit contributions
ASC-0.317
eur-0.281
 Agric-0.280
PLA-0.278
 Ribbon-0.277
Token Donald
Token ID3759
Feature activation+1.54e+00

Pos logit contributions
ASC+0.251
eur+0.228
 Agric+0.228
PLA+0.226
 Ribbon+0.226
Neg logit contributions
anasia-0.097
 vas-0.085
 Bengals-0.080
 [*-0.078
cius-0.076
Token John
Token ID1757
Feature activation+2.33e+00

Pos logit contributions
ASC+1.460
eur+1.312
 Agric+1.297
 Ribbon+1.293
orate+1.293
Neg logit contributions
anasia-0.818
 vas-0.743
 Bengals-0.703
 [*-0.695
cius-0.691
Token Trump
Token ID1301
Feature activation+2.96e+00

Pos logit contributions
ASC+1.975
eur+1.753
 Agric+1.743
 Ribbon+1.727
orate+1.725
Neg logit contributions
anasia-1.476
 vas-1.351
 Bengals-1.308
 [*-1.290
cius-1.274
TokenHouse
Token ID18102
Feature activation+5.40e+00

Pos logit contributions
ASC+2.369
PLA+2.067
eur+2.058
 Agric+2.030
orate+2.009
Neg logit contributions
anasia-2.039
 vas-1.913
 Bengals-1.847
 [*-1.828
cius-1.802
Token committee
Token ID5583
Feature activation-1.10e+00

Pos logit contributions
ASC+4.568
eur+4.035
 Agric+4.032
 Ribbon+3.989
PLA+3.984
Neg logit contributions
anasia-3.441
 vas-3.160
 Bengals-3.053
 [*-3.016
cius-2.967
Token believes
Token ID5804
Feature activation-4.33e-01

Pos logit contributions
anasia+0.633
 vas+0.598
 Bengals+0.595
 [*+0.565
cius+0.537
Neg logit contributions
ASC-0.980
eur-0.878
 Agric-0.869
 Ribbon-0.859
PLA-0.849
Token it
Token ID340
Feature activation+7.72e-01

Pos logit contributions
anasia+0.272
 vas+0.250
 Bengals+0.244
 [*+0.237
cius+0.231
Neg logit contributions
ASC-0.371
eur-0.328
 Agric-0.326
PLA-0.325
 Ribbon-0.325
Token has
Token ID468
Feature activation+4.70e-01

Pos logit contributions
ASC+0.561
eur+0.486
 Agric+0.484
PLA+0.478
 Ribbon+0.477
Neg logit contributions
anasia-0.584
 vas-0.546
 Bengals-0.532
 [*-0.524
cius-0.515
Token evidence
Token ID2370
Feature activation-7.02e-01

Pos logit contributions
ASC+0.313
eur+0.266
 Agric+0.265
 Ribbon+0.262
PLA+0.260
Neg logit contributions
anasia-0.385
 vas-0.361
 Bengals-0.352
 [*-0.348
cius-0.343
Token Donald
Token ID3759
Feature activation-1.43e+00

Pos logit contributions
anasia+0.747
 vas+0.689
 Bengals+0.667
 [*+0.655
cius+0.642
Neg logit contributions
ASC-1.006
eur-0.891
 Agric-0.886
PLA-0.878
 Ribbon-0.877
Token Trump
Token ID1301
Feature activation-5.07e-01

Pos logit contributions
anasia+0.865
 vas+0.794
 Bengals+0.769
 [*+0.754
cius+0.735
Neg logit contributions
ASC-1.252
eur-1.111
 Agric-1.107
PLA-1.098
 Ribbon-1.095
Token Donald
Token ID3759
Feature activation+8.11e-01

Pos logit contributions
anasia+0.319
 vas+0.294
 Bengals+0.284
 [*+0.279
cius+0.274
Neg logit contributions
ASC-0.434
eur-0.384
 Agric-0.383
PLA-0.379
 Ribbon-0.379
Token John
Token ID1757
Feature activation+2.51e+00

Pos logit contributions
ASC+0.799
eur+0.719
 Agric+0.719
PLA+0.712
 Ribbon+0.711
Neg logit contributions
anasia-0.405
 vas-0.364
 Bengals-0.350
 [*-0.341
cius-0.331
Token Trump
Token ID1301
Feature activation+2.60e+00

Pos logit contributions
ASC+2.089
eur+1.855
 Agric+1.842
 Ribbon+1.828
orate+1.823
Neg logit contributions
anasia-1.622
 vas-1.477
 Bengals-1.433
 [*-1.419
cius-1.409
TokenHouse
Token ID18102
Feature activation+5.24e+00

Pos logit contributions
ASC+2.076
PLA+1.812
eur+1.810
 Agric+1.789
orate+1.766
Neg logit contributions
anasia-1.793
 vas-1.676
 Bengals-1.622
 [*-1.610
cius-1.580
Token committee
Token ID5583
Feature activation-4.43e-01

Pos logit contributions
ASC+4.447
eur+3.930
 Agric+3.924
 Ribbon+3.884
PLA+3.880
Neg logit contributions
anasia-3.324
 vas-3.052
 Bengals-2.948
 [*-2.912
cius-2.863
Token believes
Token ID5804
Feature activation+1.99e-01

Pos logit contributions
anasia+0.262
 vas+0.246
 Bengals+0.244
 [*+0.234
cius+0.222
Neg logit contributions
ASC-0.391
 Agric-0.348
eur-0.347
 Ribbon-0.341
PLA-0.338
Token it
Token ID340
Feature activation+9.90e-01

Pos logit contributions
ASC+0.177
eur+0.157
 Agric+0.156
PLA+0.156
 Ribbon+0.156
Neg logit contributions
anasia-0.119
 vas-0.109
 Bengals-0.105
 [*-0.103
cius-0.100
Token has
Token ID468
Feature activation+4.87e-01

Pos logit contributions
ASC+0.782
eur+0.685
 Agric+0.684
PLA+0.677
 Ribbon+0.673
Neg logit contributions
anasia-0.687
 vas-0.641
 Bengals-0.623
 [*-0.609
cius-0.596
Token evidence
Token ID2370
Feature activation-7.36e-01

Pos logit contributions
ASC+0.329
eur+0.282
 Agric+0.280
PLA+0.277
 Ribbon+0.275
Neg logit contributions
anasia-0.394
 vas-0.370
 Bengals-0.361
 [*-0.356
cius-0.350
Token.
Token ID13
Feature activation-4.94e-01

Pos logit contributions
ASC+0.639
eur+0.559
 Agric+0.557
 Ribbon+0.555
PLA+0.554
Neg logit contributions
anasia-0.567
 vas-0.524
 Bengals-0.508
 [*-0.499
cius-0.497
Token
Token ID198
Feature activation-2.21e-02

Pos logit contributions
anasia+0.335
 vas+0.310
 Bengals+0.300
 [*+0.295
cius+0.292
Neg logit contributions
ASC-0.398
eur-0.350
 Agric-0.349
 Ribbon-0.345
PLA-0.345
Token
Token ID198
Feature activation-1.62e-01

Pos logit contributions
anasia+0.013
 vas+0.012
 Bengals+0.011
 [*+0.011
cius+0.011
Neg logit contributions
ASC-0.020
eur-0.018
 Agric-0.018
 Ribbon-0.018
PLA-0.018
TokenArticle
Token ID14906
Feature activation-4.27e+00

Pos logit contributions
anasia+0.117
 vas+0.109
 Bengals+0.106
 [*+0.104
cius+0.102
Neg logit contributions
ASC-0.124
eur-0.108
 Agric-0.108
PLA-0.107
 Ribbon-0.106
Token Continued
Token ID22168
Feature activation+6.37e-01

Pos logit contributions
anasia+3.070
 vas+2.931
 Bengals+2.871
 [*+2.768
cius+2.682
Neg logit contributions
ASC-3.182
 Ribbon-2.718
orate-2.689
 Agric-2.684
PLA-2.660
Token Below
Token ID10383
Feature activation+4.84e+00

Pos logit contributions
ASC+0.555
eur+0.493
 Agric+0.493
 Ribbon+0.487
PLA+0.485
Neg logit contributions
anasia-0.394
 vas-0.361
 Bengals-0.344
cius-0.341
 [*-0.340
Token
Token ID198
Feature activation+1.33e+00

Pos logit contributions
ASC+3.863
eur+3.433
PLA+3.343
 Agric+3.326
 Ribbon+3.311
Neg logit contributions
anasia-3.276
 vas-3.025
cius-2.906
 Bengals-2.852
 [*-2.825
Token
Token ID198
Feature activation+1.03e+00

Pos logit contributions
ASC+1.160
eur+1.035
 Agric+1.024
PLA+1.015
 Ribbon+1.013
Neg logit contributions
anasia-0.819
 vas-0.750
 Bengals-0.720
 [*-0.707
cius-0.706
TokenThe
Token ID464
Feature activation+9.07e-02

Pos logit contributions
ASC+0.787
eur+0.684
PLA+0.677
 Agric+0.674
orate+0.664
Neg logit contributions
anasia-0.746
 vas-0.698
 Bengals-0.676
 [*-0.662
cius-0.658
Token T
Token ID309
Feature activation+3.05e-01

Pos logit contributions
ASC+0.075
eur+0.066
 Agric+0.066
PLA+0.065
 Ribbon+0.065
Neg logit contributions
anasia-0.060
 vas-0.055
 Bengals-0.053
 [*-0.053
cius-0.052
TokenPA
Token ID4537
Feature activation-2.95e-01

Pos logit contributions
ASC+0.124
eur+0.095
 Agric+0.095
 Ribbon+0.092
orate+0.091
Neg logit contributions
anasia-0.328
 vas-0.312
 Bengals-0.306
 [*-0.304
cius-0.300
Token)
Token ID8
Feature activation-1.80e-01

Pos logit contributions
anasia+0.081
 vas+0.076
 Bengals+0.074
 [*+0.073
cius+0.072
Neg logit contributions
ASC-0.074
eur-0.064
 Agric-0.064
PLA-0.063
 Ribbon-0.063
Token that
Token ID326
Feature activation-2.85e-01

Pos logit contributions
anasia+0.123
 vas+0.114
 Bengals+0.111
 [*+0.109
cius+0.107
Neg logit contributions
ASC-0.143
eur-0.126
 Agric-0.125
 Ribbon-0.124
PLA-0.124
Token tore
Token ID26197
Feature activation+1.29e+00

Pos logit contributions
anasia+0.195
 vas+0.182
 Bengals+0.176
 [*+0.173
cius+0.170
Neg logit contributions
ASC-0.228
eur-0.200
 Agric-0.199
PLA-0.197
 Ribbon-0.197
Token the
Token ID262
Feature activation+1.28e-01

Pos logit contributions
ASC+0.976
eur+0.852
 Agric+0.851
 Ribbon+0.837
orate+0.835
Neg logit contributions
anasia-0.940
 vas-0.866
 Bengals-0.841
 [*-0.830
cius-0.828
Token country
Token ID1499
Feature activation+6.18e-01

Pos logit contributions
ASC+0.092
eur+0.080
 Agric+0.079
PLA+0.078
 Ribbon+0.078
Neg logit contributions
anasia-0.097
 vas-0.091
 Bengals-0.088
 [*-0.087
cius-0.086
Token apart
Token ID5475
Feature activation+4.82e+00

Pos logit contributions
ASC+0.378
eur+0.318
 Agric+0.316
 Ribbon+0.311
PLA+0.311
Neg logit contributions
anasia-0.539
 vas-0.508
 Bengals-0.496
 [*-0.490
cius-0.484
Token.
Token ID13
Feature activation+1.26e-01

Pos logit contributions
ASC+3.449
eur+3.035
 Agric+3.022
orate+2.963
 parity+2.961
Neg logit contributions
anasia-3.567
 vas-3.296
 Bengals-3.238
cius-3.226
 [*-3.136
Token Likewise
Token ID22660
Feature activation-3.82e-01

Pos logit contributions
ASC+0.101
eur+0.088
 Agric+0.088
 Ribbon+0.087
PLA+0.087
Neg logit contributions
anasia-0.087
 vas-0.080
 Bengals-0.078
 [*-0.076
cius-0.076
Token,
Token ID11
Feature activation-7.17e-01

Pos logit contributions
anasia+0.254
 vas+0.235
 Bengals+0.228
 [*+0.224
cius+0.220
Neg logit contributions
ASC-0.313
eur-0.276
 Agric-0.274
 Ribbon-0.271
PLA-0.271
Token the
Token ID262
Feature activation+1.42e-01

Pos logit contributions
anasia+0.497
 vas+0.461
 Bengals+0.447
 [*+0.440
cius+0.433
Neg logit contributions
ASC-0.568
eur-0.498
 Agric-0.495
PLA-0.490
 Ribbon-0.490
Token neoliberal
Token ID31972
Feature activation+3.10e-01

Pos logit contributions
ASC+0.109
eur+0.096
 Agric+0.095
 Ribbon+0.094
PLA+0.094
Neg logit contributions
anasia-0.101
 vas-0.094
 Bengals-0.091
 [*-0.090
cius-0.089
Token President
Token ID1992
Feature activation-5.71e-01

Pos logit contributions
ASC+1.989
 Agric+1.760
eur+1.758
 Ribbon+1.745
 parity+1.745
Neg logit contributions
anasia-1.658
 vas-1.511
 [*-1.449
cius-1.444
 Bengals-1.443
Token Trump
Token ID1301
Feature activation-3.89e-01

Pos logit contributions
anasia+0.341
 vas+0.312
 Bengals+0.301
 [*+0.295
cius+0.291
Neg logit contributions
ASC-0.507
eur-0.452
 Agric-0.450
 Ribbon-0.446
orate-0.444
Token Donald
Token ID3759
Feature activation-5.05e-01

Pos logit contributions
anasia+0.258
 vas+0.239
 Bengals+0.231
 [*+0.228
cius+0.223
Neg logit contributions
ASC-0.320
 Agric-0.281
eur-0.281
PLA-0.278
 Ribbon-0.278
Token John
Token ID1757
Feature activation+1.59e+00

Pos logit contributions
anasia+0.235
 vas+0.208
 Bengals+0.203
 [*+0.196
cius+0.186
Neg logit contributions
ASC-0.513
 Agric-0.467
eur-0.464
PLA-0.464
 Ribbon-0.459
Token Trump
Token ID1301
Feature activation+2.20e+00

Pos logit contributions
ASC+1.349
eur+1.197
 Agric+1.190
 Ribbon+1.179
orate+1.177
Neg logit contributions
anasia-1.008
 vas-0.923
 Bengals-0.895
 [*-0.884
cius-0.871
TokenHouse
Token ID18102
Feature activation+4.74e+00

Pos logit contributions
ASC+1.752
eur+1.524
PLA+1.518
 Agric+1.499
orate+1.486
Neg logit contributions
anasia-1.533
 vas-1.437
 Bengals-1.392
 [*-1.372
cius-1.346
Token committee
Token ID5583
Feature activation-8.19e-01

Pos logit contributions
ASC+4.022
 Agric+3.551
eur+3.549
 Ribbon+3.513
PLA+3.508
Neg logit contributions
anasia-3.019
 vas-2.770
 Bengals-2.673
 [*-2.648
cius-2.604
Token believes
Token ID5804
Feature activation+2.79e-02

Pos logit contributions
anasia+0.481
 Bengals+0.450
 vas+0.450
 [*+0.428
cius+0.417
Neg logit contributions
ASC-0.725
 Agric-0.643
eur-0.641
 Ribbon-0.631
PLA-0.629
Token it
Token ID340
Feature activation+7.50e-01

Pos logit contributions
ASC+0.025
eur+0.022
 Agric+0.022
PLA+0.022
 Ribbon+0.022
Neg logit contributions
anasia-0.017
 vas-0.015
 Bengals-0.015
 [*-0.015
cius-0.014
Token has
Token ID468
Feature activation+6.97e-01

Pos logit contributions
ASC+0.558
 Agric+0.485
eur+0.484
PLA+0.481
 Ribbon+0.474
Neg logit contributions
anasia-0.553
 vas-0.521
 Bengals-0.509
 [*-0.495
cius-0.484
Token evidence
Token ID2370
Feature activation-8.89e-01

Pos logit contributions
ASC+0.468
eur+0.401
 Agric+0.398
PLA+0.394
 Ribbon+0.392
Neg logit contributions
anasia-0.566
 vas-0.532
 Bengals-0.519
 [*-0.512
cius-0.504
Token seriously
Token ID6411
Feature activation+2.23e-01

Pos logit contributions
anasia+0.372
 vas+0.344
 Bengals+0.333
 [*+0.328
cius+0.323
Neg logit contributions
ASC-0.448
eur-0.395
 Agric-0.393
 Ribbon-0.388
PLA-0.387
Token
Token ID198
Feature activation+2.38e-01

Pos logit contributions
ASC+0.183
eur+0.161
 Agric+0.161
 Ribbon+0.159
PLA+0.159
Neg logit contributions
anasia-0.149
 vas-0.137
 Bengals-0.133
 [*-0.131
cius-0.129
Token
Token ID198
Feature activation-2.67e-01

Pos logit contributions
ASC+0.212
eur+0.189
 Agric+0.188
PLA+0.186
 Ribbon+0.186
Neg logit contributions
anasia-0.142
 vas-0.130
 Bengals-0.125
 [*-0.123
cius-0.121
TokenArticle
Token ID14906
Feature activation-3.65e+00

Pos logit contributions
anasia+0.188
 vas+0.174
 Bengals+0.169
 [*+0.167
cius+0.164
Neg logit contributions
ASC-0.209
eur-0.183
 Agric-0.182
 Ribbon-0.180
PLA-0.180
Token Continued
Token ID22168
Feature activation+5.77e-01

Pos logit contributions
anasia+2.524
 vas+2.408
 Bengals+2.387
 [*+2.235
cius+2.235
Neg logit contributions
ASC-2.818
orate-2.406
 Agric-2.406
 Ribbon-2.387
PLA-2.367
Token Below
Token ID10383
Feature activation+4.70e+00

Pos logit contributions
ASC+0.504
eur+0.447
 Agric+0.446
 Ribbon+0.441
PLA+0.440
Neg logit contributions
anasia-0.356
 vas-0.326
 Bengals-0.310
cius-0.308
 [*-0.307
Token
Token ID198
Feature activation+7.12e-01

Pos logit contributions
ASC+3.742
eur+3.326
PLA+3.242
 Agric+3.232
 Ribbon+3.229
Neg logit contributions
anasia-3.174
 vas-2.940
cius-2.829
 Bengals-2.753
 [*-2.740
Token
Token ID198
Feature activation+4.55e-01

Pos logit contributions
ASC+0.629
eur+0.561
 Agric+0.556
PLA+0.551
 Ribbon+0.551
Neg logit contributions
anasia-0.430
 vas-0.393
 Bengals-0.378
 [*-0.372
cius-0.368
Token
Token ID447
Feature activation+8.03e-01

Pos logit contributions
ASC+0.337
eur+0.291
 Agric+0.289
PLA+0.287
 Ribbon+0.285
Neg logit contributions
anasia-0.340
 vas-0.318
 Bengals-0.309
 [*-0.304
cius-0.300
Token
Token ID250
Feature activation+5.39e-01

Pos logit contributions
ASC+0.681
eur+0.603
 Agric+0.600
PLA+0.594
 Ribbon+0.593
Neg logit contributions
anasia-0.510
 vas-0.470
 Bengals-0.454
 [*-0.447
cius-0.440
TokenTax
Token ID27017
Feature activation+1.89e+00

Pos logit contributions
ASC+0.413
eur+0.360
 Agric+0.358
 Ribbon+0.354
PLA+0.354
Neg logit contributions
anasia-0.388
 vas-0.361
 Bengals-0.350
 [*-0.345
cius-0.340
Token.
Token ID13
Feature activation+2.12e+00

Pos logit contributions
ASC+0.436
eur+0.381
 Agric+0.378
 Ribbon+0.374
PLA+0.372
Neg logit contributions
anasia-0.406
 vas-0.379
 Bengals-0.367
 [*-0.360
cius-0.355
Tokenforms
Token ID23914
Feature activation+1.31e+00

Pos logit contributions
ASC+1.826
eur+1.613
 Agric+1.584
 Ribbon+1.581
PLA+1.580
Neg logit contributions
anasia-1.338
 vas-1.239
 Bengals-1.189
 [*-1.166
cius-1.142
Token.
Token ID13
Feature activation+1.97e+00

Pos logit contributions
ASC+0.947
eur+0.817
 Agric+0.812
 Ribbon+0.803
orate+0.799
Neg logit contributions
anasia-0.996
 vas-0.931
 Bengals-0.902
 [*-0.889
cius-0.879
Tokentext
Token ID5239
Feature activation+3.24e+00

Pos logit contributions
ASC+1.353
eur+1.146
 Agric+1.129
 Ribbon+1.126
PLA+1.126
Neg logit contributions
anasia-1.590
 vas-1.494
 Bengals-1.452
 [*-1.428
cius-1.405
Tokenrend
Token ID10920
Feature activation+3.00e+00

Pos logit contributions
ASC+2.382
eur+2.028
 Agric+2.005
 Ribbon+2.004
orate+1.985
Neg logit contributions
anasia-2.473
 vas-2.309
 Bengals-2.228
 [*-2.188
cius-2.173
Tokenerer
Token ID11882
Feature activation+4.63e+00

Pos logit contributions
ASC+1.218
eur+0.948
 Agric+0.911
 Ribbon+0.898
orate+0.888
Neg logit contributions
anasia-3.237
 vas-3.095
 Bengals-3.016
 [*-2.969
cius-2.968
Token]
Token ID60
Feature activation+1.75e+00

Pos logit contributions
ASC+3.337
eur+2.822
 Ribbon+2.811
 Agric+2.798
 parity+2.773
Neg logit contributions
anasia-3.563
 vas-3.321
 Bengals-3.185
 [*-3.137
cius-3.116
Token::
Token ID3712
Feature activation+2.30e+00

Pos logit contributions
ASC+1.199
eur+1.020
 Agric+1.010
 Ribbon+1.000
PLA+0.998
Neg logit contributions
anasia-1.416
 vas-1.326
 Bengals-1.286
 [*-1.265
cius-1.250
TokenMeasure
Token ID47384
Feature activation+2.28e+00

Pos logit contributions
ASC+1.633
eur+1.390
 Agric+1.377
PLA+1.371
 Ribbon+1.365
Neg logit contributions
anasia-1.802
 vas-1.685
 Bengals-1.639
 [*-1.612
cius-1.587
TokenText
Token ID8206
Feature activation+2.88e+00

Pos logit contributions
ASC+1.631
eur+1.389
 Ribbon+1.370
 Agric+1.368
orate+1.359
Neg logit contributions
anasia-1.777
 vas-1.661
 Bengals-1.608
 [*-1.581
cius-1.563
Token($
Token ID16763
Feature activation-2.76e-01

Pos logit contributions
ASC+2.162
eur+1.871
 Ribbon+1.856
 Agric+1.838
orate+1.817
Neg logit contributions
anasia-2.148
 vas-1.998
 Bengals-1.913
cius-1.879
 [*-1.876
Token
Token ID251
Feature activation+6.62e-02

Pos logit contributions
anasia+0.418
 vas+0.383
 Bengals+0.370
 [*+0.364
cius+0.357
Neg logit contributions
ASC-0.595
eur-0.528
 Agric-0.526
PLA-0.521
 Ribbon-0.521
Token
Token ID198
Feature activation-1.25e-01

Pos logit contributions
ASC+0.057
eur+0.050
 Agric+0.050
 Ribbon+0.050
PLA+0.050
Neg logit contributions
anasia-0.042
 vas-0.038
 Bengals-0.037
 [*-0.036
cius-0.036
Token
Token ID198
Feature activation-5.44e-01

Pos logit contributions
anasia+0.075
 vas+0.068
 Bengals+0.066
 [*+0.065
cius+0.064
Neg logit contributions
ASC-0.112
eur-0.099
 Agric-0.099
PLA-0.098
 Ribbon-0.098
TokenHe
Token ID1544
Feature activation-5.32e-01

Pos logit contributions
anasia+0.406
 vas+0.379
 Bengals+0.368
 [*+0.362
cius+0.358
Neg logit contributions
ASC-0.403
eur-0.349
 Agric-0.347
PLA-0.344
 Ribbon-0.342
Token took
Token ID1718
Feature activation+1.72e+00

Pos logit contributions
anasia+0.352
 vas+0.325
 Bengals+0.315
 [*+0.310
cius+0.304
Neg logit contributions
ASC-0.438
eur-0.386
 Agric-0.385
 Ribbon-0.380
PLA-0.380
Token apart
Token ID5475
Feature activation+4.61e+00

Pos logit contributions
ASC+1.406
 Agric+1.245
eur+1.244
 Ribbon+1.229
orate+1.222
Neg logit contributions
anasia-1.142
 vas-1.038
 Bengals-1.008
 [*-0.998
cius-0.994
Token some
Token ID617
Feature activation-9.76e-01

Pos logit contributions
ASC+3.399
 Agric+3.014
eur+2.990
 Ribbon+2.965
 Dynam+2.933
Neg logit contributions
anasia-3.379
 vas-3.047
cius-2.991
 [*-2.955
 Bengals-2.939
Token elements
Token ID4847
Feature activation-1.05e+00

Pos logit contributions
anasia+0.612
 vas+0.568
 Bengals+0.550
 [*+0.539
cius+0.526
Neg logit contributions
ASC-0.832
eur-0.737
 Agric-0.733
PLA-0.727
 Ribbon-0.726
Token of
Token ID286
Feature activation-6.70e-01

Pos logit contributions
anasia+0.686
 vas+0.634
 Bengals+0.615
 [*+0.605
cius+0.592
Neg logit contributions
ASC-0.878
eur-0.775
 Agric-0.772
PLA-0.764
 Ribbon-0.763
Token the
Token ID262
Feature activation-6.85e-01

Pos logit contributions
anasia+0.473
 vas+0.439
 Bengals+0.426
 [*+0.420
cius+0.413
Neg logit contributions
ASC-0.522
eur-0.457
 Agric-0.455
 Ribbon-0.450
PLA-0.450
Token mechanism
Token ID9030
Feature activation-2.79e-01

Pos logit contributions
anasia+0.503
 vas+0.470
 Bengals+0.457
 [*+0.450
cius+0.442
Neg logit contributions
ASC-0.514
eur-0.446
 Agric-0.444
PLA-0.440
 Ribbon-0.439
Token away
Token ID1497
Feature activation+1.31e+00

Pos logit contributions
anasia+0.383
 vas+0.355
 Bengals+0.344
 [*+0.340
cius+0.333
Neg logit contributions
ASC-0.443
eur-0.388
 Agric-0.387
PLA-0.383
 Ribbon-0.383
Token from
Token ID422
Feature activation+7.13e-01

Pos logit contributions
ASC+0.948
eur+0.822
 Agric+0.819
orate+0.801
 Dynam+0.799
Neg logit contributions
anasia-0.993
 vas-0.919
 Bengals-0.894
 [*-0.878
cius-0.875
Token Kirby
Token ID23965
Feature activation+6.22e-01

Pos logit contributions
ASC+0.565
eur+0.496
 Agric+0.495
 Ribbon+0.488
orate+0.487
Neg logit contributions
anasia-0.493
 vas-0.455
 Bengals-0.441
 [*-0.434
cius-0.431
Token's
Token ID338
Feature activation+1.39e+00

Pos logit contributions
ASC+0.505
eur+0.444
 Agric+0.442
 Ribbon+0.438
PLA+0.436
Neg logit contributions
anasia-0.418
 vas-0.384
 Bengals-0.373
 [*-0.368
cius-0.362
Token bomb
Token ID5194
Feature activation+2.19e+00

Pos logit contributions
ASC+1.118
 Agric+0.982
eur+0.980
 Ribbon+0.974
 Dynam+0.965
Neg logit contributions
anasia-0.944
 vas-0.859
 Bengals-0.835
 [*-0.826
cius-0.818
Tokenastic
Token ID3477
Feature activation+4.51e+00

Pos logit contributions
ASC+0.914
eur+0.698
 Agric+0.684
orate+0.673
PLA+0.673
Neg logit contributions
anasia-2.350
 vas-2.227
 Bengals-2.186
 [*-2.167
cius-2.155
Token style
Token ID3918
Feature activation+1.96e+00

Pos logit contributions
ASC+3.544
eur+3.154
 Dynam+3.140
 Ribbon+3.126
 Agric+3.120
Neg logit contributions
anasia-3.067
 vas-2.749
 Bengals-2.685
cius-2.676
 [*-2.658
Token of
Token ID286
Feature activation+7.20e-01

Pos logit contributions
ASC+1.537
eur+1.354
 Agric+1.338
 Dynam+1.329
 parity+1.327
Neg logit contributions
anasia-1.366
 vas-1.251
 Bengals-1.217
 [*-1.204
cius-1.189
Token storytelling
Token ID23689
Feature activation+4.22e-01

Pos logit contributions
ASC+0.567
eur+0.497
 Agric+0.495
 Ribbon+0.489
PLA+0.489
Neg logit contributions
anasia-0.501
 vas-0.464
 Bengals-0.451
 [*-0.444
cius-0.437
Token.
Token ID13
Feature activation-4.83e-02

Pos logit contributions
ASC+0.327
eur+0.287
 Agric+0.285
 Ribbon+0.282
orate+0.281
Neg logit contributions
anasia-0.299
 vas-0.275
 Bengals-0.268
 [*-0.264
cius-0.261
Token According
Token ID4784
Feature activation-1.19e-01

Pos logit contributions
anasia+0.033
 vas+0.030
 Bengals+0.029
 [*+0.029
cius+0.028
Neg logit contributions
ASC-0.039
 Agric-0.034
eur-0.034
 Ribbon-0.034
PLA-0.034
Token)
Token ID8
Feature activation+1.58e+00

Pos logit contributions
anasia+0.116
 vas+0.108
 Bengals+0.105
 [*+0.104
cius+0.102
Neg logit contributions
ASC-0.117
eur-0.101
 Agric-0.101
 Ribbon-0.100
PLA-0.100
Token Mem
Token ID4942
Feature activation+3.10e+00

Pos logit contributions
ASC+1.231
eur+1.073
 Agric+1.071
 Ribbon+1.061
PLA+1.052
Neg logit contributions
anasia-1.121
 vas-1.031
 Bengals-1.000
 [*-0.984
cius-0.975
Tokenc
Token ID66
Feature activation+2.09e+00

Pos logit contributions
ASC+2.215
eur+1.922
 Agric+1.896
 Ribbon+1.888
orate+1.875
Neg logit contributions
anasia-2.368
 vas-2.227
 Bengals-2.165
 [*-2.115
cius-2.085
Tokenpy
Token ID9078
Feature activation-5.15e-01

Pos logit contributions
ASC+1.017
eur+0.812
 Agric+0.807
orate+0.792
PLA+0.785
Neg logit contributions
anasia-2.080
 vas-1.979
 Bengals-1.937
 [*-1.914
cius-1.897
TokenIn
Token ID818
Feature activation+1.66e+00

Pos logit contributions
anasia+0.372
 vas+0.346
 Bengals+0.337
 [*+0.332
cius+0.326
Neg logit contributions
ASC-0.392
eur-0.342
 Agric-0.341
PLA-0.337
 Ribbon-0.336
TokenMemory
Token ID30871
Feature activation+4.51e+00

Pos logit contributions
ASC+1.268
eur+1.105
 Agric+1.099
 Ribbon+1.087
PLA+1.086
Neg logit contributions
anasia-1.193
 vas-1.108
 Bengals-1.077
 [*-1.059
cius-1.043
Token 4
Token ID604
Feature activation+2.88e+00

Pos logit contributions
ASC+3.242
eur+2.779
 Agric+2.748
 Ribbon+2.741
 parity+2.717
Neg logit contributions
anasia-3.429
 vas-3.193
 Bengals-3.098
cius-3.029
 [*-3.025
Token66
Token ID2791
Feature activation+3.53e+00

Pos logit contributions
ASC+2.138
eur+1.854
 Agric+1.839
 Ribbon+1.829
PLA+1.820
Neg logit contributions
anasia-2.127
 vas-1.977
 Bengals-1.907
 [*-1.894
cius-1.877
Token284
Token ID30336
Feature activation+1.17e+00

Pos logit contributions
ASC+2.636
eur+2.277
 Agric+2.259
 Ribbon+2.239
PLA+2.236
Neg logit contributions
anasia-2.594
 vas-2.416
 Bengals-2.328
 [*-2.308
cius-2.289
Token 4
Token ID604
Feature activation+2.49e-01

Pos logit contributions
ASC+0.890
eur+0.774
 Agric+0.771
PLA+0.760
 Ribbon+0.760
Neg logit contributions
anasia-0.849
 vas-0.790
 Bengals-0.763
 [*-0.755
cius-0.744
Token64
Token ID2414
Feature activation+2.17e+00

Pos logit contributions
ASC+0.177
eur+0.152
 Agric+0.152
 Ribbon+0.150
PLA+0.150
Neg logit contributions
anasia-0.193
 vas-0.181
 Bengals-0.176
 [*-0.174
cius-0.171
Token nat
Token ID34664
Feature activation+1.91e+00

Pos logit contributions
ASC+3.515
 Agric+3.224
 Ribbon+3.185
eur+3.175
 parity+3.142
Neg logit contributions
anasia-2.539
 Bengals-2.231
 vas-2.187
 [*-2.154
cius-2.153
Tokenut
Token ID315
Feature activation+1.95e+00

Pos logit contributions
ASC+1.456
eur+1.290
orate+1.263
 Agric+1.256
PLA+1.250
Neg logit contributions
anasia-1.356
 vas-1.271
 Bengals-1.252
 [*-1.227
cius-1.193
Tokenu
Token ID84
Feature activation+2.00e+00

Pos logit contributions
ASC+1.520
eur+1.345
orate+1.324
 Agric+1.324
PLA+1.312
Neg logit contributions
anasia-1.356
 vas-1.253
 Bengals-1.231
 [*-1.204
cius-1.181
Tokenwa
Token ID10247
Feature activation+1.80e+00

Pos logit contributions
ASC+1.591
eur+1.418
orate+1.404
 Agric+1.400
PLA+1.393
Neg logit contributions
anasia-1.340
 Bengals-1.215
 vas-1.213
 [*-1.175
cius-1.153
Token na
Token ID12385
Feature activation+2.21e+00

Pos logit contributions
ASC+1.468
eur+1.311
 Agric+1.297
orate+1.292
 Ribbon+1.287
Neg logit contributions
anasia-1.169
 Bengals-1.061
 vas-1.057
 [*-1.019
cius-1.018
Token ang
Token ID3550
Feature activation+4.46e+00

Pos logit contributions
ASC+1.835
eur+1.649
 Agric+1.645
 Ribbon+1.639
orate+1.632
Neg logit contributions
anasia-1.400
 Bengals-1.255
 vas-1.244
 [*-1.206
cius-1.204
Token kan
Token ID43998
Feature activation+2.58e+00

Pos logit contributions
ASC+3.710
 Agric+3.382
eur+3.366
 Ribbon+3.351
 parity+3.313
Neg logit contributions
anasia-2.719
 Bengals-2.420
 vas-2.370
 [*-2.334
cius-2.324
Tokenil
Token ID346
Feature activation+7.09e-01

Pos logit contributions
ASC+1.922
eur+1.711
 Agric+1.684
orate+1.681
PLA+1.670
Neg logit contributions
anasia-1.829
 vas-1.699
 Bengals-1.689
 [*-1.647
cius-1.602
Tokenang
Token ID648
Feature activation+2.83e+00

Pos logit contributions
ASC+0.549
eur+0.484
 Agric+0.479
orate+0.477
PLA+0.474
Neg logit contributions
anasia-0.498
 vas-0.461
 Bengals-0.453
 [*-0.443
cius-0.435
Token an
Token ID281
Feature activation+1.16e+00

Pos logit contributions
ASC+2.351
eur+2.102
 Agric+2.097
 Ribbon+2.079
orate+2.076
Neg logit contributions
anasia-1.788
 Bengals-1.607
 vas-1.589
 [*-1.541
cius-1.539
Tokenak
Token ID461
Feature activation+1.94e+00

Pos logit contributions
ASC+0.850
eur+0.750
 Agric+0.736
orate+0.730
 Ribbon+0.725
Neg logit contributions
anasia-0.856
 vas-0.798
 Bengals-0.787
 [*-0.767
cius-0.754
Tokenre
Token ID260
Feature activation+4.34e-02

Pos logit contributions
ASC+0.875
eur+0.792
orate+0.782
 Agric+0.777
PLA+0.773
Neg logit contributions
anasia-0.517
 vas-0.475
 Bengals-0.456
 [*-0.443
cius-0.430
Token.
Token ID13
Feature activation+1.11e+00

Pos logit contributions
ASC+0.033
eur+0.029
 Agric+0.029
PLA+0.028
orate+0.028
Neg logit contributions
anasia-0.031
 vas-0.029
 Bengals-0.028
 [*-0.028
cius-0.027
Tokenkov
Token ID21862
Feature activation+1.71e+00

Pos logit contributions
ASC+0.795
eur+0.690
 Agric+0.681
PLA+0.673
orate+0.673
Neg logit contributions
anasia-0.850
 vas-0.794
 Bengals-0.773
 [*-0.762
cius-0.749
Tokenid
Token ID312
Feature activation+2.22e+00

Pos logit contributions
ASC+1.304
eur+1.137
 Agric+1.128
orate+1.117
PLA+1.109
Neg logit contributions
anasia-1.230
 vas-1.151
 Bengals-1.117
 [*-1.099
cius-1.068
Tokeng
Token ID70
Feature activation+3.08e+00

Pos logit contributions
ASC+1.660
eur+1.459
 Agric+1.438
orate+1.431
PLA+1.409
Neg logit contributions
anasia-1.618
 vas-1.511
 Bengals-1.466
 [*-1.447
cius-1.397
Tokenoyal
Token ID4815
Feature activation+4.46e+00

Pos logit contributions
ASC+2.320
eur+2.026
 Agric+1.994
orate+1.983
PLA+1.977
Neg logit contributions
anasia-2.244
 vas-2.099
 Bengals-2.045
 [*-1.996
cius-1.937
Token.
Token ID13
Feature activation+1.95e+00

Pos logit contributions
ASC+3.198
eur+2.827
 Agric+2.716
orate+2.703
 Ribbon+2.678
Neg logit contributions
anasia-3.352
 vas-3.131
 Bengals-3.061
 [*-3.034
cius-2.893
Tokennet
Token ID3262
Feature activation+1.58e+00

Pos logit contributions
ASC+1.366
eur+1.191
 Agric+1.165
orate+1.158
PLA+1.153
Neg logit contributions
anasia-1.528
 vas-1.424
 Bengals-1.393
 [*-1.372
cius-1.343
Token)
Token ID8
Feature activation+4.32e-01

Pos logit contributions
ASC+1.123
eur+0.973
 Agric+0.968
PLA+0.957
 Ribbon+0.951
Neg logit contributions
anasia-1.225
 vas-1.139
 Bengals-1.110
 [*-1.091
cius-1.085
Token or
Token ID393
Feature activation-2.63e-01

Pos logit contributions
ASC+0.364
eur+0.321
 Agric+0.320
 Ribbon+0.317
PLA+0.316
Neg logit contributions
anasia-0.279
 vas-0.257
 Bengals-0.248
 [*-0.244
cius-0.240
Token Stan
Token ID7299
Feature activation-1.64e-01

Pos logit contributions
anasia+0.191
 vas+0.179
 Bengals+0.175
 [*+0.173
cius+0.168
Neg logit contributions
ASC-0.197
eur-0.172
 Agric-0.169
PLA-0.169
orate-0.168
Tokenong
Token ID506
Feature activation+2.30e+00

Pos logit contributions
ASC+1.512
eur+1.277
orate+1.254
PLA+1.245
 Agric+1.234
Neg logit contributions
anasia-1.948
 vas-1.856
 Bengals-1.810
 [*-1.794
cius-1.752
TokenCh
Token ID1925
Feature activation+3.14e+00

Pos logit contributions
ASC+1.518
eur+1.285
 Agric+1.270
PLA+1.267
 Ribbon+1.263
Neg logit contributions
anasia-1.906
 vas-1.786
 Bengals-1.746
 [*-1.724
cius-1.698
Tokenoya
Token ID23790
Feature activation+2.41e+00

Pos logit contributions
ASC+3.018
eur+2.746
orate+2.720
 Agric+2.719
PLA+2.707
Neg logit contributions
anasia-1.576
 vas-1.448
 Bengals-1.407
 [*-1.363
cius-1.319
TokenWeek
Token ID20916
Feature activation+3.03e+00

Pos logit contributions
ASC+1.787
eur+1.550
PLA+1.526
 Ribbon+1.522
 Agric+1.522
Neg logit contributions
anasia-1.788
 vas-1.664
 Bengals-1.618
 [*-1.603
cius-1.575
Tokenend
Token ID437
Feature activation+2.15e+00

Pos logit contributions
ASC+2.284
eur+2.026
orate+2.000
 Agric+1.973
PLA+1.970
Neg logit contributions
anasia-2.167
 vas-2.024
 Bengals-1.975
cius-1.923
 [*-1.921
TokenT
Token ID51
Feature activation+4.45e+00

Pos logit contributions
ASC+1.690
eur+1.476
 Agric+1.462
PLA+1.454
 Ribbon+1.454
Neg logit contributions
anasia-1.506
 vas-1.396
 Bengals-1.354
 [*-1.338
cius-1.315
Tokenear
Token ID451
Feature activation+1.83e+00

Pos logit contributions
ASC+2.888
eur+2.466
orate+2.405
PLA+2.393
 Agric+2.332
Neg logit contributions
anasia-3.678
 vas-3.494
 Bengals-3.412
 [*-3.373
cius-3.339
TokenV
Token ID53
Feature activation+1.87e+00

Pos logit contributions
ASC+1.329
eur+1.151
 Agric+1.138
PLA+1.129
 Ribbon+1.128
Neg logit contributions
anasia-1.388
 vas-1.293
 Bengals-1.260
 [*-1.247
cius-1.225
Tokenoid
Token ID1868
Feature activation+1.05e+00

Pos logit contributions
ASC+1.658
eur+1.475
 Agric+1.458
orate+1.457
PLA+1.450
Neg logit contributions
anasia-1.117
 vas-1.027
 Bengals-0.991
 [*-0.972
cius-0.944
TokenRay
Token ID19591
Feature activation+1.76e+00

Pos logit contributions
ASC+0.788
eur+0.686
 Agric+0.680
PLA+0.674
 Ribbon+0.674
Neg logit contributions
anasia-0.774
 vas-0.722
 Bengals-0.702
 [*-0.691
cius-0.682
TokenJ
Token ID41
Feature activation+3.37e+00

Pos logit contributions
ASC+1.342
eur+1.169
PLA+1.150
 Agric+1.148
 Ribbon+1.145
Neg logit contributions
anasia-1.269
 vas-1.181
 Bengals-1.147
 [*-1.136
cius-1.115
Tokenargs
Token ID22046
Feature activation-8.49e-01

Pos logit contributions
anasia+0.040
 vas+0.037
 Bengals+0.035
 [*+0.035
cius+0.034
Neg logit contributions
ASC-0.051
eur-0.045
 Agric-0.044
PLA-0.044
 Ribbon-0.044
Token["
Token ID14692
Feature activation-3.83e-01

Pos logit contributions
anasia+0.555
 vas+0.515
 [*+0.499
 Bengals+0.494
cius+0.482
Neg logit contributions
ASC-0.700
 Agric-0.622
eur-0.614
 Ribbon-0.614
orate-0.612
Tokenimages
Token ID17566
Feature activation+1.93e+00

Pos logit contributions
anasia+0.138
 vas+0.118
 Bengals+0.111
 [*+0.107
cius+0.104
Neg logit contributions
ASC-0.431
eur-0.393
 Agric-0.393
 Ribbon-0.390
PLA-0.389
Token"]
Token ID8973
Feature activation+9.82e-01

Pos logit contributions
ASC+1.135
eur+0.944
 Agric+0.922
PLA+0.918
orate+0.906
Neg logit contributions
anasia-1.734
 vas-1.635
 Bengals-1.601
 [*-1.576
cius-1.569
Token):
Token ID2599
Feature activation+1.26e+00

Pos logit contributions
ASC+0.611
eur+0.515
 Agric+0.512
PLA+0.505
 Ribbon+0.503
Neg logit contributions
anasia-0.847
 vas-0.797
 Bengals-0.778
 [*-0.769
cius-0.760
Token #
Token ID1303
Feature activation+4.45e+00

Pos logit contributions
ASC+0.993
eur+0.878
 Agric+0.871
 Ribbon+0.865
PLA+0.861
Neg logit contributions
anasia-0.874
 vas-0.788
 Bengals-0.771
 [*-0.758
cius-0.756
Token load
Token ID3440
Feature activation+2.38e+00

Pos logit contributions
ASC+3.268
 Agric+2.863
PLA+2.857
 Dynam+2.817
 parity+2.814
Neg logit contributions
anasia-3.329
 vas-2.913
 Bengals-2.907
cius-2.897
 [*-2.794
Token the
Token ID262
Feature activation+2.86e-01

Pos logit contributions
ASC+1.754
eur+1.522
 Agric+1.507
PLA+1.496
 Ribbon+1.486
Neg logit contributions
anasia-1.791
 vas-1.642
 Bengals-1.604
cius-1.582
 [*-1.571
Token image
Token ID2939
Feature activation+1.75e-01

Pos logit contributions
ASC+0.218
eur+0.191
 Agric+0.190
 Ribbon+0.188
PLA+0.187
Neg logit contributions
anasia-0.206
 vas-0.191
 Bengals-0.185
 [*-0.183
cius-0.180
Token,
Token ID11
Feature activation+1.21e+00

Pos logit contributions
ASC+0.144
eur+0.127
 Agric+0.126
 Ribbon+0.125
PLA+0.125
Neg logit contributions
anasia-0.116
 vas-0.107
 Bengals-0.104
 [*-0.102
cius-0.100
Token resize
Token ID47558
Feature activation+9.04e-01

Pos logit contributions
ASC+0.756
eur+0.640
 Agric+0.634
orate+0.625
PLA+0.625
Neg logit contributions
anasia-1.038
 vas-0.970
 Bengals-0.953
 [*-0.938
cius-0.928
TokenTrump
Token ID6170
Feature activation+1.06e+00

Pos logit contributions
anasia+0.121
 vas+0.112
 Bengals+0.109
 [*+0.107
cius+0.106
Neg logit contributions
ASC-0.128
eur-0.112
 Agric-0.111
PLA-0.110
 Ribbon-0.110
Token
Token ID447
Feature activation+1.40e+00

Pos logit contributions
ASC+0.851
eur+0.751
 Agric+0.743
 Ribbon+0.737
PLA+0.736
Neg logit contributions
anasia-0.725
 vas-0.666
 Bengals-0.645
 [*-0.635
cius-0.626
Token
Token ID247
Feature activation+3.25e-01

Pos logit contributions
ASC+1.214
eur+1.081
 Agric+1.072
 Ribbon+1.063
PLA+1.062
Neg logit contributions
anasia-0.864
 vas-0.791
 Bengals-0.764
 [*-0.751
cius-0.736
Tokens
Token ID82
Feature activation-1.85e-01

Pos logit contributions
ASC+0.264
eur+0.232
 Agric+0.230
PLA+0.228
 Ribbon+0.228
Neg logit contributions
anasia-0.220
 vas-0.203
 Bengals-0.196
 [*-0.194
cius-0.190
Token sal
Token ID3664
Feature activation+4.32e-01

Pos logit contributions
anasia+0.124
 vas+0.115
 Bengals+0.111
 [*+0.110
cius+0.108
Neg logit contributions
ASC-0.151
eur-0.133
 Agric-0.132
 Ribbon-0.131
PLA-0.131
Tokenvo
Token ID13038
Feature activation+4.42e+00

Pos logit contributions
ASC+0.260
eur+0.218
 Agric+0.217
 Ribbon+0.213
PLA+0.213
Neg logit contributions
anasia-0.381
 vas-0.359
 Bengals-0.351
 [*-0.347
cius-0.342
Token ran
Token ID4966
Feature activation+1.35e-01

Pos logit contributions
ASC+3.372
eur+3.043
 parity+2.929
PLA+2.917
 Agric+2.917
Neg logit contributions
anasia-3.089
 vas-2.818
 Bengals-2.742
cius-2.727
 [*-2.670
Token counter
Token ID3753
Feature activation+1.17e+00

Pos logit contributions
ASC+0.113
eur+0.100
 Agric+0.099
 Ribbon+0.098
PLA+0.098
Neg logit contributions
anasia-0.088
 vas-0.081
 Bengals-0.078
 [*-0.077
cius-0.076
Token to
Token ID284
Feature activation-2.31e-01

Pos logit contributions
ASC+0.892
eur+0.780
 Agric+0.775
PLA+0.772
orate+0.765
Neg logit contributions
anasia-0.839
 vas-0.777
 Bengals-0.758
 [*-0.743
cius-0.737
Token efforts
Token ID4040
Feature activation-8.75e-01

Pos logit contributions
anasia+0.157
 vas+0.145
 Bengals+0.141
 [*+0.139
cius+0.136
Neg logit contributions
ASC-0.186
eur-0.163
 Agric-0.162
 Ribbon-0.161
PLA-0.161
Token this
Token ID428
Feature activation-3.11e-01

Pos logit contributions
anasia+0.591
 vas+0.550
 Bengals+0.535
 [*+0.527
cius+0.516
Neg logit contributions
ASC-0.707
eur-0.619
 Agric-0.618
 Ribbon-0.611
PLA-0.611
Token things
Token ID1243
Feature activation-1.28e+00

Pos logit contributions
anasia+0.717
 vas+0.669
 Bengals+0.644
 [*+0.639
cius+0.619
Neg logit contributions
ASC-0.880
eur-0.775
 Agric-0.774
orate-0.766
PLA-0.766
Token.
Token ID13
Feature activation-6.74e-01

Pos logit contributions
anasia+0.867
 vas+0.805
 Bengals+0.778
 [*+0.772
cius+0.751
Neg logit contributions
ASC-1.024
eur-0.901
 Agric-0.900
PLA-0.889
 Ribbon-0.886
Token See
Token ID4091
Feature activation-1.13e+00

Pos logit contributions
anasia+0.483
 vas+0.450
 Bengals+0.436
 [*+0.432
cius+0.422
Neg logit contributions
ASC-0.516
eur-0.451
 Agric-0.449
PLA-0.444
orate-0.444
Token |
Token ID930
Feature activation+5.79e-01

Pos logit contributions
anasia+0.814
 vas+0.758
 Bengals+0.735
 [*+0.727
cius+0.713
Neg logit contributions
ASC-0.867
eur-0.756
 Agric-0.753
PLA-0.744
 Ribbon-0.743
Tokenaut
Token ID2306
Feature activation-1.58e+00

Pos logit contributions
ASC+0.446
eur+0.389
 Agric+0.383
PLA+0.380
 Ribbon+0.380
Neg logit contributions
anasia-0.416
 vas-0.387
 Bengals-0.378
 [*-0.368
cius-0.364
Tokenoc
Token ID420
Feature activation+4.40e+00

Pos logit contributions
anasia+1.194
 vas+1.114
 Bengals+1.075
 [*+1.073
cius+1.061
Neg logit contributions
ASC-1.152
 Agric-1.004
eur-0.987
 Ribbon-0.981
PLA-0.981
Tokenomm
Token ID2002
Feature activation+2.46e+00

Pos logit contributions
ASC+3.496
orate+3.078
eur+3.070
 Agric+2.988
 Ribbon+2.970
Neg logit contributions
anasia-2.984
 vas-2.796
 Bengals-2.725
 [*-2.629
cius-2.596
Tokenand
Token ID392
Feature activation+1.38e+00

Pos logit contributions
ASC+1.753
eur+1.525
orate+1.509
 Agric+1.500
 Ribbon+1.498
Neg logit contributions
anasia-1.879
 vas-1.781
 Bengals-1.731
 [*-1.675
cius-1.662
Token|
Token ID91
Feature activation+1.20e-02

Pos logit contributions
ASC+0.865
eur+0.736
 Agric+0.718
 Ribbon+0.711
orate+0.710
Neg logit contributions
anasia-1.183
 vas-1.115
 Bengals-1.090
 [*-1.070
cius-1.057
Token.
Token ID13
Feature activation-5.61e-01

Pos logit contributions
ASC+0.009
eur+0.008
 Agric+0.008
 Ribbon+0.008
PLA+0.008
Neg logit contributions
anasia-0.008
 vas-0.008
 Bengals-0.008
 [*-0.007
cius-0.007
Token 3
Token ID513
Feature activation-6.69e-01

Pos logit contributions
anasia+0.388
 vas+0.359
 Bengals+0.349
 [*+0.343
cius+0.338
Neg logit contributions
ASC-0.445
eur-0.390
 Agric-0.388
 Ribbon-0.384
PLA-0.383
Token.
Token ID13
Feature activation+3.06e-01

Pos logit contributions
ASC+0.804
eur+0.700
 Agric+0.691
PLA+0.689
orate+0.683
Neg logit contributions
anasia-0.763
 vas-0.708
 Bengals-0.689
 [*-0.674
cius-0.670
Tokenparse
Token ID29572
Feature activation+2.50e+00

Pos logit contributions
ASC+0.224
 Agric+0.194
eur+0.194
 Ribbon+0.192
PLA+0.191
Neg logit contributions
anasia-0.230
 vas-0.214
 Bengals-0.208
 [*-0.206
cius-0.203
Token_
Token ID62
Feature activation+1.90e+00

Pos logit contributions
ASC+1.820
eur+1.580
PLA+1.553
 Agric+1.545
orate+1.535
Neg logit contributions
anasia-1.893
 vas-1.768
 Bengals-1.711
cius-1.686
 [*-1.680
Tokenargs
Token ID22046
Feature activation+8.30e-02

Pos logit contributions
ASC+1.509
eur+1.327
PLA+1.308
orate+1.301
 Agric+1.285
Neg logit contributions
anasia-1.301
 vas-1.217
 Bengals-1.179
 [*-1.148
cius-1.148
Token())
Token ID28955
Feature activation-2.69e-01

Pos logit contributions
ASC+0.069
eur+0.061
 Agric+0.061
 Ribbon+0.060
orate+0.060
Neg logit contributions
anasia-0.054
 vas-0.050
 Bengals-0.049
 [*-0.048
cius-0.047
Token #
Token ID1303
Feature activation+4.39e+00

Pos logit contributions
anasia+0.180
 vas+0.164
 Bengals+0.160
 [*+0.157
cius+0.156
Neg logit contributions
ASC-0.221
eur-0.194
 Agric-0.194
 Ribbon-0.191
PLA-0.191
Token initialize
Token ID41216
Feature activation+1.81e+00

Pos logit contributions
ASC+3.059
 Agric+2.655
eur+2.633
orate+2.630
PLA+2.628
Neg logit contributions
anasia-3.433
 vas-3.112
 Bengals-3.104
cius-3.041
 [*-2.983
Token a
Token ID257
Feature activation+1.44e+00

Pos logit contributions
ASC+1.397
eur+1.227
 Agric+1.214
 Ribbon+1.199
PLA+1.197
Neg logit contributions
anasia-1.285
 vas-1.178
 Bengals-1.152
 [*-1.132
cius-1.131
Token rectangular
Token ID36954
Feature activation-3.11e-01

Pos logit contributions
ASC+0.822
eur+0.683
 Agric+0.679
 Ribbon+0.667
PLA+0.664
Neg logit contributions
anasia-1.311
 vas-1.233
 Bengals-1.207
 [*-1.194
cius-1.181
Token and
Token ID290
Feature activation-1.13e+00

Pos logit contributions
anasia+0.203
 vas+0.186
 Bengals+0.181
 [*+0.178
cius+0.175
Neg logit contributions
ASC-0.259
eur-0.229
 Agric-0.227
 Ribbon-0.225
PLA-0.225
Token square
Token ID6616
Feature activation-1.06e+00

Pos logit contributions
anasia+0.881
 vas+0.834
 Bengals+0.808
 [*+0.803
cius+0.779
Neg logit contributions
ASC-0.793
 Agric-0.683
eur-0.683
PLA-0.677
 Ribbon-0.670
Token make
Token ID787
Feature activation+1.87e-01

Pos logit contributions
ASC+0.302
eur+0.266
 Agric+0.266
PLA+0.263
 Ribbon+0.263
Neg logit contributions
anasia-0.235
 vas-0.216
 Bengals-0.208
 [*-0.206
cius-0.203
Token it
Token ID340
Feature activation+6.07e-01

Pos logit contributions
ASC+0.150
eur+0.132
 Agric+0.131
 Ribbon+0.130
PLA+0.130
Neg logit contributions
anasia-0.128
 vas-0.118
 Bengals-0.114
 [*-0.113
cius-0.111
Token through
Token ID832
Feature activation+1.49e-02

Pos logit contributions
ASC+0.500
eur+0.442
 Agric+0.442
 Ribbon+0.437
PLA+0.435
Neg logit contributions
anasia-0.400
 vas-0.367
 Bengals-0.355
 [*-0.351
cius-0.348
Token the
Token ID262
Feature activation+6.71e-01

Pos logit contributions
ASC+0.012
eur+0.010
 Agric+0.010
 Ribbon+0.010
PLA+0.010
Neg logit contributions
anasia-0.010
 vas-0.010
 Bengals-0.009
 [*-0.009
cius-0.009
Token g
Token ID308
Feature activation+2.54e+00

Pos logit contributions
ASC+0.556
 Agric+0.491
eur+0.491
 Ribbon+0.484
PLA+0.482
Neg logit contributions
anasia-0.441
 vas-0.404
 Bengals-0.391
 [*-0.386
cius-0.381
Tokenauntlet
Token ID32633
Feature activation+4.37e+00

Pos logit contributions
ASC+1.525
eur+1.276
 Agric+1.274
orate+1.245
PLA+1.237
Neg logit contributions
anasia-2.219
 vas-2.110
 Bengals-2.066
 [*-2.036
cius-2.015
Token of
Token ID286
Feature activation+9.94e-01

Pos logit contributions
ASC+3.383
 Agric+2.984
eur+2.967
 parity+2.924
 Ribbon+2.909
Neg logit contributions
anasia-3.057
 vas-2.773
cius-2.712
 Bengals-2.687
 [*-2.660
Token the
Token ID262
Feature activation+2.83e-02

Pos logit contributions
ASC+0.810
 Agric+0.717
eur+0.714
 Ribbon+0.704
orate+0.701
Neg logit contributions
anasia-0.665
 vas-0.608
 Bengals-0.590
 [*-0.580
cius-0.577
Token Oregon
Token ID8819
Feature activation+6.70e-01

Pos logit contributions
ASC+0.024
eur+0.021
 Agric+0.021
 Ribbon+0.021
PLA+0.021
Neg logit contributions
anasia-0.018
 vas-0.017
 Bengals-0.016
 [*-0.016
cius-0.016
Token State
Token ID1812
Feature activation+1.48e-01

Pos logit contributions
ASC+0.604
 Agric+0.538
eur+0.538
 Ribbon+0.531
PLA+0.531
Neg logit contributions
anasia-0.390
 vas-0.356
 Bengals-0.343
 [*-0.338
cius-0.331
Token voter
Token ID10765
Feature activation-1.47e+00

Pos logit contributions
ASC+0.119
eur+0.104
 Agric+0.104
 Ribbon+0.102
PLA+0.102
Neg logit contributions
anasia-0.102
 vas-0.094
 Bengals-0.091
 [*-0.090
cius-0.089
Token
Token ID198
Feature activation+8.75e-01

Pos logit contributions
ASC+0.764
eur+0.681
 Agric+0.673
PLA+0.668
 Ribbon+0.665
Neg logit contributions
anasia-0.534
 vas-0.488
 Bengals-0.471
 [*-0.461
cius-0.460
Tokenimpl
Token ID23928
Feature activation-2.06e+00

Pos logit contributions
ASC+0.695
eur+0.609
 Agric+0.605
PLA+0.599
orate+0.596
Neg logit contributions
anasia-0.606
 vas-0.563
 Bengals-0.546
 [*-0.537
cius-0.528
Token Board
Token ID5926
Feature activation+3.63e-01

Pos logit contributions
anasia+1.262
 vas+1.160
 Bengals+1.119
 [*+1.112
cius+1.066
Neg logit contributions
ASC-1.788
eur-1.581
PLA-1.570
 Agric-1.567
 Ribbon-1.555
Token {
Token ID1391
Feature activation-3.45e+00

Pos logit contributions
ASC+0.359
eur+0.323
 Agric+0.323
 Ribbon+0.319
PLA+0.319
Neg logit contributions
anasia-0.180
 vas-0.161
 Bengals-0.154
 [*-0.149
cius-0.149
Token pub
Token ID2240
Feature activation-2.04e+00

Pos logit contributions
anasia+2.079
 vas+1.947
 Bengals+1.886
 [*+1.862
cius+1.773
Neg logit contributions
ASC-3.005
eur-2.667
PLA-2.640
 Agric-2.617
orate-2.602
Token fn
Token ID24714
Feature activation-7.33e+00

Pos logit contributions
anasia+1.167
 vas+1.073
 Bengals+1.027
 [*+1.009
cius+0.986
Neg logit contributions
ASC-1.852
eur-1.651
 Agric-1.639
PLA-1.636
 Ribbon-1.630
Token copy
Token ID4866
Feature activation+1.39e+00

Pos logit contributions
anasia+4.126
 vas+4.002
 [*+3.740
 Bengals+3.723
cius+3.454
Neg logit contributions
ASC-6.497
eur-5.801
PLA-5.792
 Agric-5.705
orate-5.678
Token_
Token ID62
Feature activation+1.81e+00

Pos logit contributions
ASC+1.257
 Agric+1.115
eur+1.113
orate+1.100
PLA+1.099
Neg logit contributions
anasia-0.816
 vas-0.747
 Bengals-0.718
 [*-0.695
cius-0.692
Tokenboard
Token ID3526
Feature activation+1.24e+00

Pos logit contributions
ASC+1.387
eur+1.215
 Agric+1.199
orate+1.188
PLA+1.181
Neg logit contributions
anasia-1.301
 vas-1.212
 Bengals-1.182
 [*-1.151
cius-1.138
Token (
Token ID357
Feature activation-1.27e+00

Pos logit contributions
ASC+1.094
eur+0.969
 Agric+0.967
orate+0.956
PLA+0.953
Neg logit contributions
anasia-0.750
 vas-0.686
 Bengals-0.665
cius-0.644
 [*-0.642
Token &
Token ID1222
Feature activation-2.83e+00

Pos logit contributions
anasia+0.786
 vas+0.723
 Bengals+0.698
 [*+0.687
cius+0.673
Neg logit contributions
ASC-1.098
eur-0.974
 Agric-0.969
PLA-0.960
 Ribbon-0.960
Token <
Token ID1279
Feature activation+5.33e-01

Pos logit contributions
ASC+0.767
eur+0.685
 Agric+0.683
PLA+0.677
orate+0.677
Neg logit contributions
anasia-0.410
 vas-0.372
 Bengals-0.356
 [*-0.344
cius-0.344
Token T
Token ID309
Feature activation-6.68e-01

Pos logit contributions
ASC+0.444
 Agric+0.393
eur+0.390
 Ribbon+0.389
orate+0.385
Neg logit contributions
anasia-0.347
 vas-0.319
 Bengals-0.307
 [*-0.303
cius-0.301
Token >
Token ID1875
Feature activation-7.37e-01

Pos logit contributions
anasia+0.265
 vas+0.231
 Bengals+0.219
 [*+0.212
cius+0.210
Neg logit contributions
ASC-0.725
eur-0.659
 Agric-0.656
PLA-0.653
 Ribbon-0.653
Token {
Token ID1391
Feature activation-2.66e+00

Pos logit contributions
anasia+0.435
 vas+0.398
 Bengals+0.383
 [*+0.376
cius+0.370
Neg logit contributions
ASC-0.660
eur-0.587
 Agric-0.585
 Ribbon-0.580
PLA-0.579
Token pub
Token ID2240
Feature activation-1.11e+00

Pos logit contributions
anasia+1.540
 vas+1.419
 Bengals+1.368
 [*+1.357
cius+1.298
Neg logit contributions
ASC-2.394
eur-2.131
PLA-2.120
 Agric-2.109
orate-2.091
Token fn
Token ID24714
Feature activation-6.87e+00

Pos logit contributions
anasia+0.630
 vas+0.573
 Bengals+0.553
 [*+0.543
cius+0.531
Neg logit contributions
ASC-1.011
eur-0.904
 Agric-0.902
 Ribbon-0.892
PLA-0.890
Token new
Token ID649
Feature activation-3.67e-01

Pos logit contributions
anasia+4.275
 vas+4.106
 [*+3.887
 Bengals+3.860
cius+3.709
Neg logit contributions
ASC-5.746
PLA-5.105
eur-5.098
 Agric-4.997
orate-4.942
Token (
Token ID357
Feature activation-1.39e+00

Pos logit contributions
anasia+0.188
 vas+0.170
 Bengals+0.163
 [*+0.159
cius+0.155
Neg logit contributions
ASC-0.357
eur-0.321
 Agric-0.320
orate-0.317
 Ribbon-0.316
Token t
Token ID256
Feature activation-2.04e-01

Pos logit contributions
anasia+0.857
 vas+0.787
 Bengals+0.760
 [*+0.747
cius+0.733
Neg logit contributions
ASC-1.209
eur-1.073
 Agric-1.069
PLA-1.058
 Ribbon-1.058
Token :
Token ID1058
Feature activation-1.14e+00

Pos logit contributions
anasia+0.130
 vas+0.118
 Bengals+0.114
 [*+0.112
cius+0.111
Neg logit contributions
ASC-0.172
 Agric-0.154
eur-0.153
 Ribbon-0.152
PLA-0.151
Token T
Token ID309
Feature activation+9.63e-01

Pos logit contributions
anasia+0.726
 vas+0.668
 Bengals+0.646
 [*+0.636
cius+0.624
Neg logit contributions
ASC-0.965
eur-0.854
 Agric-0.851
 Ribbon-0.842
PLA-0.841
Token <
Token ID1279
Feature activation+2.99e-01

Pos logit contributions
ASC+0.906
eur+0.815
 Agric+0.814
PLA+0.808
orate+0.806
Neg logit contributions
anasia-0.422
 vas-0.379
 Bengals-0.358
cius-0.346
 [*-0.345
Token T
Token ID309
Feature activation-6.83e-01

Pos logit contributions
ASC+0.253
 Agric+0.223
eur+0.222
 Ribbon+0.221
PLA+0.219
Neg logit contributions
anasia-0.192
 vas-0.176
 Bengals-0.170
 [*-0.167
cius-0.166
Token >
Token ID1875
Feature activation-5.87e-01

Pos logit contributions
anasia+0.258
 vas+0.223
 Bengals+0.212
 [*+0.205
cius+0.202
Neg logit contributions
ASC-0.755
eur-0.687
 Agric-0.684
PLA-0.682
 Ribbon-0.681
Token {
Token ID1391
Feature activation-2.91e+00

Pos logit contributions
anasia+0.281
 vas+0.249
 Bengals+0.237
 [*+0.231
cius+0.230
Neg logit contributions
ASC-0.591
 Agric-0.534
eur-0.533
 Ribbon-0.528
PLA-0.527
Token pub
Token ID2240
Feature activation-7.09e-01

Pos logit contributions
anasia+1.734
 vas+1.602
 Bengals+1.545
 [*+1.527
cius+1.481
Neg logit contributions
ASC-2.571
eur-2.289
 Agric-2.264
PLA-2.262
 Ribbon-2.243
Token fn
Token ID24714
Feature activation-6.61e+00

Pos logit contributions
anasia+0.443
 vas+0.401
 Bengals+0.391
 [*+0.382
cius+0.378
Neg logit contributions
ASC-0.612
 Agric-0.543
eur-0.543
orate-0.536
 Ribbon-0.535
Token load
Token ID3440
Feature activation+1.93e+00

Pos logit contributions
anasia+3.874
 vas+3.748
 [*+3.548
 Bengals+3.528
cius+3.346
Neg logit contributions
ASC-5.714
eur-5.115
PLA-5.068
 Agric-5.033
orate-5.007
Token <
Token ID1279
Feature activation+5.93e-01

Pos logit contributions
ASC+1.850
 Agric+1.628
eur+1.624
PLA+1.616
 Dynam+1.607
Neg logit contributions
anasia-1.036
 vas-0.942
 Bengals-0.901
cius-0.871
 [*-0.862
Token '
Token ID705
Feature activation+1.54e+00

Pos logit contributions
ASC+0.523
 Agric+0.465
eur+0.464
 Ribbon+0.460
PLA+0.458
Neg logit contributions
anasia-0.357
 vas-0.326
 Bengals-0.314
 [*-0.309
cius-0.305
Tokena
Token ID64
Feature activation+8.92e-01

Pos logit contributions
ASC+1.039
eur+0.885
 Agric+0.877
 Ribbon+0.865
PLA+0.856
Neg logit contributions
anasia-1.246
 vas-1.167
 Bengals-1.136
 [*-1.125
cius-1.115
Token >
Token ID1875
Feature activation+4.86e-01

Pos logit contributions
ASC+0.829
eur+0.744
 Agric+0.738
 Ribbon+0.736
orate+0.734
Neg logit contributions
anasia-0.494
 vas-0.442
 Bengals-0.428
 [*-0.420
cius-0.414
Token null
Token ID9242
Feature activation-6.20e-01

Pos logit contributions
ASC+0.548
eur+0.477
 Agric+0.474
 Ribbon+0.470
orate+0.469
Neg logit contributions
anasia-0.534
 vas-0.493
 Bengals-0.482
 [*-0.471
cius-0.467
Token atomic
Token ID17226
Feature activation-2.40e+00

Pos logit contributions
anasia+0.442
 vas+0.410
 Bengals+0.399
 [*+0.393
cius+0.386
Neg logit contributions
ASC-0.479
eur-0.419
 Agric-0.417
 Ribbon-0.412
PLA-0.411
Token pointer
Token ID17562
Feature activation-1.58e+00

Pos logit contributions
anasia+1.586
 vas+1.482
 Bengals+1.428
 [*+1.420
cius+1.380
Neg logit contributions
ASC-1.960
eur-1.721
 Agric-1.717
PLA-1.711
 Ribbon-1.695
Token.
Token ID13
Feature activation+6.49e-01

Pos logit contributions
anasia+1.094
 vas+1.023
 Bengals+0.990
 [*+0.979
cius+0.957
Neg logit contributions
ASC-1.250
eur-1.096
 Agric-1.088
PLA-1.085
 Ribbon-1.077
Token pub
Token ID2240
Feature activation-1.92e+00

Pos logit contributions
ASC+0.518
 Agric+0.455
eur+0.455
 Ribbon+0.450
orate+0.448
Neg logit contributions
anasia-0.445
 vas-0.408
 Bengals-0.397
 [*-0.390
cius-0.385
Token fn
Token ID24714
Feature activation-6.54e+00

Pos logit contributions
anasia+1.086
 vas+0.992
 Bengals+0.953
 [*+0.937
cius+0.915
Neg logit contributions
ASC-1.762
eur-1.574
 Agric-1.568
PLA-1.555
 Ribbon-1.553
Token null
Token ID9242
Feature activation+5.20e-01

Pos logit contributions
anasia+3.341
 vas+3.191
 [*+2.983
 Bengals+2.936
cius+2.839
Neg logit contributions
ASC-6.181
PLA-5.601
eur-5.587
 Agric-5.515
orate-5.432
Token ()
Token ID7499
Feature activation-1.01e+00

Pos logit contributions
ASC+0.496
eur+0.444
 Agric+0.441
orate+0.439
PLA+0.436
Neg logit contributions
anasia-0.277
 vas-0.253
 Bengals-0.242
 [*-0.234
cius-0.231
Token ->
Token ID4613
Feature activation-1.93e+00

Pos logit contributions
anasia+0.439
 vas+0.384
 Bengals+0.367
 [*+0.355
cius+0.348
Neg logit contributions
ASC-1.057
eur-0.957
 Agric-0.954
 Ribbon-0.947
PLA-0.945
Token Atomic
Token ID28976
Feature activation+1.47e+00

Pos logit contributions
anasia+1.472
 vas+1.379
 Bengals+1.342
 [*+1.327
cius+1.303
Neg logit contributions
ASC-1.386
eur-1.198
 Agric-1.189
PLA-1.179
 Ribbon-1.173
Token <
Token ID1279
Feature activation+8.89e-02

Pos logit contributions
ASC+1.489
eur+1.342
 Agric+1.331
 Ribbon+1.328
orate+1.324
Neg logit contributions
anasia-0.684
 vas-0.616
 Bengals-0.588
cius-0.557
 [*-0.556
Token Guard
Token ID4932
Feature activation-1.35e-01

Pos logit contributions
anasia+3.503
 vas+3.323
 Bengals+3.242
 [*+3.204
cius+3.113
Neg logit contributions
ASC-3.554
PLA-3.055
eur-3.014
orate-3.004
 Agric-2.952
Token {
Token ID1391
Feature activation-4.10e+00

Pos logit contributions
anasia+0.061
 vas+0.054
 Bengals+0.052
 [*+0.050
cius+0.049
Neg logit contributions
ASC-0.140
eur-0.127
 Agric-0.126
 Ribbon-0.125
PLA-0.125
Token...
Token ID2644
Feature activation-9.98e-01

Pos logit contributions
anasia+2.698
 vas+2.548
 Bengals+2.464
 [*+2.430
cius+2.373
Neg logit contributions
ASC-3.338
eur-2.909
PLA-2.909
 Agric-2.868
orate-2.863
Token }
Token ID1782
Feature activation-1.48e-01

Pos logit contributions
anasia+0.631
 vas+0.580
 Bengals+0.561
 [*+0.552
cius+0.542
Neg logit contributions
ASC-0.851
eur-0.754
 Agric-0.752
 Ribbon-0.743
PLA-0.743
Token pub
Token ID2240
Feature activation-1.72e+00

Pos logit contributions
anasia+0.089
 vas+0.082
 Bengals+0.079
 [*+0.077
cius+0.076
Neg logit contributions
ASC-0.130
eur-0.116
 Agric-0.115
 Ribbon-0.114
PLA-0.114
Token fn
Token ID24714
Feature activation-6.07e+00

Pos logit contributions
anasia+0.851
 vas+0.771
 Bengals+0.735
 [*+0.718
cius+0.700
Neg logit contributions
ASC-1.696
eur-1.525
 Agric-1.517
PLA-1.512
 Ribbon-1.507
Token pin
Token ID6757
Feature activation-8.52e-01

Pos logit contributions
anasia+3.640
 vas+3.477
 Bengals+3.298
 [*+3.270
cius+3.150
Neg logit contributions
ASC-5.246
PLA-4.653
eur-4.622
 Agric-4.524
orate-4.519
Token ()
Token ID7499
Feature activation-1.35e+00

Pos logit contributions
anasia+0.475
 vas+0.431
 Bengals+0.415
 [*+0.407
cius+0.398
Neg logit contributions
ASC-0.791
eur-0.707
 Agric-0.705
 Ribbon-0.698
PLA-0.698
Token ->
Token ID4613
Feature activation-1.66e+00

Pos logit contributions
anasia+0.556
 vas+0.493
 Bengals+0.468
 [*+0.457
cius+0.438
Neg logit contributions
ASC-1.445
eur-1.314
 Agric-1.307
PLA-1.300
 Ribbon-1.297
Token Guard
Token ID4932
Feature activation+1.78e+00

Pos logit contributions
anasia+1.132
 vas+1.053
 Bengals+1.022
 [*+1.007
cius+0.988
Neg logit contributions
ASC-1.327
eur-1.163
 Agric-1.153
PLA-1.147
orate-1.141
Token ;
Token ID2162
Feature activation-9.97e-01

Pos logit contributions
ASC+1.818
eur+1.649
 Agric+1.643
 Ribbon+1.626
PLA+1.619
Neg logit contributions
anasia-0.821
 vas-0.728
 Bengals-0.694
cius-0.658
 [*-0.654
Token 172
Token ID23120
Feature activation-1.18e+00

Pos logit contributions
anasia+0.249
 vas+0.232
 Bengals+0.226
 [*+0.221
cius+0.216
Neg logit contributions
ASC-0.287
eur-0.251
 Agric-0.250
PLA-0.248
 Ribbon-0.246
Token games
Token ID1830
Feature activation-7.73e-01

Pos logit contributions
anasia+0.825
 vas+0.778
 Bengals+0.761
 [*+0.744
cius+0.723
Neg logit contributions
ASC-0.916
eur-0.804
 Agric-0.796
PLA-0.794
orate-0.792
Token and
Token ID290
Feature activation-4.84e-01

Pos logit contributions
anasia+0.510
 vas+0.474
 Bengals+0.462
 [*+0.454
cius+0.441
Neg logit contributions
ASC-0.637
eur-0.557
 Agric-0.556
PLA-0.552
orate-0.550
Token two
Token ID734
Feature activation-2.01e-01

Pos logit contributions
anasia+0.332
 vas+0.310
 Bengals+0.302
 [*+0.296
cius+0.289
Neg logit contributions
ASC-0.386
eur-0.337
 Agric-0.336
PLA-0.334
orate-0.332
Token Super
Token ID3115
Feature activation-1.74e+00

Pos logit contributions
anasia+0.143
 vas+0.134
 Bengals+0.130
 [*+0.127
cius+0.125
Neg logit contributions
ASC-0.155
eur-0.136
 Agric-0.135
PLA-0.134
orate-0.133
Token Bowl
Token ID8693
Feature activation-5.60e+00

Pos logit contributions
anasia+1.735
 vas+1.660
 Bengals+1.635
 [*+1.610
cius+1.593
Neg logit contributions
ASC-0.830
eur-0.665
 Agric-0.653
orate-0.647
PLA-0.645
Tokens
Token ID82
Feature activation-1.64e+00

Pos logit contributions
anasia+3.163
 vas+2.939
 Bengals+2.865
 [*+2.704
cius+2.617
Neg logit contributions
ASC-5.061
orate-4.502
 Agric-4.493
PLA-4.467
eur-4.384
Token in
Token ID287
Feature activation-9.41e-01

Pos logit contributions
anasia+1.074
 vas+1.001
 Bengals+0.977
 [*+0.964
cius+0.928
Neg logit contributions
ASC-1.363
 Agric-1.188
eur-1.187
PLA-1.181
orate-1.175
Token the
Token ID262
Feature activation-1.84e-01

Pos logit contributions
anasia+0.705
 vas+0.661
 Bengals+0.645
 [*+0.633
cius+0.620
Neg logit contributions
ASC-0.691
eur-0.597
 Agric-0.595
PLA-0.589
 Ribbon-0.585
Token NFL
Token ID5134
Feature activation-1.41e-01

Pos logit contributions
anasia+0.131
 vas+0.122
 Bengals+0.119
 [*+0.117
cius+0.114
Neg logit contributions
ASC-0.142
eur-0.123
 Agric-0.123
PLA-0.122
orate-0.121
Token:
Token ID25
Feature activation-1.00e+00

Pos logit contributions
anasia+0.094
 vas+0.088
 Bengals+0.085
 [*+0.084
cius+0.082
Neg logit contributions
ASC-0.115
eur-0.101
 Agric-0.101
PLA-0.099
 Ribbon-0.099
Tokenwrap
Token ID37150
Feature activation+2.51e+00

Pos logit contributions
ASC+2.163
eur+1.865
orate+1.838
 Agric+1.821
PLA+1.802
Neg logit contributions
anasia-2.428
 vas-2.277
 Bengals-2.210
 [*-2.166
cius-2.145
Token ())
Token ID32865
Feature activation-1.21e+00

Pos logit contributions
ASC+2.378
eur+2.135
 Agric+2.111
orate+2.102
 Ribbon+2.091
Neg logit contributions
anasia-1.330
 vas-1.215
 Bengals-1.157
 [*-1.123
cius-1.097
Token }
Token ID1782
Feature activation-3.93e-01

Pos logit contributions
anasia+0.696
 vas+0.636
 Bengals+0.612
 [*+0.602
cius+0.588
Neg logit contributions
ASC-1.103
eur-0.983
 Agric-0.980
PLA-0.972
 Ribbon-0.971
Token }
Token ID1782
Feature activation-4.82e-02

Pos logit contributions
anasia+0.212
 vas+0.192
 Bengals+0.185
 [*+0.181
cius+0.177
Neg logit contributions
ASC-0.372
eur-0.333
 Agric-0.332
PLA-0.329
 Ribbon-0.329
Token pub
Token ID2240
Feature activation-1.14e+00

Pos logit contributions
anasia+0.028
 vas+0.025
 Bengals+0.024
 [*+0.024
cius+0.024
Neg logit contributions
ASC-0.044
eur-0.039
 Agric-0.039
 Ribbon-0.039
PLA-0.038
Token fn
Token ID24714
Feature activation-4.98e+00

Pos logit contributions
anasia+0.680
 vas+0.623
 Bengals+0.600
 [*+0.590
cius+0.577
Neg logit contributions
ASC-1.017
eur-0.904
 Agric-0.901
PLA-0.893
 Ribbon-0.892
Token apply
Token ID4174
Feature activation-5.03e-01

Pos logit contributions
anasia+3.478
 vas+3.344
 Bengals+3.181
 [*+3.150
cius+3.015
Neg logit contributions
ASC-3.845
eur-3.324
PLA-3.323
 Agric-3.303
 Ribbon-3.256
Token_
Token ID62
Feature activation+2.24e+00

Pos logit contributions
anasia+0.360
 vas+0.335
 Bengals+0.325
 [*+0.321
cius+0.316
Neg logit contributions
ASC-0.386
eur-0.338
 Agric-0.336
PLA-0.332
 Ribbon-0.331
Tokenmove
Token ID21084
Feature activation+7.42e-01

Pos logit contributions
ASC+1.735
eur+1.550
orate+1.516
 Agric+1.499
PLA+1.494
Neg logit contributions
anasia-1.558
 vas-1.459
 Bengals-1.442
 [*-1.391
cius-1.366
Token (
Token ID357
Feature activation-5.30e-01

Pos logit contributions
ASC+0.644
eur+0.575
 Agric+0.570
orate+0.567
PLA+0.561
Neg logit contributions
anasia-0.452
 vas-0.412
 Bengals-0.405
cius-0.390
 [*-0.389
Token &
Token ID1222
Feature activation-2.18e+00

Pos logit contributions
anasia+0.328
 vas+0.300
 Bengals+0.290
 [*+0.285
cius+0.281
Neg logit contributions
ASC-0.459
eur-0.407
 Agric-0.406
 Ribbon-0.401
PLA-0.401
Token the
Token ID262
Feature activation-4.28e-01

Pos logit contributions
anasia+0.132
 vas+0.122
 Bengals+0.119
 [*+0.117
cius+0.115
Neg logit contributions
ASC-0.157
eur-0.138
 Agric-0.137
 Ribbon-0.136
PLA-0.136
Token space
Token ID2272
Feature activation-7.25e-01

Pos logit contributions
anasia+0.279
 vas+0.257
 Bengals+0.249
 [*+0.245
cius+0.241
Neg logit contributions
ASC-0.357
eur-0.315
 Agric-0.314
 Ribbon-0.310
PLA-0.310
Token let
Token ID1309
Feature activation-3.27e+00

Pos logit contributions
anasia+0.469
 vas+0.431
 Bengals+0.417
 [*+0.411
cius+0.404
Neg logit contributions
ASC-0.608
eur-0.538
 Agric-0.535
 Ribbon-0.530
PLA-0.529
Token ob
Token ID909
Feature activation-7.31e-01

Pos logit contributions
anasia+2.134
 vas+2.009
 Bengals+1.936
 [*+1.919
cius+1.853
Neg logit contributions
ASC-2.670
eur-2.357
 Agric-2.344
PLA-2.335
 Ribbon-2.324
Tokenb
Token ID65
Feature activation-8.42e-01

Pos logit contributions
anasia+0.553
 vas+0.516
 Bengals+0.502
 [*+0.495
cius+0.488
Neg logit contributions
ASC-0.532
eur-0.461
 Agric-0.459
 Ribbon-0.453
PLA-0.453
Token =
Token ID796
Feature activation-4.97e+00

Pos logit contributions
anasia+0.578
 vas+0.536
 Bengals+0.520
 [*+0.512
cius+0.503
Neg logit contributions
ASC-0.672
eur-0.590
 Agric-0.587
 Ribbon-0.581
PLA-0.580
Token fit
Token ID4197
Feature activation+3.80e-01

Pos logit contributions
anasia+3.124
 vas+3.045
 Bengals+2.928
 [*+2.919
cius+2.756
Neg logit contributions
ASC-4.030
eur-3.596
PLA-3.558
orate-3.516
 Agric-3.495
Token(
Token ID7
Feature activation-1.32e+00

Pos logit contributions
ASC+0.286
eur+0.248
 Agric+0.247
 Ribbon+0.244
PLA+0.244
Neg logit contributions
anasia-0.279
 vas-0.259
 Bengals-0.252
 [*-0.248
cius-0.245
Tokenspace
Token ID13200
Feature activation+1.55e-01

Pos logit contributions
anasia+0.828
 vas+0.764
 Bengals+0.738
 [*+0.727
cius+0.712
Neg logit contributions
ASC-1.122
eur-0.996
 Agric-0.992
 Ribbon-0.982
PLA-0.982
Token);
Token ID1776
Feature activation-4.59e-01

Pos logit contributions
ASC+0.116
eur+0.100
 Agric+0.100
PLA+0.099
 Ribbon+0.099
Neg logit contributions
anasia-0.115
 vas-0.107
 Bengals-0.104
 [*-0.102
cius-0.101
Token //
Token ID3373
Feature activation+2.31e+00

Pos logit contributions
anasia+0.267
 vas+0.243
 Bengals+0.234
 [*+0.230
cius+0.226
Neg logit contributions
ASC-0.414
eur-0.370
 Agric-0.369
 Ribbon-0.365
PLA-0.364
Token this
Token ID428
Feature activation-8.10e-01

Pos logit contributions
anasia+0.058
 vas+0.054
 Bengals+0.053
 [*+0.052
cius+0.051
Neg logit contributions
ASC-0.060
eur-0.052
 Agric-0.052
PLA-0.051
orate-0.051
Token public
Token ID1171
Feature activation+1.04e+00

Pos logit contributions
anasia+0.541
 vas+0.506
 Bengals+0.490
 [*+0.481
cius+0.468
Neg logit contributions
ASC-0.659
eur-0.579
 Agric-0.574
PLA-0.572
orate-0.570
Token sculpture
Token ID26924
Feature activation-2.34e-01

Pos logit contributions
ASC+0.831
eur+0.732
 Agric+0.727
 Ribbon+0.719
orate+0.718
Neg logit contributions
anasia-0.710
 vas-0.654
 Bengals-0.638
 [*-0.628
cius-0.621
Token by
Token ID416
Feature activation+3.73e-01

Pos logit contributions
anasia+0.162
 vas+0.150
 Bengals+0.145
 [*+0.143
cius+0.141
Neg logit contributions
ASC-0.186
eur-0.163
 Agric-0.162
 Ribbon-0.160
PLA-0.160
Token Eld
Token ID19208
Feature activation+7.79e-01

Pos logit contributions
ASC+0.301
eur+0.265
 Agric+0.264
PLA+0.261
 Ribbon+0.261
Neg logit contributions
anasia-0.253
 vas-0.234
 Bengals-0.227
 [*-0.223
cius-0.219
Tokenon
Token ID261
Feature activation-4.94e+00

Pos logit contributions
ASC+0.664
eur+0.596
 Agric+0.589
orate+0.584
 Ribbon+0.581
Neg logit contributions
anasia-0.485
 vas-0.450
 Bengals-0.436
 [*-0.428
cius-0.418
Token Garn
Token ID30937
Feature activation-1.37e+00

Pos logit contributions
anasia+3.424
 vas+3.184
 Bengals+3.129
 [*+3.061
cius+2.993
Neg logit contributions
ASC-3.818
PLA-3.347
eur-3.265
orate-3.240
 parity-3.239
Tokenet
Token ID316
Feature activation+5.57e-02

Pos logit contributions
anasia+0.821
 vas+0.752
 Bengals+0.725
 [*+0.713
cius+0.700
Neg logit contributions
ASC-1.207
eur-1.072
 Agric-1.068
PLA-1.059
 Ribbon-1.057
Token uses
Token ID3544
Feature activation+1.13e+00

Pos logit contributions
ASC+0.044
eur+0.039
 Agric+0.039
PLA+0.038
 Ribbon+0.038
Neg logit contributions
anasia-0.038
 vas-0.036
 Bengals-0.035
 [*-0.034
cius-0.033
Token just
Token ID655
Feature activation+8.12e-01

Pos logit contributions
ASC+0.886
eur+0.778
 Agric+0.775
 Ribbon+0.768
orate+0.764
Neg logit contributions
anasia-0.787
 vas-0.723
 Bengals-0.702
 [*-0.695
cius-0.684
Token a
Token ID257
Feature activation+5.68e-01

Pos logit contributions
ASC+0.666
eur+0.588
 Agric+0.585
 Ribbon+0.578
orate+0.578
Neg logit contributions
anasia-0.540
 vas-0.497
 Bengals-0.482
 [*-0.475
cius-0.468
Tokenstate
Token ID5219
Feature activation-1.32e+00

Pos logit contributions
anasia+0.061
 vas+0.057
 Bengals+0.056
 [*+0.055
cius+0.054
Neg logit contributions
ASC-0.042
eur-0.036
 Agric-0.035
PLA-0.035
orate-0.035
Token );
Token ID5619
Feature activation-1.37e+00

Pos logit contributions
anasia+0.737
 vas+0.670
 Bengals+0.644
 [*+0.630
cius+0.619
Neg logit contributions
ASC-1.227
eur-1.098
 Agric-1.093
 Ribbon-1.083
PLA-1.082
Token...
Token ID2644
Feature activation-8.89e-01

Pos logit contributions
anasia+0.736
 vas+0.672
 Bengals+0.644
 [*+0.633
cius+0.613
Neg logit contributions
ASC-1.305
eur-1.167
 Agric-1.159
PLA-1.155
 Ribbon-1.148
Token }
Token ID1782
Feature activation+7.72e-02

Pos logit contributions
anasia+0.481
 vas+0.437
 Bengals+0.420
 [*+0.412
cius+0.401
Neg logit contributions
ASC-0.838
eur-0.751
 Agric-0.747
PLA-0.742
 Ribbon-0.741
Token pub
Token ID2240
Feature activation-8.66e-01

Pos logit contributions
ASC+0.069
eur+0.061
 Agric+0.061
 Ribbon+0.060
PLA+0.060
Neg logit contributions
anasia-0.046
 vas-0.042
 Bengals-0.041
 [*-0.040
cius-0.039
Token fn
Token ID24714
Feature activation-4.84e+00

Pos logit contributions
anasia+0.524
 vas+0.479
 Bengals+0.464
 [*+0.455
cius+0.447
Neg logit contributions
ASC-0.761
eur-0.678
 Agric-0.676
 Ribbon-0.669
PLA-0.668
Token undo
Token ID23981
Feature activation+6.06e-02

Pos logit contributions
anasia+3.534
 vas+3.403
 Bengals+3.234
 [*+3.225
cius+3.086
Neg logit contributions
ASC-3.569
eur-3.085
PLA-3.077
 Agric-3.054
 Ribbon-3.023
Token_
Token ID62
Feature activation+1.98e+00

Pos logit contributions
ASC+0.046
eur+0.041
 Agric+0.040
PLA+0.040
 Ribbon+0.040
Neg logit contributions
anasia-0.043
 vas-0.040
 Bengals-0.039
 [*-0.039
cius-0.038
Tokenmove
Token ID21084
Feature activation+6.21e-01

Pos logit contributions
ASC+1.555
eur+1.380
orate+1.345
PLA+1.336
 Agric+1.325
Neg logit contributions
anasia-1.377
 vas-1.287
 Bengals-1.267
 [*-1.224
cius-1.215
Token (
Token ID357
Feature activation-6.85e-01

Pos logit contributions
ASC+0.556
eur+0.496
 Agric+0.490
orate+0.489
 Ribbon+0.485
Neg logit contributions
anasia-0.364
 vas-0.331
 Bengals-0.323
cius-0.314
 [*-0.312
Token &
Token ID1222
Feature activation-2.04e+00

Pos logit contributions
anasia+0.423
 vas+0.388
 Bengals+0.375
 [*+0.368
cius+0.362
Neg logit contributions
ASC-0.594
eur-0.527
 Agric-0.526
 Ribbon-0.520
PLA-0.520
Token active
Token ID4075
Feature activation-1.51e+00

Pos logit contributions
anasia+0.287
 vas+0.264
 Bengals+0.257
 [*+0.252
cius+0.249
Neg logit contributions
ASC-0.337
eur-0.297
 Agric-0.296
 Ribbon-0.292
PLA-0.291
Token:
Token ID25
Feature activation-1.25e-01

Pos logit contributions
anasia+1.028
 vas+0.953
 Bengals+0.924
 [*+0.912
cius+0.895
Neg logit contributions
ASC-1.212
eur-1.063
 Agric-1.059
PLA-1.047
 Ribbon-1.046
Token
Token ID198
Feature activation+3.30e-01

Pos logit contributions
anasia+0.076
 vas+0.069
 Bengals+0.067
 [*+0.066
cius+0.065
Neg logit contributions
ASC-0.110
eur-0.098
 Agric-0.098
 Ribbon-0.097
PLA-0.097
Token
Token ID198
Feature activation+2.03e-01

Pos logit contributions
ASC+0.293
eur+0.261
 Agric+0.259
PLA+0.256
 Ribbon+0.256
Neg logit contributions
anasia-0.199
 vas-0.182
 Bengals-0.175
 [*-0.172
cius-0.170
Tokenpub
Token ID12984
Feature activation-1.80e+00

Pos logit contributions
ASC+0.159
eur+0.139
 Agric+0.138
 Ribbon+0.137
PLA+0.137
Neg logit contributions
anasia-0.142
 vas-0.132
 Bengals-0.128
 [*-0.126
cius-0.124
Token struct
Token ID2878
Feature activation-4.79e+00

Pos logit contributions
anasia+0.911
 vas+0.826
 Bengals+0.789
 [*+0.772
cius+0.752
Neg logit contributions
ASC-1.760
eur-1.576
 Agric-1.570
PLA-1.566
 Ribbon-1.560
Token Guard
Token ID4932
Feature activation-1.35e-01

Pos logit contributions
anasia+3.503
 vas+3.323
 Bengals+3.242
 [*+3.204
cius+3.113
Neg logit contributions
ASC-3.554
PLA-3.055
eur-3.014
orate-3.004
 Agric-2.952
Token {
Token ID1391
Feature activation-4.10e+00

Pos logit contributions
anasia+0.061
 vas+0.054
 Bengals+0.052
 [*+0.050
cius+0.049
Neg logit contributions
ASC-0.140
eur-0.127
 Agric-0.126
 Ribbon-0.125
PLA-0.125
Token...
Token ID2644
Feature activation-9.98e-01

Pos logit contributions
anasia+2.698
 vas+2.548
 Bengals+2.464
 [*+2.430
cius+2.373
Neg logit contributions
ASC-3.338
eur-2.909
PLA-2.909
 Agric-2.868
orate-2.863
Token }
Token ID1782
Feature activation-1.48e-01

Pos logit contributions
anasia+0.631
 vas+0.580
 Bengals+0.561
 [*+0.552
cius+0.542
Neg logit contributions
ASC-0.851
eur-0.754
 Agric-0.752
 Ribbon-0.743
PLA-0.743
Token pub
Token ID2240
Feature activation-1.72e+00

Pos logit contributions
anasia+0.089
 vas+0.082
 Bengals+0.079
 [*+0.077
cius+0.076
Neg logit contributions
ASC-0.130
eur-0.116
 Agric-0.115
 Ribbon-0.114
PLA-0.114
Token.
Token ID13
Feature activation+1.61e+00

Pos logit contributions
ASC+1.309
 Agric+1.147
eur+1.144
 Ribbon+1.133
orate+1.126
Neg logit contributions
anasia-1.248
 vas-1.144
 Bengals-1.106
 [*-1.098
cius-1.087
Token Fine
Token ID17867
Feature activation+1.12e-01

Pos logit contributions
ASC+1.241
 Agric+1.094
 Ribbon+1.087
eur+1.082
PLA+1.072
Neg logit contributions
anasia-1.157
 vas-1.057
 Bengals-1.009
cius-1.005
 [*-1.005
Token cut
Token ID2005
Feature activation-1.88e-01

Pos logit contributions
ASC+0.097
eur+0.086
 Agric+0.085
PLA+0.085
 Ribbon+0.084
Neg logit contributions
anasia-0.070
 vas-0.065
 Bengals-0.063
 [*-0.061
cius-0.060
Token the
Token ID262
Feature activation-1.97e-01

Pos logit contributions
anasia+0.122
 vas+0.112
 Bengals+0.109
 [*+0.107
cius+0.105
Neg logit contributions
ASC-0.157
eur-0.138
 Agric-0.138
PLA-0.136
 Ribbon-0.136
Token 4
Token ID604
Feature activation+2.31e-01

Pos logit contributions
anasia+0.131
 vas+0.120
 Bengals+0.117
 [*+0.115
cius+0.113
Neg logit contributions
ASC-0.161
eur-0.142
 Agric-0.142
 Ribbon-0.140
PLA-0.140
Token garlic
Token ID17644
Feature activation-4.78e+00

Pos logit contributions
ASC+0.188
eur+0.166
 Agric+0.165
 Ribbon+0.164
orate+0.163
Neg logit contributions
anasia-0.156
 vas-0.143
 Bengals-0.138
 [*-0.137
cius-0.135
Token cloves
Token ID45025
Feature activation-4.05e+00

Pos logit contributions
anasia+1.895
 vas+1.742
 Bengals+1.652
 [*+1.543
cius+1.471
Neg logit contributions
ASC-5.118
eur-4.692
PLA-4.668
 Agric-4.616
 Ribbon-4.602
Token and
Token ID290
Feature activation-7.97e-01

Pos logit contributions
anasia+2.555
 vas+2.401
 Bengals+2.313
 [*+2.280
cius+2.213
Neg logit contributions
ASC-3.420
eur-3.035
PLA-3.001
 Agric-2.999
 Ribbon-2.957
Token the
Token ID262
Feature activation+1.07e-01

Pos logit contributions
anasia+0.505
 vas+0.460
 Bengals+0.446
 [*+0.439
cius+0.432
Neg logit contributions
ASC-0.680
eur-0.602
 Agric-0.601
 Ribbon-0.595
orate-0.594
Token ginger
Token ID25072
Feature activation-3.34e+00

Pos logit contributions
ASC+0.091
eur+0.081
 Agric+0.081
 Ribbon+0.080
orate+0.080
Neg logit contributions
anasia-0.068
 vas-0.062
 Bengals-0.060
 [*-0.059
cius-0.058
Token.
Token ID13
Feature activation+6.25e-02

Pos logit contributions
anasia+2.173
 vas+2.028
 Bengals+1.961
 [*+1.918
cius+1.875
Neg logit contributions
ASC-2.782
eur-2.452
PLA-2.427
 Agric-2.427
 Ribbon-2.404
Token of
Token ID286
Feature activation-1.57e-01

Pos logit contributions
ASC+0.519
eur+0.458
 Agric+0.457
 Ribbon+0.452
PLA+0.451
Neg logit contributions
anasia-0.402
 vas-0.370
 Bengals-0.358
 [*-0.352
cius-0.346
Token Sciences
Token ID13473
Feature activation-8.79e-01

Pos logit contributions
anasia+0.124
 vas+0.116
 Bengals+0.113
 [*+0.112
cius+0.111
Neg logit contributions
ASC-0.109
eur-0.094
 Agric-0.093
 Ribbon-0.092
PLA-0.092
Token.
Token ID13
Feature activation+1.56e-01

Pos logit contributions
anasia+0.593
 vas+0.548
 Bengals+0.532
 [*+0.523
cius+0.515
Neg logit contributions
ASC-0.712
eur-0.626
 Agric-0.624
 Ribbon-0.616
PLA-0.616
Token
Token ID198
Feature activation+3.13e-02

Pos logit contributions
ASC+0.136
eur+0.121
 Agric+0.121
 Ribbon+0.119
PLA+0.119
Neg logit contributions
anasia-0.096
 vas-0.088
 Bengals-0.085
cius-0.083
 [*-0.083
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
ASC+0.028
eur+0.025
 Agric+0.025
PLA+0.024
 Ribbon+0.024
Neg logit contributions
anasia-0.019
 vas-0.017
 Bengals-0.017
 [*-0.016
cius-0.016
TokenExplore
Token ID35433
Feature activation-4.69e+00

Pos logit contributions
anasia+0.176
 vas+0.164
 Bengals+0.159
 [*+0.156
cius+0.154
Neg logit contributions
ASC-0.192
eur-0.168
 Agric-0.166
PLA-0.165
orate-0.164
Token further
Token ID2252
Feature activation-1.56e+00

Pos logit contributions
anasia+1.790
 vas+1.573
 Bengals+1.490
 [*+1.460
cius+1.334
Neg logit contributions
ASC-5.079
 Agric-4.610
eur-4.608
orate-4.572
 Ribbon-4.566
Token:
Token ID25
Feature activation-7.00e-01

Pos logit contributions
anasia+1.114
 vas+1.033
 Bengals+1.003
 [*+0.988
cius+0.975
Neg logit contributions
ASC-1.211
eur-1.059
 Agric-1.053
 Ribbon-1.041
PLA-1.041
Token New
Token ID968
Feature activation-4.37e-01

Pos logit contributions
anasia+0.509
 vas+0.474
 Bengals+0.461
 [*+0.455
cius+0.447
Neg logit contributions
ASC-0.530
eur-0.462
 Agric-0.459
PLA-0.454
 Ribbon-0.453
Token Insight
Token ID39917
Feature activation-7.49e-01

Pos logit contributions
anasia+0.291
 vas+0.269
 Bengals+0.260
 [*+0.256
cius+0.252
Neg logit contributions
ASC-0.359
eur-0.316
 Agric-0.315
 Ribbon-0.311
PLA-0.311
Token Into
Token ID20008
Feature activation-1.46e+00

Pos logit contributions
anasia+0.527
 vas+0.489
 Bengals+0.475
 [*+0.468
cius+0.459
Neg logit contributions
ASC-0.586
eur-0.513
 Agric-0.510
PLA-0.504
 Ribbon-0.504
Token only
Token ID691
Feature activation+4.78e-01

Pos logit contributions
anasia+1.306
 vas+1.213
 Bengals+1.169
 [*+1.160
cius+1.125
Neg logit contributions
ASC-1.687
eur-1.478
 Agric-1.472
PLA-1.468
 Ribbon-1.460
Token within
Token ID1626
Feature activation-1.00e+00

Pos logit contributions
ASC+0.391
eur+0.345
 Agric+0.344
 Ribbon+0.340
PLA+0.339
Neg logit contributions
anasia-0.317
 vas-0.292
 Bengals-0.284
 [*-0.279
cius-0.275
Token the
Token ID262
Feature activation+4.13e-01

Pos logit contributions
anasia+0.725
 vas+0.677
 Bengals+0.655
 [*+0.648
cius+0.637
Neg logit contributions
ASC-0.765
eur-0.666
 Agric-0.662
PLA-0.656
 Ribbon-0.655
Token subject
Token ID2426
Feature activation+1.43e+00

Pos logit contributions
ASC+0.296
eur+0.257
 Agric+0.256
 Ribbon+0.252
PLA+0.252
Neg logit contributions
anasia-0.316
 vas-0.294
 Bengals-0.287
 [*-0.283
cius-0.279
Token areas
Token ID3006
Feature activation-6.01e-01

Pos logit contributions
ASC+1.122
eur+0.991
 Agric+0.982
orate+0.980
 parity+0.967
Neg logit contributions
anasia-1.005
 vas-0.921
 Bengals-0.903
 [*-0.884
cius-0.873
Token enumer
Token ID27056
Feature activation-4.66e+00

Pos logit contributions
anasia+0.403
 vas+0.373
 Bengals+0.362
 [*+0.356
cius+0.350
Neg logit contributions
ASC-0.489
eur-0.430
 Agric-0.429
PLA-0.424
 Ribbon-0.424
Tokenated
Token ID515
Feature activation-1.72e+00

Pos logit contributions
anasia+3.678
 vas+3.453
 Bengals+3.405
 [*+3.364
cius+3.312
Neg logit contributions
ASC-3.185
eur-2.705
 Agric-2.700
 Ribbon-2.691
PLA-2.680
Token under
Token ID739
Feature activation+3.04e-01

Pos logit contributions
anasia+1.085
 vas+1.002
 Bengals+0.967
 [*+0.956
cius+0.934
Neg logit contributions
ASC-1.461
eur-1.291
 Agric-1.287
PLA-1.275
 Ribbon-1.273
Token section
Token ID2665
Feature activation-3.11e+00

Pos logit contributions
ASC+0.233
eur+0.204
 Agric+0.203
 Ribbon+0.201
orate+0.200
Neg logit contributions
anasia-0.218
 vas-0.202
 Bengals-0.197
 [*-0.193
cius-0.190
Token 51
Token ID6885
Feature activation+4.20e-01

Pos logit contributions
anasia+2.080
 vas+1.957
 Bengals+1.896
 [*+1.866
cius+1.788
Neg logit contributions
ASC-2.513
eur-2.185
PLA-2.172
 Agric-2.164
orate-2.162
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
ASC+0.334
eur+0.293
 Agric+0.292
 Ribbon+0.288
PLA+0.288
Neg logit contributions
anasia-0.290
 vas-0.269
 Bengals-0.261
 [*-0.257
cius-0.252
Token (
Token ID357
Feature activation-2.33e+00

Pos logit contributions
ASC+0.544
eur+0.478
 Agric+0.474
 Ribbon+0.472
PLA+0.472
Neg logit contributions
anasia-0.423
 vas-0.390
 Bengals-0.376
 [*-0.369
cius-0.368
Token path
Token ID3108
Feature activation-5.74e-01

Pos logit contributions
anasia+1.454
 vas+1.341
 Bengals+1.295
 [*+1.280
cius+1.247
Neg logit contributions
ASC-1.987
eur-1.763
 Agric-1.758
 Ribbon-1.736
PLA-1.736
Token,
Token ID837
Feature activation-1.50e+00

Pos logit contributions
anasia+0.356
 vas+0.326
 Bengals+0.316
 [*+0.309
cius+0.305
Neg logit contributions
ASC-0.499
eur-0.442
 Agric-0.439
PLA-0.436
 Ribbon-0.435
Token 4
Token ID604
Feature activation+1.05e-01

Pos logit contributions
anasia+0.961
 vas+0.889
 Bengals+0.858
 [*+0.847
cius+0.827
Neg logit contributions
ASC-1.262
eur-1.116
 Agric-1.112
PLA-1.100
 Ribbon-1.099
Token )
Token ID1267
Feature activation-2.04e+00

Pos logit contributions
ASC+0.097
eur+0.086
 Agric+0.086
PLA+0.085
 Ribbon+0.085
Neg logit contributions
anasia-0.060
 vas-0.054
 Bengals-0.052
 [*-0.051
cius-0.051
Token =
Token ID796
Feature activation-4.57e+00

Pos logit contributions
anasia+1.300
 vas+1.205
 Bengals+1.170
 [*+1.154
cius+1.113
Neg logit contributions
ASC-1.702
eur-1.515
 Agric-1.513
orate-1.496
PLA-1.492
Token '.
Token ID45302
Feature activation-1.51e+00

Pos logit contributions
anasia+2.658
 vas+2.501
 [*+2.403
 Bengals+2.403
cius+2.260
Neg logit contributions
ASC-3.983
eur-3.569
 Agric-3.551
PLA-3.530
orate-3.527
Tokencl
Token ID565
Feature activation+2.73e+00

Pos logit contributions
anasia+1.213
 vas+1.139
 Bengals+1.109
 [*+1.100
cius+1.083
Neg logit contributions
ASC-1.020
 Agric-0.874
eur-0.871
 Ribbon-0.861
PLA-0.856
Tokenj
Token ID73
Feature activation+1.11e+00

Pos logit contributions
ASC+2.163
eur+1.926
orate+1.897
 Agric+1.883
 Ribbon+1.873
Neg logit contributions
anasia-1.844
 vas-1.710
 Bengals-1.669
 [*-1.630
cius-1.608
Token'
Token ID6
Feature activation+3.71e+00

Pos logit contributions
ASC+0.944
eur+0.838
 Agric+0.825
PLA+0.821
 Ribbon+0.818
Neg logit contributions
anasia-0.715
 vas-0.652
 Bengals-0.633
 [*-0.619
cius-0.617
Token OR
Token ID6375
Feature activation+7.56e-01

Pos logit contributions
ASC+3.022
eur+2.632
 Ribbon+2.622
 Agric+2.615
 parity+2.604
Neg logit contributions
anasia-2.519
 vas-2.287
cius-2.199
 Bengals-2.191
 [*-2.148
Token to
Token ID284
Feature activation-1.01e-01

Pos logit contributions
anasia+0.199
 vas+0.183
 Bengals+0.178
 [*+0.175
cius+0.173
Neg logit contributions
ASC-0.238
eur-0.209
 Agric-0.208
PLA-0.205
 Ribbon-0.205
Token images
Token ID4263
Feature activation-1.35e-01

Pos logit contributions
anasia+0.063
 vas+0.058
 Bengals+0.056
 [*+0.055
cius+0.054
Neg logit contributions
ASC-0.087
eur-0.077
 Agric-0.077
PLA-0.076
 Ribbon-0.076
Token directory
Token ID8619
Feature activation-5.87e-01

Pos logit contributions
anasia+0.093
 vas+0.086
 Bengals+0.083
 [*+0.082
cius+0.081
Neg logit contributions
ASC-0.108
eur-0.095
 Agric-0.094
 Ribbon-0.093
PLA-0.093
Token")
Token ID4943
Feature activation+1.36e-01

Pos logit contributions
anasia+0.401
 vas+0.370
 Bengals+0.359
 [*+0.354
cius+0.348
Neg logit contributions
ASC-0.471
eur-0.413
 Agric-0.411
 Ribbon-0.407
PLA-0.406
Token args
Token ID26498
Feature activation-1.04e+00

Pos logit contributions
ASC+0.111
eur+0.098
 Agric+0.097
 Ribbon+0.096
PLA+0.096
Neg logit contributions
anasia-0.091
 vas-0.084
 Bengals-0.081
 [*-0.080
cius-0.079
Token =
Token ID796
Feature activation-4.55e+00

Pos logit contributions
anasia+0.648
 vas+0.595
 Bengals+0.576
 [*+0.567
cius+0.556
Neg logit contributions
ASC-0.901
eur-0.799
 Agric-0.797
 Ribbon-0.789
PLA-0.788
Token v
Token ID410
Feature activation+1.01e-01

Pos logit contributions
anasia+2.814
 vas+2.686
 [*+2.589
 Bengals+2.560
cius+2.427
Neg logit contributions
ASC-3.845
eur-3.422
 Agric-3.396
orate-3.378
PLA-3.367
Tokenars
Token ID945
Feature activation-7.91e-01

Pos logit contributions
ASC+0.073
eur+0.063
 Agric+0.063
PLA+0.062
 Ribbon+0.062
Neg logit contributions
anasia-0.077
 vas-0.072
 Bengals-0.070
 [*-0.069
cius-0.068
Token(
Token ID7
Feature activation-2.42e+00

Pos logit contributions
anasia+0.574
 vas+0.534
 Bengals+0.519
 [*+0.513
cius+0.504
Neg logit contributions
ASC-0.600
eur-0.522
 Agric-0.520
 Ribbon-0.514
PLA-0.514
Tokenap
Token ID499
Feature activation+9.26e-01

Pos logit contributions
anasia+1.824
 vas+1.702
 Bengals+1.652
 [*+1.639
cius+1.606
Neg logit contributions
ASC-1.748
 Agric-1.527
eur-1.521
 Ribbon-1.511
orate-1.498
Token.
Token ID13
Feature activation-8.67e-01

Pos logit contributions
ASC+0.713
eur+0.619
 Agric+0.614
PLA+0.612
orate+0.609
Neg logit contributions
anasia-0.663
 vas-0.616
 Bengals-0.598
 [*-0.586
cius-0.578
Tokenulse
Token ID9615
Feature activation-1.13e+00

Pos logit contributions
anasia+0.013
 vas+0.011
 Bengals+0.011
 [*+0.011
cius+0.010
Neg logit contributions
ASC-0.032
eur-0.029
 Agric-0.029
PLA-0.028
 Ribbon-0.028
Token period
Token ID2278
Feature activation-1.03e+00

Pos logit contributions
anasia+0.802
 vas+0.744
 Bengals+0.723
 [*+0.712
cius+0.702
Neg logit contributions
ASC-0.877
eur-0.768
 Agric-0.763
 Ribbon-0.755
PLA-0.754
Token",
Token ID1600
Feature activation-7.04e-01

Pos logit contributions
anasia+0.668
 vas+0.614
 Bengals+0.596
 [*+0.585
cius+0.577
Neg logit contributions
ASC-0.857
eur-0.763
 Agric-0.754
 Ribbon-0.747
orate-0.747
Token Float
Token ID48436
Feature activation-1.24e+00

Pos logit contributions
anasia+0.508
 vas+0.472
 Bengals+0.459
 [*+0.452
cius+0.445
Neg logit contributions
ASC-0.537
eur-0.468
 Agric-0.466
 Ribbon-0.461
PLA-0.460
Token)
Token ID8
Feature activation-1.10e+00

Pos logit contributions
anasia+0.948
 vas+0.888
 Bengals+0.865
 [*+0.854
cius+0.840
Neg logit contributions
ASC-0.888
eur-0.768
 Agric-0.766
PLA-0.755
 Ribbon-0.754
Token =
Token ID796
Feature activation-4.53e+00

Pos logit contributions
anasia+0.688
 vas+0.629
 Bengals+0.610
 [*+0.596
cius+0.591
Neg logit contributions
ASC-0.941
eur-0.835
 Agric-0.830
 Ribbon-0.822
PLA-0.821
Token 1
Token ID352
Feature activation+5.89e-01

Pos logit contributions
anasia+2.735
 vas+2.617
 [*+2.485
 Bengals+2.477
cius+2.397
Neg logit contributions
ASC-3.870
eur-3.442
 Agric-3.393
PLA-3.383
orate-3.374
Token //
Token ID3373
Feature activation+1.47e+00

Pos logit contributions
ASC+0.485
eur+0.429
 Agric+0.427
 Ribbon+0.423
PLA+0.422
Neg logit contributions
anasia-0.390
 vas-0.356
 Bengals-0.346
 [*-0.339
cius-0.337
Token seconds
Token ID4201
Feature activation-1.86e+00

Pos logit contributions
ASC+1.316
eur+1.170
 Agric+1.167
PLA+1.155
 Ribbon+1.153
Neg logit contributions
anasia-0.867
 vas-0.780
 Bengals-0.757
 [*-0.740
cius-0.729
Token 1
Token ID352
Feature activation-6.94e-01

Pos logit contributions
anasia+1.169
 vas+1.084
 Bengals+1.045
 [*+1.031
cius+1.006
Neg logit contributions
ASC-1.586
eur-1.403
 Agric-1.394
PLA-1.382
 Ribbon-1.378
Token 2
Token ID362
Feature activation-2.13e+00

Pos logit contributions
anasia+0.473
 vas+0.436
 Bengals+0.422
 [*+0.415
cius+0.411
Neg logit contributions
ASC-0.559
eur-0.493
 Agric-0.490
 Ribbon-0.484
PLA-0.484
Token |
Token ID930
Feature activation-6.60e-01

Pos logit contributions
ASC+0.506
eur+0.444
 Agric+0.442
PLA+0.437
 Ribbon+0.436
Neg logit contributions
anasia-0.445
 vas-0.412
 Bengals-0.399
 [*-0.393
cius-0.388
Token 2
Token ID362
Feature activation-1.50e+00

Pos logit contributions
anasia+0.448
 vas+0.415
 Bengals+0.403
 [*+0.397
cius+0.389
Neg logit contributions
ASC-0.531
eur-0.466
 Agric-0.464
PLA-0.461
orate-0.459
Token |
Token ID930
Feature activation-9.35e-01

Pos logit contributions
anasia+0.980
 vas+0.904
 Bengals+0.878
 [*+0.864
cius+0.844
Neg logit contributions
ASC-1.249
eur-1.102
 Agric-1.097
 Ribbon-1.086
PLA-1.086
Token struct
Token ID2878
Feature activation-3.74e+00

Pos logit contributions
anasia+0.618
 vas+0.572
 Bengals+0.555
 [*+0.547
cius+0.534
Neg logit contributions
ASC-0.769
eur-0.678
 Agric-0.673
PLA-0.668
 Ribbon-0.667
Token Board
Token ID5926
Feature activation-2.25e+00

Pos logit contributions
anasia+2.476
 vas+2.308
 Bengals+2.249
 [*+2.214
cius+2.118
Neg logit contributions
ASC-3.058
eur-2.654
PLA-2.651
orate-2.639
 Agric-2.600
Token {
Token ID1391
Feature activation-4.51e+00

Pos logit contributions
anasia+0.988
 vas+0.873
 Bengals+0.831
 [*+0.813
cius+0.783
Neg logit contributions
ASC-2.349
eur-2.130
 Agric-2.123
PLA-2.106
 Ribbon-2.106
Token |
Token ID930
Feature activation-1.65e+00

Pos logit contributions
anasia+2.816
 vas+2.628
 Bengals+2.534
 [*+2.487
cius+2.421
Neg logit contributions
ASC-3.824
eur-3.382
PLA-3.346
 Ribbon-3.318
 Agric-3.316
Token ^
Token ID10563
Feature activation-9.03e-01

Pos logit contributions
anasia+1.104
 vas+1.023
 Bengals+0.991
 [*+0.976
cius+0.955
Neg logit contributions
ASC-1.350
eur-1.188
 Agric-1.180
PLA-1.171
 Ribbon-1.169
Token^^^^
Token ID39397
Feature activation+7.88e-01

Pos logit contributions
anasia+0.611
 vas+0.566
 Bengals+0.549
 [*+0.541
cius+0.530
Neg logit contributions
ASC-0.729
eur-0.641
 Agric-0.638
PLA-0.631
 Ribbon-0.631
Token^^^^
Token ID39397
Feature activation+3.49e-04

Pos logit contributions
ASC+0.561
eur+0.484
 Agric+0.483
PLA+0.476
 Ribbon+0.475
Neg logit contributions
anasia-0.609
 vas-0.569
 Bengals-0.552
 [*-0.544
cius-0.541
Token^^
Token ID18237
Feature activation+4.07e-01

Pos logit contributions
ASC+0.000
eur+0.000
 Agric+0.000
PLA+0.000
 Ribbon+0.000
Neg logit contributions
anasia-0.000
 vas-0.000
 Bengals-0.000
 [*-0.000
cius-0.000
Token out
Token ID503
Feature activation-1.48e+00

Pos logit contributions
anasia+0.132
 vas+0.120
 Bengals+0.116
 [*+0.114
cius+0.112
Neg logit contributions
ASC-0.194
eur-0.173
 Agric-0.172
 Ribbon-0.170
PLA-0.170
Token at
Token ID379
Feature activation-8.03e-01

Pos logit contributions
anasia+0.962
 vas+0.887
 Bengals+0.858
 [*+0.845
cius+0.830
Neg logit contributions
ASC-1.236
eur-1.092
 Agric-1.087
 Ribbon-1.075
PLA-1.075
Token http
Token ID2638
Feature activation-1.38e+00

Pos logit contributions
anasia+0.531
 vas+0.490
 Bengals+0.474
 [*+0.467
cius+0.459
Neg logit contributions
ASC-0.662
eur-0.584
 Agric-0.582
 Ribbon-0.575
PLA-0.575
Token://
Token ID1378
Feature activation-2.09e+00

Pos logit contributions
anasia+0.846
 vas+0.780
 Bengals+0.754
 [*+0.749
cius+0.722
Neg logit contributions
ASC-1.197
 Agric-1.063
eur-1.060
 Ribbon-1.055
orate-1.050
Tokenw
Token ID86
Feature activation-2.46e+00

Pos logit contributions
anasia+1.522
 vas+1.413
 Bengals+1.371
 [*+1.352
cius+1.337
Neg logit contributions
ASC-1.586
 Agric-1.377
eur-1.368
 Ribbon-1.363
PLA-1.355
Tokenashington
Token ID2542
Feature activation-4.50e+00

Pos logit contributions
anasia+2.027
 vas+1.892
 Bengals+1.849
 [*+1.820
cius+1.803
Neg logit contributions
ASC-1.624
 Agric-1.379
eur-1.377
 Ribbon-1.371
PLA-1.360
Tokenbeer
Token ID42428
Feature activation-4.76e-01

Pos logit contributions
anasia+2.372
 vas+2.118
 Bengals+2.040
cius+2.010
 [*+1.968
Neg logit contributions
ASC-4.274
 Agric-3.830
 Ribbon-3.823
 parity-3.806
 Dynam-3.786
Token.
Token ID13
Feature activation+3.69e-01

Pos logit contributions
anasia+0.340
 vas+0.317
 Bengals+0.307
 [*+0.303
cius+0.297
Neg logit contributions
ASC-0.366
eur-0.321
 Agric-0.318
PLA-0.315
 Ribbon-0.314
Tokencom
Token ID785
Feature activation-1.25e+00

Pos logit contributions
ASC+0.262
eur+0.227
 Agric+0.225
PLA+0.222
orate+0.222
Neg logit contributions
anasia-0.285
 vas-0.267
 Bengals-0.260
 [*-0.256
cius-0.252
Token/
Token ID14
Feature activation+5.09e-01

Pos logit contributions
anasia+0.816
 vas+0.754
 Bengals+0.731
 [*+0.720
cius+0.705
Neg logit contributions
ASC-1.037
eur-0.914
 Agric-0.910
PLA-0.900
 Ribbon-0.899
Tokenw
Token ID86
Feature activation+1.96e-01

Pos logit contributions
ASC+0.406
eur+0.359
 Agric+0.356
 Ribbon+0.352
PLA+0.352
Neg logit contributions
anasia-0.350
 vas-0.324
 Bengals-0.314
 [*-0.309
cius-0.304
Token component
Token ID7515
Feature activation-1.23e+00

Pos logit contributions
ASC+0.538
eur+0.474
 Agric+0.473
 Ribbon+0.467
PLA+0.466
Neg logit contributions
anasia-0.437
 vas-0.399
 Bengals-0.389
 [*-0.380
cius-0.377
Token const
Token ID1500
Feature activation-2.99e+00

Pos logit contributions
anasia+0.790
 vas+0.730
 Bengals+0.705
 [*+0.695
cius+0.681
Neg logit contributions
ASC-1.029
eur-0.909
 Agric-0.905
PLA-0.896
 Ribbon-0.895
Token float
Token ID12178
Feature activation-4.22e+00

Pos logit contributions
anasia+1.751
 vas+1.637
 Bengals+1.566
 [*+1.541
cius+1.504
Neg logit contributions
ASC-2.663
eur-2.356
 Agric-2.352
PLA-2.338
 Ribbon-2.327
Token TA
Token ID21664
Feature activation+8.98e-01

Pos logit contributions
anasia+2.712
 vas+2.594
 Bengals+2.489
 [*+2.469
cius+2.385
Neg logit contributions
ASC-3.442
eur-3.028
 Agric-3.018
PLA-2.992
orate-2.982
TokenU
Token ID52
Feature activation-8.47e-01

Pos logit contributions
ASC+0.710
eur+0.624
 Agric+0.616
PLA+0.613
 Ribbon+0.610
Neg logit contributions
anasia-0.623
 vas-0.575
 Bengals-0.559
 [*-0.550
cius-0.543
Token =
Token ID796
Feature activation-4.46e+00

Pos logit contributions
anasia+0.561
 vas+0.519
 Bengals+0.503
 [*+0.495
cius+0.486
Neg logit contributions
ASC-0.696
eur-0.613
 Agric-0.611
 Ribbon-0.604
PLA-0.603
Token 6
Token ID718
Feature activation-6.03e-01

Pos logit contributions
anasia+2.771
 vas+2.663
 Bengals+2.533
 [*+2.490
cius+2.435
Neg logit contributions
ASC-3.750
eur-3.324
PLA-3.286
 Agric-3.254
orate-3.249
Token.
Token ID13
Feature activation-6.48e-01

Pos logit contributions
anasia+0.415
 vas+0.384
 Bengals+0.373
 [*+0.367
cius+0.361
Neg logit contributions
ASC-0.481
eur-0.422
 Agric-0.420
 Ribbon-0.415
PLA-0.415
Token283
Token ID30290
Feature activation+3.00e-02

Pos logit contributions
anasia+0.601
 vas+0.569
 Bengals+0.556
 [*+0.552
cius+0.543
Neg logit contributions
ASC-0.357
eur-0.295
 Agric-0.295
PLA-0.289
 Ribbon-0.289
Token185
Token ID21652
Feature activation+4.73e-01

Pos logit contributions
ASC+0.027
eur+0.025
 Agric+0.024
PLA+0.024
 Ribbon+0.024
Neg logit contributions
anasia-0.017
 vas-0.016
 Bengals-0.015
 [*-0.015
cius-0.015
Token307
Token ID22996
Feature activation+7.81e-01

Pos logit contributions
ASC+0.373
eur+0.327
 Agric+0.325
PLA+0.321
 Ribbon+0.321
Neg logit contributions
anasia-0.330
 vas-0.306
 Bengals-0.296
 [*-0.292
cius-0.288
Token had
Token ID550
Feature activation-1.25e+00

Pos logit contributions
ASC+0.688
eur+0.613
 Agric+0.604
orate+0.598
 parity+0.598
Neg logit contributions
anasia-0.597
 vas-0.547
 Bengals-0.534
cius-0.523
 [*-0.522
Token come
Token ID1282
Feature activation+1.35e+00

Pos logit contributions
anasia+0.821
 vas+0.760
 Bengals+0.736
 [*+0.725
cius+0.708
Neg logit contributions
ASC-1.034
eur-0.910
 Agric-0.907
PLA-0.899
 Ribbon-0.897
Token on
Token ID319
Feature activation+9.92e-01

Pos logit contributions
ASC+1.060
eur+0.934
 Agric+0.930
orate+0.920
 parity+0.919
Neg logit contributions
anasia-0.942
 vas-0.865
 Bengals-0.841
cius-0.826
 [*-0.826
Token a
Token ID257
Feature activation+1.62e+00

Pos logit contributions
ASC+0.766
eur+0.671
 Agric+0.668
orate+0.660
 Ribbon+0.659
Neg logit contributions
anasia-0.707
 vas-0.651
 Bengals-0.634
 [*-0.624
cius-0.617
Token P
Token ID350
Feature activation+5.00e-02

Pos logit contributions
ASC+1.320
eur+1.166
 Agric+1.159
 Ribbon+1.153
orate+1.152
Neg logit contributions
anasia-1.078
 vas-0.977
 Bengals-0.954
 [*-0.939
cius-0.930
TokenIL
Token ID4146
Feature activation+2.56e+00

Pos logit contributions
ASC+0.033
eur+0.028
 Agric+0.027
orate+0.027
PLA+0.027
Neg logit contributions
anasia-0.042
 vas-0.039
 Bengals-0.038
 [*-0.038
cius-0.037
Token by
Token ID416
Feature activation+3.52e-01

Pos logit contributions
ASC+1.970
eur+1.734
 Agric+1.719
PLA+1.702
 Ribbon+1.700
Neg logit contributions
anasia-1.822
 vas-1.670
 Bengals-1.620
 [*-1.595
cius-1.590
Token Raj
Token ID13308
Feature activation+3.65e-02

Pos logit contributions
ASC+0.274
eur+0.240
 Agric+0.239
 Ribbon+0.236
PLA+0.236
Neg logit contributions
anasia-0.248
 vas-0.230
 Bengals-0.223
 [*-0.220
cius-0.216
Tokenendra
Token ID48286
Feature activation+8.83e-01

Pos logit contributions
ASC+0.027
eur+0.024
 Agric+0.024
 Ribbon+0.024
orate+0.024
Neg logit contributions
anasia-0.027
 vas-0.025
 Bengals-0.024
 [*-0.024
cius-0.023
Token S
Token ID311
Feature activation-6.90e-02

Pos logit contributions
ASC+0.746
 Agric+0.663
eur+0.662
 Ribbon+0.655
PLA+0.649
Neg logit contributions
anasia-0.563
 vas-0.514
 Bengals-0.497
 [*-0.492
cius-0.485
Tokenont
Token ID756
Feature activation+3.22e-01

Pos logit contributions
anasia+0.051
 vas+0.047
 Bengals+0.046
 [*+0.045
cius+0.045
Neg logit contributions
ASC-0.052
eur-0.045
 Agric-0.045
PLA-0.044
 Ribbon-0.044
Token Han
Token ID9530
Feature activation-3.56e-01

Pos logit contributions
ASC+0.067
eur+0.059
 Agric+0.059
PLA+0.058
 Ribbon+0.058
Neg logit contributions
anasia-0.055
 vas-0.051
 Bengals-0.050
 [*-0.049
cius-0.048
Token Solo
Token ID20284
Feature activation-5.54e-02

Pos logit contributions
anasia+0.285
 vas+0.267
 Bengals+0.260
 [*+0.257
cius+0.253
Neg logit contributions
ASC-0.243
eur-0.209
 Agric-0.208
 Ribbon-0.205
PLA-0.205
Token in
Token ID287
Feature activation-9.60e-02

Pos logit contributions
anasia+0.037
 vas+0.034
 Bengals+0.033
 [*+0.032
cius+0.032
Neg logit contributions
ASC-0.045
eur-0.040
 Agric-0.040
 Ribbon-0.039
PLA-0.039
Token his
Token ID465
Feature activation+2.80e-01

Pos logit contributions
anasia+0.069
 vas+0.064
 Bengals+0.063
 [*+0.062
cius+0.061
Neg logit contributions
ASC-0.073
eur-0.064
 Agric-0.063
PLA-0.063
orate-0.063
Token classic
Token ID6833
Feature activation+2.47e+00

Pos logit contributions
ASC+0.228
eur+0.201
 Agric+0.200
 Ribbon+0.198
PLA+0.197
Neg logit contributions
anasia-0.188
 vas-0.173
 Bengals-0.168
 [*-0.166
cius-0.163
Token delivery
Token ID7585
Feature activation+2.60e+00

Pos logit contributions
ASC+2.028
 Agric+1.797
eur+1.794
 Ribbon+1.785
PLA+1.763
Neg logit contributions
anasia-1.627
 vas-1.484
 Bengals-1.437
 [*-1.423
cius-1.416
Token stride
Token ID33769
Feature activation+9.84e-01

Pos logit contributions
ASC+2.062
eur+1.854
 Agric+1.818
 Ribbon+1.811
orate+1.797
Neg logit contributions
anasia-1.772
 vas-1.600
 Bengals-1.568
cius-1.550
 [*-1.539
Token.
Token ID13
Feature activation+1.00e-02

Pos logit contributions
ASC+0.791
eur+0.700
 Agric+0.693
 Ribbon+0.686
PLA+0.685
Neg logit contributions
anasia-0.666
 vas-0.615
 Bengals-0.597
 [*-0.586
cius-0.583
Token Cricket
Token ID34761
Feature activation+5.76e-02

Pos logit contributions
ASC+0.008
eur+0.007
 Agric+0.007
 Ribbon+0.007
PLA+0.007
Neg logit contributions
anasia-0.007
 vas-0.006
 Bengals-0.006
 [*-0.006
cius-0.006
Token nerd
Token ID34712
Feature activation+3.09e-01

Pos logit contributions
ASC+0.047
eur+0.042
 Agric+0.042
 Ribbon+0.041
PLA+0.041
Neg logit contributions
anasia-0.038
 vas-0.035
 Bengals-0.034
 [*-0.034
cius-0.033
Tokenos
Token ID418
Feature activation+1.24e-01

Pos logit contributions
ASC+0.259
eur+0.229
 Agric+0.228
 Ribbon+0.226
PLA+0.225
Neg logit contributions
anasia-0.200
 vas-0.184
 Bengals-0.178
 [*-0.176
cius-0.173
Token just
Token ID655
Feature activation-2.95e-01

Pos logit contributions
anasia+0.244
 vas+0.223
 Bengals+0.215
 [*+0.211
cius+0.206
Neg logit contributions
ASC-0.385
eur-0.344
 Agric-0.342
PLA-0.339
 Ribbon-0.339
Token make
Token ID787
Feature activation-2.97e-01

Pos logit contributions
anasia+0.172
 vas+0.157
 Bengals+0.151
 [*+0.149
cius+0.145
Neg logit contributions
ASC-0.267
eur-0.238
 Agric-0.237
 Ribbon-0.235
PLA-0.235
Token K
Token ID509
Feature activation+3.95e-01

Pos logit contributions
anasia+0.217
 vas+0.202
 Bengals+0.196
 [*+0.194
cius+0.190
Neg logit contributions
ASC-0.224
eur-0.194
 Agric-0.193
PLA-0.191
 Ribbon-0.191
Tokenessel
Token ID7878
Feature activation+9.18e-01

Pos logit contributions
ASC+0.225
eur+0.187
 Agric+0.184
PLA+0.182
orate+0.181
Neg logit contributions
anasia-0.362
 vas-0.342
 Bengals-0.335
 [*-0.331
cius-0.327
Token go
Token ID467
Feature activation+1.05e+00

Pos logit contributions
ASC+0.774
eur+0.687
 Agric+0.683
 Ribbon+0.676
PLA+0.674
Neg logit contributions
anasia-0.588
 vas-0.539
 Bengals-0.521
 [*-0.514
cius-0.508
Token away
Token ID1497
Feature activation+2.79e+00

Pos logit contributions
ASC+0.832
eur+0.735
 Agric+0.731
 Ribbon+0.724
orate+0.718
Neg logit contributions
anasia-0.720
 vas-0.663
 Bengals-0.644
 [*-0.635
cius-0.630
Token.
Token ID13
Feature activation+1.17e+00

Pos logit contributions
ASC+2.116
eur+1.864
 Agric+1.850
 Ribbon+1.828
 parity+1.810
Neg logit contributions
anasia-2.007
 vas-1.850
 Bengals-1.801
cius-1.780
 [*-1.762
Token You
Token ID921
Feature activation+1.04e+00

Pos logit contributions
ASC+0.924
 Agric+0.811
eur+0.811
 Ribbon+0.802
PLA+0.796
Neg logit contributions
anasia-0.821
 vas-0.760
 Bengals-0.726
cius-0.720
 [*-0.719
Token even
Token ID772
Feature activation+1.17e+00

Pos logit contributions
ASC+0.856
eur+0.756
 Agric+0.751
PLA+0.743
 Ribbon+0.743
Neg logit contributions
anasia-0.690
 vas-0.635
 Bengals-0.615
 [*-0.605
cius-0.596
Token went
Token ID1816
Feature activation+1.26e+00

Pos logit contributions
ASC+0.929
eur+0.820
 Agric+0.814
 Ribbon+0.805
PLA+0.803
Neg logit contributions
anasia-0.801
 vas-0.735
 Bengals-0.714
 [*-0.702
cius-0.696
Token as
Token ID355
Feature activation+1.82e+00

Pos logit contributions
ASC+1.124
eur+1.004
 Agric+0.997
 Ribbon+0.994
PLA+0.992
Neg logit contributions
anasia-0.755
 vas-0.679
 Bengals-0.648
cius-0.647
 [*-0.641
Token meet
Token ID1826
Feature activation+2.74e-01

Pos logit contributions
anasia+0.258
 vas+0.237
 Bengals+0.229
 [*+0.226
cius+0.222
Neg logit contributions
ASC-0.347
eur-0.308
 Agric-0.307
 Ribbon-0.304
PLA-0.303
Token government
Token ID1230
Feature activation+1.46e+00

Pos logit contributions
ASC+0.210
eur+0.183
 Agric+0.183
 Ribbon+0.180
PLA+0.180
Neg logit contributions
anasia-0.198
 vas-0.182
 Bengals-0.178
 [*-0.175
cius-0.172
Token commitments
Token ID19405
Feature activation+1.99e+00

Pos logit contributions
ASC+1.151
eur+1.012
 parity+1.006
 Agric+1.006
orate+0.998
Neg logit contributions
anasia-1.007
 vas-0.913
 Bengals-0.904
 [*-0.878
cius-0.876
Token without
Token ID1231
Feature activation+2.74e-01

Pos logit contributions
ASC+1.571
eur+1.386
 Agric+1.373
 Ribbon+1.359
PLA+1.358
Neg logit contributions
anasia-1.377
 vas-1.264
 Bengals-1.226
 [*-1.203
cius-1.187
Token added
Token ID2087
Feature activation+3.98e-01

Pos logit contributions
ASC+0.217
eur+0.191
 Agric+0.190
 Ribbon+0.188
PLA+0.187
Neg logit contributions
anasia-0.190
 vas-0.175
 Bengals-0.170
 [*-0.168
cius-0.166
Token borrowing
Token ID23669
Feature activation+2.97e+00

Pos logit contributions
ASC+0.330
eur+0.292
 Agric+0.292
 Ribbon+0.288
PLA+0.287
Neg logit contributions
anasia-0.259
 vas-0.237
 Bengals-0.231
 [*-0.227
cius-0.225
Token,
Token ID11
Feature activation+3.32e-01

Pos logit contributions
ASC+2.304
eur+2.034
 Agric+2.026
 parity+2.020
orate+1.999
Neg logit contributions
anasia-2.093
 vas-1.898
 Bengals-1.846
cius-1.828
 [*-1.809
Token those
Token ID883
Feature activation-7.49e-02

Pos logit contributions
ASC+0.260
eur+0.227
 Agric+0.226
PLA+0.224
 Ribbon+0.223
Neg logit contributions
anasia-0.234
 vas-0.216
 Bengals-0.210
 [*-0.207
cius-0.204
Token "
Token ID366
Feature activation-2.32e-01

Pos logit contributions
anasia+0.050
 vas+0.045
 Bengals+0.044
 [*+0.043
cius+0.043
Neg logit contributions
ASC-0.062
eur-0.055
 Agric-0.054
 Ribbon-0.054
orate-0.054
Tokenextra
Token ID26086
Feature activation+2.54e-01

Pos logit contributions
anasia+0.175
 vas+0.164
 Bengals+0.159
 [*+0.157
cius+0.155
Neg logit contributions
ASC-0.170
eur-0.147
 Agric-0.146
PLA-0.145
 Ribbon-0.144
Tokenordinary
Token ID35947
Feature activation-5.85e-01

Pos logit contributions
ASC+0.181
eur+0.156
 Agric+0.156
PLA+0.155
orate+0.154
Neg logit contributions
anasia-0.196
 vas-0.182
 Bengals-0.178
 [*-0.175
cius-0.174
Token than
Token ID621
Feature activation-4.72e-01

Pos logit contributions
ASC+0.573
eur+0.511
 Agric+0.509
 parity+0.503
 Ribbon+0.502
Neg logit contributions
anasia-0.412
 vas-0.374
 Bengals-0.362
 [*-0.356
cius-0.351
Token 60
Token ID3126
Feature activation+1.30e-01

Pos logit contributions
anasia+0.292
 vas+0.267
 Bengals+0.258
 [*+0.253
cius+0.250
Neg logit contributions
ASC-0.409
eur-0.364
 Agric-0.363
 Ribbon-0.358
PLA-0.357
Token percent
Token ID1411
Feature activation+8.56e-01

Pos logit contributions
ASC+0.094
eur+0.081
 Agric+0.081
 Ribbon+0.080
PLA+0.080
Neg logit contributions
anasia-0.100
 vas-0.093
 Bengals-0.090
 [*-0.089
cius-0.088
Token of
Token ID286
Feature activation-2.75e-01

Pos logit contributions
ASC+0.689
eur+0.609
 Agric+0.604
 parity+0.599
PLA+0.596
Neg logit contributions
anasia-0.581
 vas-0.534
 Bengals-0.518
 [*-0.507
cius-0.502
Token our
Token ID674
Feature activation-1.67e-01

Pos logit contributions
anasia+0.192
 vas+0.177
 Bengals+0.172
 [*+0.170
cius+0.167
Neg logit contributions
ASC-0.217
eur-0.190
 Agric-0.190
 Ribbon-0.187
PLA-0.187
Token gross
Token ID10319
Feature activation+2.80e+00

Pos logit contributions
anasia+0.124
 vas+0.115
 Bengals+0.112
 [*+0.110
cius+0.109
Neg logit contributions
ASC-0.124
eur-0.108
 Agric-0.108
 Ribbon-0.106
PLA-0.106
Token domestic
Token ID5928
Feature activation+1.35e+00

Pos logit contributions
ASC+1.817
eur+1.550
 Agric+1.528
 parity+1.513
PLA+1.509
Neg logit contributions
anasia-2.347
 vas-2.186
 Bengals-2.141
 [*-2.106
cius-2.097
Token product
Token ID1720
Feature activation-1.07e-01

Pos logit contributions
ASC+1.327
eur+1.196
 Agric+1.189
 parity+1.180
 Ribbon+1.179
Neg logit contributions
anasia-0.673
 vas-0.603
 Bengals-0.574
 [*-0.560
cius-0.558
Token and
Token ID290
Feature activation+3.85e-01

Pos logit contributions
anasia+0.073
 vas+0.067
 Bengals+0.065
 [*+0.064
cius+0.063
Neg logit contributions
ASC-0.086
eur-0.076
 Agric-0.075
PLA-0.075
 Ribbon-0.074
Token possess
Token ID8588
Feature activation-1.74e-01

Pos logit contributions
ASC+0.321
eur+0.284
 Agric+0.283
 Ribbon+0.279
PLA+0.279
Neg logit contributions
anasia-0.251
 vas-0.231
 Bengals-0.223
 [*-0.220
cius-0.216
Token enormous
Token ID9812
Feature activation-4.85e-01

Pos logit contributions
anasia+0.111
 vas+0.102
 Bengals+0.099
 [*+0.097
cius+0.096
Neg logit contributions
ASC-0.147
eur-0.130
 Agric-0.129
 Ribbon-0.128
PLA-0.127
Token hiring
Token ID12965
Feature activation+5.47e-01

Pos logit contributions
ASC+0.304
eur+0.262
 Agric+0.262
 Ribbon+0.258
PLA+0.258
Neg logit contributions
anasia-0.322
 vas-0.299
 Bengals-0.292
 [*-0.288
cius-0.284
Token for
Token ID329
Feature activation-6.08e-01

Pos logit contributions
ASC+0.431
eur+0.378
 Agric+0.376
 Ribbon+0.372
PLA+0.372
Neg logit contributions
anasia-0.382
 vas-0.353
 Bengals-0.343
 [*-0.338
cius-0.332
Token entry
Token ID5726
Feature activation-4.53e-01

Pos logit contributions
anasia+0.434
 vas+0.401
 Bengals+0.390
 [*+0.384
cius+0.379
Neg logit contributions
ASC-0.470
eur-0.412
 Agric-0.410
 Ribbon-0.405
PLA-0.404
Token-
Token ID12
Feature activation-2.24e-01

Pos logit contributions
anasia+0.290
 vas+0.267
 Bengals+0.259
 [*+0.254
cius+0.250
Neg logit contributions
ASC-0.382
eur-0.338
 Agric-0.337
PLA-0.333
 Ribbon-0.333
Tokenlevel
Token ID5715
Feature activation-9.20e-02

Pos logit contributions
anasia+0.127
 vas+0.115
 Bengals+0.111
 [*+0.109
cius+0.106
Neg logit contributions
ASC-0.206
eur-0.183
 Agric-0.183
PLA-0.181
 Ribbon-0.181
Token HR
Token ID15172
Feature activation-2.98e-01

Pos logit contributions
anasia+0.067
 vas+0.062
 Bengals+0.060
 [*+0.059
cius+0.058
Neg logit contributions
ASC-0.070
eur-0.061
 Agric-0.061
 Ribbon-0.060
PLA-0.060
Token positions
Token ID6116
Feature activation+4.07e-01

Pos logit contributions
anasia+0.214
 vas+0.199
 Bengals+0.193
 [*+0.191
cius+0.187
Neg logit contributions
ASC-0.228
eur-0.199
 Agric-0.198
 Ribbon-0.196
PLA-0.196
Token.
Token ID13
Feature activation+6.09e-01

Pos logit contributions
ASC+0.321
eur+0.281
 Agric+0.280
PLA+0.276
 Ribbon+0.276
Neg logit contributions
anasia-0.284
 vas-0.263
 Bengals-0.255
 [*-0.251
cius-0.247
Token We
Token ID775
Feature activation+8.37e-01

Pos logit contributions
ASC+0.455
 Agric+0.396
eur+0.395
 Ribbon+0.391
PLA+0.389
Neg logit contributions
anasia-0.452
 vas-0.421
 Bengals-0.405
 [*-0.399
cius-0.398
Token have
Token ID423
Feature activation+1.54e+00

Pos logit contributions
ASC+0.685
eur+0.603
 Agric+0.601
 Ribbon+0.594
orate+0.593
Neg logit contributions
anasia-0.559
 vas-0.512
 Bengals-0.497
 [*-0.489
cius-0.481
Token our
Token ID674
Feature activation+6.17e-01

Pos logit contributions
ASC+1.225
eur+1.074
 Agric+1.073
 Ribbon+1.062
PLA+1.058
Neg logit contributions
anasia-1.062
 vas-0.974
 Bengals-0.944
 [*-0.932
cius-0.922
Token six
Token ID2237
Feature activation-1.20e+00

Pos logit contributions
anasia+0.887
 vas+0.823
 Bengals+0.800
 [*+0.788
cius+0.775
Neg logit contributions
ASC-0.988
eur-0.864
 Agric-0.860
 Ribbon-0.850
PLA-0.850
Token financial
Token ID3176
Feature activation-2.34e+00

Pos logit contributions
anasia+0.777
 vas+0.717
 Bengals+0.694
 [*+0.683
cius+0.670
Neg logit contributions
ASC-1.000
eur-0.883
 Agric-0.879
 Ribbon-0.870
PLA-0.869
Token institutions
Token ID6712
Feature activation-1.99e+00

Pos logit contributions
anasia+1.670
 vas+1.564
 Bengals+1.520
 [*+1.500
cius+1.461
Neg logit contributions
ASC-1.790
eur-1.563
 Agric-1.549
PLA-1.544
 Ribbon-1.544
Token in
Token ID287
Feature activation-7.79e-01

Pos logit contributions
anasia+1.305
 vas+1.213
 Bengals+1.176
 [*+1.165
cius+1.139
Neg logit contributions
ASC-1.644
eur-1.448
PLA-1.443
 Agric-1.439
 Ribbon-1.438
Token this
Token ID428
Feature activation+4.10e-01

Pos logit contributions
anasia+0.548
 vas+0.507
 Bengals+0.492
 [*+0.485
cius+0.477
Neg logit contributions
ASC-0.611
eur-0.534
 Agric-0.533
 Ribbon-0.525
PLA-0.525
Token country
Token ID1499
Feature activation-8.70e-02

Pos logit contributions
ASC+0.312
eur+0.272
 Agric+0.271
 Ribbon+0.267
PLA+0.267
Neg logit contributions
anasia-0.297
 vas-0.276
 Bengals-0.268
 [*-0.264
cius-0.260
Token own
Token ID898
Feature activation-1.23e+00

Pos logit contributions
anasia+0.059
 vas+0.055
 Bengals+0.053
 [*+0.052
cius+0.052
Neg logit contributions
ASC-0.070
eur-0.061
 Agric-0.061
 Ribbon-0.060
PLA-0.060
Token assets
Token ID6798
Feature activation-2.05e+00

Pos logit contributions
anasia+0.776
 vas+0.713
 Bengals+0.689
 [*+0.678
cius+0.666
Neg logit contributions
ASC-1.056
eur-0.935
 Agric-0.932
 Ribbon-0.922
PLA-0.921
Token equal
Token ID4961
Feature activation+4.90e-03

Pos logit contributions
anasia+1.375
 vas+1.279
 Bengals+1.245
 [*+1.234
cius+1.193
Neg logit contributions
ASC-1.651
eur-1.447
 Agric-1.446
PLA-1.441
 Ribbon-1.436
Token to
Token ID284
Feature activation+2.66e-01

Pos logit contributions
ASC+0.004
eur+0.003
 Agric+0.003
orate+0.003
PLA+0.003
Neg logit contributions
anasia-0.003
 vas-0.003
 Bengals-0.003
 [*-0.003
cius-0.003
Token more
Token ID517
Feature activation+6.64e-01

Pos logit contributions
ASC+0.224
eur+0.199
 Agric+0.198
 parity+0.197
 Ribbon+0.196
Neg logit contributions
anasia-0.171
 vas-0.156
 Bengals-0.150
 [*-0.148
cius-0.147
Token about
Token ID546
Feature activation+7.36e-01

Pos logit contributions
anasia+1.293
 vas+1.211
 Bengals+1.173
 [*+1.162
cius+1.129
Neg logit contributions
ASC-1.501
eur-1.316
 Agric-1.307
PLA-1.301
 Ribbon-1.297
Token differing
Token ID28742
Feature activation-5.37e-02

Pos logit contributions
ASC+0.574
eur+0.502
 Agric+0.501
 Ribbon+0.495
orate+0.492
Neg logit contributions
anasia-0.521
 vas-0.480
 Bengals-0.466
 [*-0.458
cius-0.455
Token interpretation
Token ID10794
Feature activation+1.37e+00

Pos logit contributions
anasia+0.040
 vas+0.037
 Bengals+0.036
 [*+0.035
cius+0.035
Neg logit contributions
ASC-0.040
eur-0.035
 Agric-0.035
 Ribbon-0.034
PLA-0.034
Token of
Token ID286
Feature activation-5.72e-01

Pos logit contributions
ASC+1.094
eur+0.965
 Agric+0.955
PLA+0.947
 Ribbon+0.945
Neg logit contributions
anasia-0.936
 vas-0.862
 Bengals-0.836
 [*-0.812
cius-0.811
Token the
Token ID262
Feature activation-6.43e-01

Pos logit contributions
anasia+0.404
 vas+0.373
 Bengals+0.361
 [*+0.355
cius+0.352
Neg logit contributions
ASC-0.447
eur-0.392
 Agric-0.390
 Ribbon-0.386
PLA-0.384
Token words
Token ID2456
Feature activation+6.19e-01

Pos logit contributions
anasia+0.423
 vas+0.390
 Bengals+0.378
 [*+0.372
cius+0.365
Neg logit contributions
ASC-0.532
eur-0.469
 Agric-0.467
 Ribbon-0.462
PLA-0.462
Token in
Token ID287
Feature activation+3.21e-01

Pos logit contributions
ASC+0.499
eur+0.437
 Agric+0.436
 Ribbon+0.431
PLA+0.430
Neg logit contributions
anasia-0.423
 vas-0.388
 Bengals-0.376
 [*-0.368
cius-0.366
Token the
Token ID262
Feature activation-4.25e-01

Pos logit contributions
ASC+0.237
eur+0.206
 Agric+0.205
 Ribbon+0.202
PLA+0.202
Neg logit contributions
anasia-0.241
 vas-0.223
 Bengals-0.217
 [*-0.213
cius-0.212
Token statements
Token ID6299
Feature activation-9.74e-01

Pos logit contributions
anasia+0.297
 vas+0.275
 Bengals+0.267
 [*+0.264
cius+0.259
Neg logit contributions
ASC-0.334
eur-0.292
 Agric-0.291
PLA-0.288
 Ribbon-0.288
Token,
Token ID11
Feature activation+2.21e-01

Pos logit contributions
anasia+0.664
 vas+0.614
 Bengals+0.595
 [*+0.585
cius+0.576
Neg logit contributions
ASC-0.784
eur-0.689
 Agric-0.686
 Ribbon-0.678
PLA-0.678
Token or
Token ID393
Feature activation-3.93e-01

Pos logit contributions
ASC+0.182
eur+0.160
 Agric+0.160
 Ribbon+0.158
PLA+0.157
Neg logit contributions
anasia-0.147
 vas-0.135
 Bengals-0.131
 [*-0.128
cius-0.127
Token Carter
Token ID10831
Feature activation+7.59e-01

Pos logit contributions
ASC+0.417
eur+0.369
 Agric+0.368
 Ribbon+0.364
PLA+0.364
Neg logit contributions
anasia-0.308
 vas-0.283
 Bengals-0.273
 [*-0.269
cius-0.264
Token re
Token ID302
Feature activation-5.04e-01

Pos logit contributions
ASC+0.579
eur+0.506
 Agric+0.502
 Ribbon+0.498
PLA+0.496
Neg logit contributions
anasia-0.547
 vas-0.507
 Bengals-0.493
 [*-0.487
cius-0.479
Tokenrun
Token ID5143
Feature activation-7.17e-01

Pos logit contributions
anasia+0.332
 vas+0.306
 Bengals+0.297
 [*+0.292
cius+0.287
Neg logit contributions
ASC-0.417
eur-0.368
 Agric-0.366
 Ribbon-0.362
PLA-0.362
Token is
Token ID318
Feature activation+5.51e-01

Pos logit contributions
anasia+0.471
 vas+0.437
 Bengals+0.423
 [*+0.417
cius+0.407
Neg logit contributions
ASC-0.593
 Agric-0.521
eur-0.521
PLA-0.515
 Ribbon-0.514
Token probably
Token ID2192
Feature activation+2.15e-01

Pos logit contributions
ASC+0.450
eur+0.398
 Agric+0.396
 Ribbon+0.391
orate+0.390
Neg logit contributions
anasia-0.369
 vas-0.338
 Bengals-0.328
 [*-0.322
cius-0.319
Token a
Token ID257
Feature activation+8.05e-02

Pos logit contributions
ASC+0.169
eur+0.148
 Agric+0.147
PLA+0.145
 Ribbon+0.145
Neg logit contributions
anasia-0.151
 vas-0.140
 Bengals-0.136
 [*-0.134
cius-0.132
Token best
Token ID1266
Feature activation+1.04e+00

Pos logit contributions
ASC+0.067
eur+0.059
 Agric+0.058
PLA+0.058
 Ribbon+0.058
Neg logit contributions
anasia-0.053
 vas-0.049
 Bengals-0.048
 [*-0.047
cius-0.046
Token-
Token ID12
Feature activation+1.33e+00

Pos logit contributions
ASC+0.959
eur+0.860
 Agric+0.855
 Ribbon+0.846
orate+0.846
Neg logit contributions
anasia-0.585
 vas-0.528
 Bengals-0.510
 [*-0.501
cius-0.492
Tokencase
Token ID7442
Feature activation+1.60e+00

Pos logit contributions
ASC+0.778
eur+0.641
 Agric+0.631
PLA+0.625
 Ribbon+0.615
Neg logit contributions
anasia-1.200
 vas-1.136
 Bengals-1.110
 [*-1.098
cius-1.076
Token scenario
Token ID8883
Feature activation+5.45e-01

Pos logit contributions
ASC+1.127
eur+0.980
 Agric+0.975
orate+0.957
 Ribbon+0.954
Neg logit contributions
anasia-1.241
 vas-1.147
 Bengals-1.121
 [*-1.106
cius-1.101
Token.
Token ID13
Feature activation-7.90e-01

Pos logit contributions
ASC+0.419
eur+0.367
 Agric+0.365
 Ribbon+0.360
PLA+0.360
Neg logit contributions
anasia-0.389
 vas-0.361
 Bengals-0.351
 [*-0.346
cius-0.341
Token.
Token ID13
Feature activation+6.65e-01

Pos logit contributions
ASC+0.995
eur+0.881
 Agric+0.875
orate+0.869
 Ribbon+0.866
Neg logit contributions
anasia-0.832
 vas-0.762
 Bengals-0.740
 [*-0.723
cius-0.716
Token But
Token ID887
Feature activation-5.64e-03

Pos logit contributions
ASC+0.533
eur+0.468
 Agric+0.468
 Ribbon+0.463
PLA+0.461
Neg logit contributions
anasia-0.455
 vas-0.421
 Bengals-0.406
 [*-0.399
cius-0.397
Token Fox
Token ID5426
Feature activation+1.16e+00

Pos logit contributions
anasia+0.004
 vas+0.004
 Bengals+0.003
 [*+0.003
cius+0.003
Neg logit contributions
ASC-0.005
eur-0.004
 Agric-0.004
PLA-0.004
 Ribbon-0.004
Token News
Token ID3000
Feature activation+1.78e+00

Pos logit contributions
ASC+0.944
eur+0.835
 Agric+0.829
PLA+0.821
 Ribbon+0.821
Neg logit contributions
anasia-0.771
 vas-0.711
 Bengals-0.688
 [*-0.677
cius-0.669
Token/
Token ID14
Feature activation+1.58e+00

Pos logit contributions
ASC+1.421
eur+1.251
 Agric+1.243
 Ribbon+1.233
PLA+1.228
Neg logit contributions
anasia-1.213
 vas-1.116
 Bengals-1.079
 [*-1.064
cius-1.056
TokenO
Token ID46
Feature activation+1.12e+00

Pos logit contributions
ASC+1.001
eur+0.846
 Agric+0.829
PLA+0.824
orate+0.822
Neg logit contributions
anasia-1.358
 vas-1.277
 Bengals-1.245
 [*-1.226
cius-1.218
Tokenpin
Token ID11635
Feature activation-5.84e-01

Pos logit contributions
ASC+1.088
eur+0.981
 Agric+0.968
PLA+0.960
 Ribbon+0.957
Neg logit contributions
anasia-0.584
 vas-0.524
 Bengals-0.506
 [*-0.493
cius-0.479
Tokenion
Token ID295
Feature activation+1.24e+00

Pos logit contributions
anasia+0.469
 vas+0.439
 Bengals+0.428
 [*+0.423
cius+0.416
Neg logit contributions
ASC-0.398
eur-0.341
 Agric-0.339
PLA-0.335
 Ribbon-0.334
Token Dynamics
Token ID33806
Feature activation+4.63e-01

Pos logit contributions
ASC+0.972
eur+0.850
 Agric+0.847
 Ribbon+0.837
PLA+0.837
Neg logit contributions
anasia-0.871
 vas-0.809
 Bengals-0.785
 [*-0.774
cius-0.761
Token did
Token ID750
Feature activation+2.52e-01

Pos logit contributions
ASC+0.381
eur+0.336
 Agric+0.334
 Ribbon+0.331
PLA+0.330
Neg logit contributions
anasia-0.306
 vas-0.283
 Bengals-0.274
 [*-0.270
cius-0.265
Token a
Token ID257
Feature activation+4.37e-01

Pos logit contributions
ASC+0.205
eur+0.180
 Agric+0.179
PLA+0.177
 Ribbon+0.177
Neg logit contributions
anasia-0.169
 vas-0.157
 Bengals-0.152
 [*-0.150
cius-0.146
Token,
Token ID11
Feature activation-1.44e+00

Pos logit contributions
anasia+0.167
 vas+0.154
 Bengals+0.150
 [*+0.148
cius+0.145
Neg logit contributions
ASC-0.192
eur-0.168
 Agric-0.168
 Ribbon-0.166
PLA-0.166
Token by
Token ID416
Feature activation-7.92e-01

Pos logit contributions
anasia+0.979
 vas+0.909
 Bengals+0.881
 [*+0.870
cius+0.853
Neg logit contributions
ASC-1.158
eur-1.016
 Agric-1.010
PLA-1.007
 Ribbon-1.002
Token building
Token ID2615
Feature activation-2.08e-01

Pos logit contributions
anasia+0.567
 vas+0.528
 Bengals+0.512
 [*+0.505
cius+0.496
Neg logit contributions
ASC-0.610
eur-0.532
 Agric-0.529
PLA-0.524
 Ribbon-0.524
Token up
Token ID510
Feature activation-7.13e-01

Pos logit contributions
anasia+0.144
 vas+0.134
 Bengals+0.130
 [*+0.128
cius+0.125
Neg logit contributions
ASC-0.165
eur-0.144
 Agric-0.144
 Ribbon-0.142
PLA-0.142
Token their
Token ID511
Feature activation-6.05e-01

Pos logit contributions
anasia+0.503
 vas+0.469
 Bengals+0.455
 [*+0.448
cius+0.440
Neg logit contributions
ASC-0.554
eur-0.484
 Agric-0.482
 Ribbon-0.477
PLA-0.477
Token military
Token ID2422
Feature activation-9.77e-01

Pos logit contributions
anasia+0.463
 vas+0.435
 Bengals+0.423
 [*+0.418
cius+0.410
Neg logit contributions
ASC-0.433
eur-0.373
 Agric-0.372
 Ribbon-0.368
PLA-0.368
Token and
Token ID290
Feature activation-4.64e-01

Pos logit contributions
anasia+0.640
 vas+0.602
 Bengals+0.581
 [*+0.571
cius+0.557
Neg logit contributions
ASC-0.806
 Agric-0.706
eur-0.704
 Ribbon-0.697
PLA-0.695
Token asking
Token ID4737
Feature activation-3.06e-01

Pos logit contributions
anasia+0.333
 vas+0.310
 Bengals+0.301
 [*+0.297
cius+0.292
Neg logit contributions
ASC-0.357
eur-0.311
 Agric-0.309
PLA-0.306
 Ribbon-0.306
Token the
Token ID262
Feature activation-1.28e+00

Pos logit contributions
anasia+0.209
 vas+0.193
 Bengals+0.187
 [*+0.185
cius+0.181
Neg logit contributions
ASC-0.245
eur-0.215
 Agric-0.214
PLA-0.212
 Ribbon-0.212
Token United
Token ID1578
Feature activation-1.14e-01

Pos logit contributions
anasia+0.976
 vas+0.921
 Bengals+0.896
 [*+0.880
cius+0.866
Neg logit contributions
ASC-0.923
eur-0.796
 Agric-0.790
PLA-0.786
orate-0.784
Token States
Token ID1829
Feature activation+1.53e-02

Pos logit contributions
anasia+0.109
 vas+0.103
 Bengals+0.100
 [*+0.100
cius+0.098
Neg logit contributions
ASC-0.061
eur-0.049
 Agric-0.049
PLA-0.048
 Ribbon-0.048
Token has
Token ID468
Feature activation-3.70e-01

Pos logit contributions
anasia+1.239
 vas+1.153
 Bengals+1.116
 [*+1.099
cius+1.071
Neg logit contributions
ASC-1.577
eur-1.386
 Agric-1.384
PLA-1.372
orate-1.369
Token remained
Token ID6150
Feature activation-8.96e-01

Pos logit contributions
anasia+0.255
 vas+0.236
 Bengals+0.229
 [*+0.226
cius+0.222
Neg logit contributions
ASC-0.294
eur-0.258
 Agric-0.257
 Ribbon-0.254
PLA-0.253
Token so
Token ID523
Feature activation+5.30e-01

Pos logit contributions
anasia+0.567
 vas+0.519
 Bengals+0.502
 [*+0.494
cius+0.486
Neg logit contributions
ASC-0.765
eur-0.678
 Agric-0.676
PLA-0.668
 Ribbon-0.668
Token elusive
Token ID29885
Feature activation-3.35e-01

Pos logit contributions
ASC+0.442
eur+0.394
 Agric+0.391
 parity+0.386
 Ribbon+0.385
Neg logit contributions
anasia-0.344
 vas-0.312
 Bengals-0.304
 [*-0.299
cius-0.296
Token,
Token ID11
Feature activation-2.92e-01

Pos logit contributions
anasia+0.227
 vas+0.210
 Bengals+0.204
 [*+0.201
cius+0.197
Neg logit contributions
ASC-0.270
eur-0.237
 Agric-0.236
 Ribbon-0.234
PLA-0.233
Token physicists
Token ID37898
Feature activation-2.21e+00

Pos logit contributions
anasia+0.204
 vas+0.189
 Bengals+0.184
 [*+0.181
cius+0.178
Neg logit contributions
ASC-0.230
eur-0.202
 Agric-0.201
PLA-0.198
 Ribbon-0.198
Token have
Token ID423
Feature activation+3.72e-01

Pos logit contributions
anasia+1.424
 vas+1.341
 Bengals+1.292
 [*+1.272
cius+1.250
Neg logit contributions
ASC-1.832
eur-1.620
PLA-1.614
 Agric-1.605
orate-1.594
Token turned
Token ID2900
Feature activation+2.84e-01

Pos logit contributions
ASC+0.299
eur+0.263
 Agric+0.262
 Ribbon+0.259
PLA+0.259
Neg logit contributions
anasia-0.252
 vas-0.233
 Bengals-0.226
 [*-0.223
cius-0.219
Token their
Token ID511
Feature activation+7.08e-01

Pos logit contributions
ASC+0.220
 Agric+0.193
eur+0.192
 Ribbon+0.189
orate+0.189
Neg logit contributions
anasia-0.203
 vas-0.187
 Bengals-0.182
 [*-0.180
cius-0.177
Token sights
Token ID21343
Feature activation+1.67e+00

Pos logit contributions
ASC+0.583
eur+0.516
 Agric+0.513
orate+0.507
 Ribbon+0.506
Neg logit contributions
anasia-0.468
 vas-0.428
 Bengals-0.414
 [*-0.409
cius-0.404
Token to
Token ID284
Feature activation+6.44e-01

Pos logit contributions
ASC+1.251
eur+1.102
 Agric+1.097
orate+1.075
 parity+1.073
Neg logit contributions
anasia-1.221
 vas-1.119
 Bengals-1.089
 [*-1.069
cius-1.065
Tokenence
Token ID594
Feature activation-1.92e+00

Pos logit contributions
anasia+0.923
 vas+0.857
 Bengals+0.833
 [*+0.820
cius+0.807
Neg logit contributions
ASC-1.003
eur-0.876
 Agric-0.872
PLA-0.863
 Ribbon-0.863
Token of
Token ID286
Feature activation-7.85e-01

Pos logit contributions
anasia+1.229
 vas+1.136
 Bengals+1.095
 [*+1.083
cius+1.059
Neg logit contributions
ASC-1.619
eur-1.423
 Agric-1.421
PLA-1.414
 Ribbon-1.410
Token office
Token ID2607
Feature activation-4.98e-01

Pos logit contributions
anasia+0.532
 vas+0.494
 Bengals+0.478
 [*+0.471
cius+0.462
Neg logit contributions
ASC-0.634
eur-0.556
 Agric-0.554
PLA-0.550
 Ribbon-0.548
Token,
Token ID11
Feature activation-1.27e+00

Pos logit contributions
anasia+0.347
 vas+0.322
 Bengals+0.312
 [*+0.308
cius+0.303
Neg logit contributions
ASC-0.393
eur-0.344
 Agric-0.343
 Ribbon-0.338
PLA-0.338
Token and
Token ID290
Feature activation-1.45e+00

Pos logit contributions
anasia+0.867
 vas+0.803
 Bengals+0.778
 [*+0.767
cius+0.753
Neg logit contributions
ASC-1.024
eur-0.899
 Agric-0.895
PLA-0.886
 Ribbon-0.885
Token the
Token ID262
Feature activation-1.62e+00

Pos logit contributions
anasia+0.994
 vas+0.925
 Bengals+0.892
 [*+0.883
cius+0.868
Neg logit contributions
ASC-1.161
eur-1.013
 Agric-1.011
PLA-1.005
 Ribbon-1.001
Token sp
Token ID599
Feature activation+4.31e-01

Pos logit contributions
anasia+1.147
 vas+1.074
 Bengals+1.034
 [*+1.025
cius+1.003
Neg logit contributions
ASC-1.265
PLA-1.097
 Agric-1.095
eur-1.095
 Ribbon-1.084
Tokenurn
Token ID700
Feature activation-9.95e-01

Pos logit contributions
ASC+0.327
eur+0.285
 Agric+0.283
orate+0.280
PLA+0.280
Neg logit contributions
anasia-0.312
 vas-0.292
 Bengals-0.284
 [*-0.279
cius-0.275
Tokens
Token ID82
Feature activation-2.06e+00

Pos logit contributions
anasia+0.643
 vas+0.592
 Bengals+0.573
 [*+0.564
cius+0.554
Neg logit contributions
ASC-0.835
eur-0.735
 Agric-0.735
PLA-0.728
 Ribbon-0.726
Token
Token ID198
Feature activation+2.45e-01

Pos logit contributions
anasia+1.312
 vas+1.215
 Bengals+1.168
 [*+1.159
cius+1.132
Neg logit contributions
ASC-1.739
eur-1.526
 Agric-1.526
PLA-1.523
 Ribbon-1.516
Token
Token ID198
Feature activation+1.39e-01

Pos logit contributions
ASC+0.217
eur+0.193
 Agric+0.192
PLA+0.190
 Ribbon+0.190
Neg logit contributions
anasia-0.148
 vas-0.135
 Bengals-0.130
 [*-0.128
cius-0.127
Token dB
Token ID30221
Feature activation+3.58e-01

Pos logit contributions
ASC+0.390
eur+0.334
 Agric+0.333
PLA+0.330
orate+0.329
Neg logit contributions
anasia-0.419
 vas-0.391
 Bengals-0.384
 [*-0.378
cius-0.370
Tokenm
Token ID76
Feature activation+4.99e-01

Pos logit contributions
ASC+0.273
eur+0.238
 Agric+0.237
PLA+0.234
 Ribbon+0.234
Neg logit contributions
anasia-0.258
 vas-0.240
 Bengals-0.234
 [*-0.230
cius-0.226
Token Ret
Token ID4990
Feature activation-1.17e-01

Pos logit contributions
ASC+0.322
eur+0.274
 Agric+0.273
 Ribbon+0.269
PLA+0.268
Neg logit contributions
anasia-0.419
 vas-0.393
 Bengals-0.383
 [*-0.378
cius-0.374
Tokenry
Token ID563
Feature activation+8.45e-01

Pos logit contributions
anasia+0.065
 vas+0.059
 Bengals+0.057
 [*+0.056
cius+0.054
Neg logit contributions
ASC-0.109
eur-0.097
 Agric-0.097
PLA-0.096
 Ribbon-0.096
Token short
Token ID1790
Feature activation-2.61e-01

Pos logit contributions
ASC+0.580
eur+0.499
 Ribbon+0.498
 Agric+0.496
 parity+0.491
Neg logit contributions
anasia-0.670
 vas-0.621
 Bengals-0.612
 [*-0.599
cius-0.597
Token limit
Token ID4179
Feature activation-1.06e+00

Pos logit contributions
anasia+0.181
 vas+0.168
 Bengals+0.163
 [*+0.161
cius+0.158
Neg logit contributions
ASC-0.207
eur-0.181
 Agric-0.180
 Ribbon-0.178
PLA-0.178
Token:
Token ID25
Feature activation+2.10e+00

Pos logit contributions
anasia+0.726
 vas+0.674
 Bengals+0.655
 [*+0.647
cius+0.630
Neg logit contributions
ASC-0.845
 Agric-0.741
eur-0.740
 Ribbon-0.733
orate-0.731
Token7
Token ID22
Feature activation+1.53e+00

Pos logit contributions
ASC+1.361
eur+1.151
 Agric+1.133
PLA+1.124
 Ribbon+1.123
Neg logit contributions
anasia-1.765
 vas-1.657
 Bengals-1.614
 [*-1.591
cius-1.578
Token R
Token ID371
Feature activation+1.06e+00

Pos logit contributions
ASC+1.068
eur+0.922
 Agric+0.920
 Ribbon+0.919
orate+0.897
Neg logit contributions
anasia-1.212
 vas-1.131
 Bengals-1.095
cius-1.078
 [*-1.075
TokenTS
Token ID4694
Feature activation+6.50e-01

Pos logit contributions
ASC+0.779
eur+0.671
 Agric+0.667
PLA+0.663
orate+0.658
Neg logit contributions
anasia-0.796
 vas-0.746
 Bengals-0.725
 [*-0.715
cius-0.703
Token thr
Token ID5636
Feature activation-1.60e+00

Pos logit contributions
ASC+0.520
eur+0.458
 Agric+0.453
 Ribbon+0.447
orate+0.447
Neg logit contributions
anasia-0.446
 vas-0.410
 Bengals-0.400
 [*-0.392
cius-0.390
Token web
Token ID3992
Feature activation-1.18e-01

Pos logit contributions
anasia+0.149
 vas+0.138
 Bengals+0.134
 [*+0.132
cius+0.130
Neg logit contributions
ASC-0.166
eur-0.146
 Agric-0.145
 Ribbon-0.143
PLA-0.143
Token browser
Token ID6444
Feature activation+1.11e+00

Pos logit contributions
anasia+0.074
 vas+0.068
 Bengals+0.066
 [*+0.065
cius+0.064
Neg logit contributions
ASC-0.101
eur-0.090
 Agric-0.089
 Ribbon-0.089
PLA-0.088
Token,
Token ID11
Feature activation-2.21e-02

Pos logit contributions
ASC+0.893
eur+0.786
 Agric+0.782
 Ribbon+0.774
PLA+0.772
Neg logit contributions
anasia-0.754
 vas-0.696
 Bengals-0.675
 [*-0.664
cius-0.655
Token saw
Token ID2497
Feature activation-2.25e+00

Pos logit contributions
anasia+0.016
 vas+0.015
 Bengals+0.014
 [*+0.014
cius+0.014
Neg logit contributions
ASC-0.017
eur-0.015
 Agric-0.015
 Ribbon-0.015
PLA-0.015
Token its
Token ID663
Feature activation-1.30e+00

Pos logit contributions
anasia+1.556
 vas+1.450
 Bengals+1.407
 [*+1.386
cius+1.352
Neg logit contributions
ASC-1.787
eur-1.564
 Agric-1.560
PLA-1.546
orate-1.535
Token 2016
Token ID1584
Feature activation-1.09e+00

Pos logit contributions
anasia+0.858
 vas+0.796
 Bengals+0.772
 [*+0.760
cius+0.743
Neg logit contributions
ASC-1.068
eur-0.939
 Agric-0.936
PLA-0.927
orate-0.924
Token revenue
Token ID6426
Feature activation-2.33e-02

Pos logit contributions
anasia+0.727
 vas+0.673
 Bengals+0.652
 [*+0.642
cius+0.630
Neg logit contributions
ASC-0.884
eur-0.777
 Agric-0.774
PLA-0.766
 Ribbon-0.765
Token increase
Token ID2620
Feature activation-1.59e+00

Pos logit contributions
anasia+0.014
 vas+0.013
 Bengals+0.013
 [*+0.012
cius+0.012
Neg logit contributions
ASC-0.020
eur-0.018
 Agric-0.018
 Ribbon-0.018
orate-0.018
Token 24
Token ID1987
Feature activation-7.59e-02

Pos logit contributions
anasia+1.030
 vas+0.954
 Bengals+0.928
 [*+0.913
cius+0.885
Neg logit contributions
ASC-1.330
eur-1.163
 Agric-1.162
PLA-1.156
 Ribbon-1.145
Token percent
Token ID1411
Feature activation+3.35e-01

Pos logit contributions
anasia+0.057
 vas+0.053
 Bengals+0.052
 [*+0.051
cius+0.050
Neg logit contributions
ASC-0.055
eur-0.048
 Agric-0.048
 Ribbon-0.047
PLA-0.047
Token to
Token ID284
Feature activation-5.88e-02

Pos logit contributions
ASC+0.266
eur+0.234
 Agric+0.233
 Ribbon+0.230
PLA+0.230
Neg logit contributions
anasia-0.231
 vas-0.214
 Bengals-0.207
 [*-0.204
cius-0.201
Tokenuring
Token ID870
Feature activation-1.75e+00

Pos logit contributions
anasia+2.428
 vas+2.276
 Bengals+2.196
 [*+2.171
cius+2.099
Neg logit contributions
ASC-2.962
 Agric-2.585
PLA-2.562
eur-2.560
orate-2.557
Token kernel
Token ID9720
Feature activation-2.50e+00

Pos logit contributions
anasia+1.099
 vas+1.023
 Bengals+0.986
 [*+0.973
cius+0.944
Neg logit contributions
ASC-1.497
eur-1.320
 Agric-1.319
PLA-1.305
 Ribbon-1.304
Token rect
Token ID13621
Feature activation-2.29e+00

Pos logit contributions
anasia+1.641
 vas+1.540
 Bengals+1.484
 [*+1.467
cius+1.412
Neg logit contributions
ASC-2.056
eur-1.805
 Agric-1.800
PLA-1.788
orate-1.787
TokenK
Token ID42
Feature activation+6.22e-01

Pos logit contributions
anasia+1.434
 vas+1.310
 Bengals+1.272
 [*+1.254
cius+1.227
Neg logit contributions
ASC-1.960
 Agric-1.738
eur-1.728
 Ribbon-1.721
PLA-1.721
Tokenernel
Token ID7948
Feature activation-2.38e-01

Pos logit contributions
ASC+0.541
eur+0.483
PLA+0.475
 Agric+0.474
 Ribbon+0.472
Neg logit contributions
anasia-0.383
 vas-0.350
 Bengals-0.339
 [*-0.334
cius-0.323
Token =
Token ID796
Feature activation-4.24e+00

Pos logit contributions
anasia+0.150
 vas+0.138
 Bengals+0.134
 [*+0.132
cius+0.129
Neg logit contributions
ASC-0.203
eur-0.180
 Agric-0.180
 Ribbon-0.178
PLA-0.178
Token c
Token ID269
Feature activation+6.68e-01

Pos logit contributions
anasia+2.697
 vas+2.608
 Bengals+2.498
 [*+2.479
cius+2.355
Neg logit contributions
ASC-3.506
eur-3.086
PLA-3.061
orate-3.043
 Agric-3.037
Tokenv
Token ID85
Feature activation-1.58e+00

Pos logit contributions
ASC+0.609
eur+0.547
 Agric+0.541
orate+0.536
PLA+0.535
Neg logit contributions
anasia-0.384
 vas-0.346
 Bengals-0.336
 [*-0.328
cius-0.321
Token2
Token ID17
Feature activation-6.82e-01

Pos logit contributions
anasia+1.089
 vas+1.011
 Bengals+0.980
 [*+0.970
cius+0.952
Neg logit contributions
ASC-1.256
eur-1.103
 Agric-1.100
 Ribbon-1.087
PLA-1.085
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
anasia+0.489
 vas+0.454
 Bengals+0.441
 [*+0.434
cius+0.427
Neg logit contributions
ASC-0.524
eur-0.458
 Agric-0.456
PLA-0.450
 Ribbon-0.450
Tokenget
Token ID1136
Feature activation+1.54e+00

Pos logit contributions
anasia+0.844
 vas+0.791
 Bengals+0.770
 [*+0.762
cius+0.753
Neg logit contributions
ASC-0.769
eur-0.666
 Agric-0.665
 Ribbon-0.657
orate-0.654
Token open
Token ID1280
Feature activation-9.26e-01

Pos logit contributions
anasia+0.725
 vas+0.670
 Bengals+0.647
 [*+0.637
cius+0.620
Neg logit contributions
ASC-1.020
eur-0.902
 Agric-0.898
PLA-0.892
 Ribbon-0.888
Token new
Token ID649
Feature activation-9.02e-01

Pos logit contributions
anasia+0.624
 vas+0.580
 Bengals+0.563
 [*+0.553
cius+0.543
Neg logit contributions
ASC-0.751
eur-0.659
 Agric-0.653
PLA-0.649
 Ribbon-0.648
Token store
Token ID3650
Feature activation-2.39e+00

Pos logit contributions
anasia+0.607
 vas+0.564
 Bengals+0.547
 [*+0.537
cius+0.528
Neg logit contributions
ASC-0.732
eur-0.642
 Agric-0.637
PLA-0.633
 Ribbon-0.632
Token at
Token ID379
Feature activation-5.50e-01

Pos logit contributions
anasia+1.468
 vas+1.360
 Bengals+1.321
 [*+1.294
cius+1.258
Neg logit contributions
ASC-2.068
eur-1.820
 Agric-1.810
PLA-1.806
orate-1.800
Token Five
Token ID10579
Feature activation-7.17e-01

Pos logit contributions
anasia+0.385
 vas+0.358
 Bengals+0.347
 [*+0.342
cius+0.336
Neg logit contributions
ASC-0.431
eur-0.377
 Agric-0.376
PLA-0.371
 Ribbon-0.371
Token Corn
Token ID11424
Feature activation-4.25e+00

Pos logit contributions
anasia+0.540
 vas+0.503
 Bengals+0.492
 [*+0.484
cius+0.476
Neg logit contributions
ASC-0.523
eur-0.451
 Agric-0.449
PLA-0.447
orate-0.443
Tokeners
Token ID364
Feature activation-4.40e-01

Pos logit contributions
anasia+2.424
 vas+2.205
 Bengals+2.182
 [*+2.117
cius+2.099
Neg logit contributions
ASC-3.872
PLA-3.407
eur-3.387
 Agric-3.358
orate-3.347
Token in
Token ID287
Feature activation-9.12e-02

Pos logit contributions
anasia+0.291
 vas+0.269
 Bengals+0.260
 [*+0.256
cius+0.252
Neg logit contributions
ASC-0.363
eur-0.320
 Agric-0.318
PLA-0.315
 Ribbon-0.315
Token Bur
Token ID5481
Feature activation+8.08e-01

Pos logit contributions
anasia+0.062
 vas+0.057
 Bengals+0.056
 [*+0.055
cius+0.054
Neg logit contributions
ASC-0.073
eur-0.064
 Agric-0.064
 Ribbon-0.063
PLA-0.063
Tokenien
Token ID2013
Feature activation-6.00e-01

Pos logit contributions
ASC+0.571
eur+0.492
 Agric+0.490
 Ribbon+0.484
PLA+0.484
Neg logit contributions
anasia-0.628
 vas-0.587
 Bengals-0.571
 [*-0.564
cius-0.556
Token
Token ID198
Feature activation+7.24e-01

Pos logit contributions
anasia+0.396
 vas+0.366
 Bengals+0.355
 [*+0.349
cius+0.343
Neg logit contributions
ASC-0.495
eur-0.436
 Agric-0.434
PLA-0.429
 Ribbon-0.429
Token only
Token ID691
Feature activation+4.78e-01

Pos logit contributions
anasia+1.306
 vas+1.213
 Bengals+1.169
 [*+1.160
cius+1.125
Neg logit contributions
ASC-1.687
eur-1.478
 Agric-1.472
PLA-1.468
 Ribbon-1.460
Token within
Token ID1626
Feature activation-1.00e+00

Pos logit contributions
ASC+0.391
eur+0.345
 Agric+0.344
 Ribbon+0.340
PLA+0.339
Neg logit contributions
anasia-0.317
 vas-0.292
 Bengals-0.284
 [*-0.279
cius-0.275
Token the
Token ID262
Feature activation+4.13e-01

Pos logit contributions
anasia+0.725
 vas+0.677
 Bengals+0.655
 [*+0.648
cius+0.637
Neg logit contributions
ASC-0.765
eur-0.666
 Agric-0.662
PLA-0.656
 Ribbon-0.655
Token subject
Token ID2426
Feature activation+1.43e+00

Pos logit contributions
ASC+0.296
eur+0.257
 Agric+0.256
 Ribbon+0.252
PLA+0.252
Neg logit contributions
anasia-0.316
 vas-0.294
 Bengals-0.287
 [*-0.283
cius-0.279
Token areas
Token ID3006
Feature activation-6.01e-01

Pos logit contributions
ASC+1.122
eur+0.991
 Agric+0.982
orate+0.980
 parity+0.967
Neg logit contributions
anasia-1.005
 vas-0.921
 Bengals-0.903
 [*-0.884
cius-0.873
Token enumer
Token ID27056
Feature activation-4.66e+00

Pos logit contributions
anasia+0.403
 vas+0.373
 Bengals+0.362
 [*+0.356
cius+0.350
Neg logit contributions
ASC-0.489
eur-0.430
 Agric-0.429
PLA-0.424
 Ribbon-0.424
Tokenated
Token ID515
Feature activation-1.72e+00

Pos logit contributions
anasia+3.678
 vas+3.453
 Bengals+3.405
 [*+3.364
cius+3.312
Neg logit contributions
ASC-3.185
eur-2.705
 Agric-2.700
 Ribbon-2.691
PLA-2.680
Token under
Token ID739
Feature activation+3.04e-01

Pos logit contributions
anasia+1.085
 vas+1.002
 Bengals+0.967
 [*+0.956
cius+0.934
Neg logit contributions
ASC-1.461
eur-1.291
 Agric-1.287
PLA-1.275
 Ribbon-1.273
Token section
Token ID2665
Feature activation-3.11e+00

Pos logit contributions
ASC+0.233
eur+0.204
 Agric+0.203
 Ribbon+0.201
orate+0.200
Neg logit contributions
anasia-0.218
 vas-0.202
 Bengals-0.197
 [*-0.193
cius-0.190
Token 51
Token ID6885
Feature activation+4.20e-01

Pos logit contributions
anasia+2.080
 vas+1.957
 Bengals+1.896
 [*+1.866
cius+1.788
Neg logit contributions
ASC-2.513
eur-2.185
PLA-2.172
 Agric-2.164
orate-2.162
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
ASC+0.334
eur+0.293
 Agric+0.292
 Ribbon+0.288
PLA+0.288
Neg logit contributions
anasia-0.290
 vas-0.269
 Bengals-0.261
 [*-0.257
cius-0.252
Token of
Token ID286
Feature activation-1.73e-01

Pos logit contributions
anasia+0.686
 vas+0.636
 Bengals+0.617
 [*+0.608
cius+0.598
Neg logit contributions
ASC-0.779
eur-0.683
 Agric-0.680
 Ribbon-0.672
PLA-0.672
Token improvement
Token ID9025
Feature activation-4.68e-01

Pos logit contributions
anasia+0.127
 vas+0.119
 Bengals+0.115
 [*+0.114
cius+0.112
Neg logit contributions
ASC-0.130
eur-0.113
 Agric-0.112
 Ribbon-0.111
PLA-0.111
Token that
Token ID326
Feature activation-8.37e-01

Pos logit contributions
anasia+0.326
 vas+0.302
 Bengals+0.294
 [*+0.289
cius+0.284
Neg logit contributions
ASC-0.369
eur-0.323
 Agric-0.322
 Ribbon-0.318
PLA-0.318
Token values
Token ID3815
Feature activation-1.08e-01

Pos logit contributions
anasia+0.599
 vas+0.555
 Bengals+0.539
 [*+0.531
cius+0.523
Neg logit contributions
ASC-0.644
eur-0.563
 Agric-0.560
 Ribbon-0.553
PLA-0.553
Token defect
Token ID11855
Feature activation+1.72e-01

Pos logit contributions
anasia+0.080
 vas+0.074
 Bengals+0.072
 [*+0.071
cius+0.070
Neg logit contributions
ASC-0.081
eur-0.070
 Agric-0.070
 Ribbon-0.069
PLA-0.069
Token prevention
Token ID14196
Feature activation-4.25e+00

Pos logit contributions
ASC+0.136
eur+0.120
 Agric+0.119
orate+0.118
 Ribbon+0.117
Neg logit contributions
anasia-0.120
 vas-0.111
 Bengals-0.108
 [*-0.106
cius-0.104
Token over
Token ID625
Feature activation-1.07e+00

Pos logit contributions
anasia+2.653
 vas+2.461
 [*+2.376
 Bengals+2.374
cius+2.283
Neg logit contributions
ASC-3.615
eur-3.199
 Agric-3.198
PLA-3.162
orate-3.142
Token defect
Token ID11855
Feature activation+7.52e-01

Pos logit contributions
anasia+0.789
 vas+0.739
 Bengals+0.716
 [*+0.709
cius+0.694
Neg logit contributions
ASC-0.805
eur-0.697
 Agric-0.694
PLA-0.689
 Ribbon-0.684
Token detection
Token ID13326
Feature activation-1.32e+00

Pos logit contributions
ASC+0.581
eur+0.512
 Agric+0.507
orate+0.501
 Ribbon+0.500
Neg logit contributions
anasia-0.533
 vas-0.494
 Bengals-0.481
 [*-0.472
cius-0.468
Token.
Token ID13
Feature activation-3.53e-02

Pos logit contributions
anasia+0.889
 vas+0.822
 Bengals+0.797
 [*+0.787
cius+0.771
Neg logit contributions
ASC-1.065
eur-0.935
 Agric-0.932
 Ribbon-0.921
PLA-0.921
Token It
Token ID632
Feature activation-2.95e-01

Pos logit contributions
anasia+0.025
 vas+0.023
 Bengals+0.022
 [*+0.022
cius+0.022
Neg logit contributions
ASC-0.028
eur-0.024
 Agric-0.024
 Ribbon-0.024
PLA-0.024
Token in
Token ID287
Feature activation+8.25e-01

Pos logit contributions
ASC+0.504
eur+0.439
 Agric+0.437
PLA+0.432
 Ribbon+0.432
Neg logit contributions
anasia-0.488
 vas-0.455
 Bengals-0.442
 [*-0.437
cius-0.429
Token the
Token ID262
Feature activation+7.30e-02

Pos logit contributions
ASC+0.645
eur+0.564
 Agric+0.561
PLA+0.554
 Ribbon+0.554
Neg logit contributions
anasia-0.585
 vas-0.539
 Bengals-0.522
 [*-0.514
cius-0.512
Token presence
Token ID4931
Feature activation-5.61e-01

Pos logit contributions
ASC+0.063
eur+0.056
 Agric+0.056
PLA+0.055
 Ribbon+0.055
Neg logit contributions
anasia-0.045
 vas-0.042
 Bengals-0.040
 [*-0.040
cius-0.039
Token of
Token ID286
Feature activation-1.01e+00

Pos logit contributions
anasia+0.358
 vas+0.330
 Bengals+0.319
 [*+0.315
cius+0.308
Neg logit contributions
ASC-0.475
eur-0.419
 Agric-0.419
 Ribbon-0.414
PLA-0.414
Token a
Token ID257
Feature activation-8.44e-01

Pos logit contributions
anasia+0.685
 vas+0.633
 Bengals+0.613
 [*+0.604
cius+0.596
Neg logit contributions
ASC-0.820
eur-0.721
 Agric-0.719
 Ribbon-0.710
PLA-0.709
Token TSA
Token ID32453
Feature activation-4.07e+00

Pos logit contributions
anasia+0.516
 vas+0.476
 Bengals+0.459
 [*+0.452
cius+0.441
Neg logit contributions
ASC-0.735
eur-0.653
 Agric-0.651
PLA-0.644
 Ribbon-0.644
Token agent
Token ID5797
Feature activation-2.01e+00

Pos logit contributions
anasia+2.205
 vas+2.037
 [*+1.944
 Bengals+1.943
cius+1.832
Neg logit contributions
ASC-3.768
 Agric-3.383
eur-3.354
orate-3.352
PLA-3.343
Token.
Token ID13
Feature activation-1.69e-02

Pos logit contributions
anasia+1.361
 vas+1.263
 Bengals+1.221
 [*+1.213
cius+1.177
Neg logit contributions
ASC-1.612
 Agric-1.417
eur-1.409
PLA-1.403
 Ribbon-1.398
Token Maybe
Token ID6674
Feature activation+2.63e-01

Pos logit contributions
anasia+0.012
 vas+0.011
 Bengals+0.011
cius+0.011
 [*+0.011
Neg logit contributions
ASC-0.013
 Agric-0.012
eur-0.011
 Ribbon-0.011
 Dynam-0.011
Token you
Token ID345
Feature activation+7.30e-01

Pos logit contributions
ASC+0.192
eur+0.167
 Agric+0.166
 Ribbon+0.164
PLA+0.164
Neg logit contributions
anasia-0.199
 vas-0.184
 Bengals-0.179
 [*-0.177
cius-0.175
Token acted
Token ID13134
Feature activation-1.16e+00

Pos logit contributions
ASC+0.579
eur+0.511
 Agric+0.508
 Ribbon+0.501
orate+0.500
Neg logit contributions
anasia-0.504
 vas-0.461
 Bengals-0.449
 [*-0.441
cius-0.437