TOP ACTIVATIONS
MAX = 13.176

} } Catch { Write - Warning - Message " F
. Photo : Justin Sullivan / Getty Images 3
29 questioned in a Reuters / I ps os poll ,
sudo nano / etc / pm / power . d
functionality . sudo mod info - p r t
y atta travelled to Mog adish u to discuss the issue
26 , 2014 . REUTERS / En rique de la Os
28 , 2014 . REUTERS / Michael K lim enty ev
' Forum for the 2013 / 14 Barclays Premier League season
module (' j q depend ency ', [ ]) . direct
wrote : Show nested quote + On
} } Catch { Write - Warning - Message " F
. ( Photo by REUTERS / Car lo Alleg ri )
sudo nano / etc / pm / power .
impl Board { pub fn copy _ board (
of the capital , Mog adish u . They
struct Guard { ... } pub fn pin () -> Guard
- C PS , 2012 2016 )). This comparison is
. ( Photo by REUTERS / Gary Cameron / File photo
mod + x / etc / pm / power . d

MIN ACTIVATIONS
MIN = -11.641

the potential or 3 har v ests a year , unlike
B é nes ( K op i ? á r 41
with all this Al J our g ensen and Ge za
ra , God of Har v ests Hot Soup
no matter how young or adorable the crit ters that Gon
, telecommunications companies were granted retro active immunity for violating the
the remarks caused , K vy at said : " Apparently
this mourn ful , highly distraught dummy might be the closest
pro - lab our , pro - worker , pro -
who was imprisoned after authorities falsely identified him as an illegal
Grant ing retro active immunity to companies that
raids . K hy ber raid Military
s )} 30 . K f 2 { ( 4 s
1 when leading after eight innings . That
chambers in the Mass and Velocity course in under 60 seconds
ating Ev gen y K uz net sov pass , before
I gave the st on ework a light , m
even the millionaire owners and shareholders of Mor neau She pell
, this j à v u isn t
the anti - war , anti - nuclear , peace movement

INTERVAL 6.972 - 13.176
CONTAINS 0.180%

DoS Mit igation No Silver Bullet Due to
living together . The epic ghost invasion of the big Apple
has learned . Reg ulators are apparently interested in
to 75 % of the cost of repairing their sidewalks .
10 of 15 Photo : Erin Bre th auer , The

INTERVAL 0.767 - 6.972
CONTAINS 34.364%

would have ignited . Q : It would have
; what would you give up for your loved ones ?
series of 5 commercials run any old time on Canadian TV
mean for example , I don t know
iked counter - clock wise for the full loop . The

INTERVAL -5.437 - 0.767
CONTAINS 64.622%

is part of the search space . While [
religious studies at the University of Pennsylvania . <|endoftext|> The Trump
in their lives . Teaching your children to sew is a
in Ra ising the Floor ), perhaps $ 600 is paid
McCabe , brings his own political baggage ? With background checks

INTERVAL -11.641 - -5.437
CONTAINS 0.834%

actually keeping your c 6 from getting out of park .
definition with a sometimes st il ted view . I think
303 s )} 35 . ex f 4 { ( 17
. V u ong says ,
She opened up her backup envelope to confirm her memory
Token }
Token ID1782
Feature activation+3.57e+00

Pos logit contributions
river+2.496
 guiActiveUn+2.483
usted+2.366
atorial+2.182
allery+2.181
Neg logit contributions
sters-1.631
NEY-1.586
 Cu-1.573
thouse-1.532
 Colo-1.527
Token }
Token ID1782
Feature activation+3.13e+00

Pos logit contributions
river+2.978
 guiActiveUn+2.948
usted+2.819
atorial+2.576
allery+2.569
Neg logit contributions
sters-2.336
NEY-2.266
 Cu-2.244
thouse-2.212
 Colo-2.194
Token Catch
Token ID25750
Feature activation+3.85e-02

Pos logit contributions
river+2.654
 guiActiveUn+2.629
usted+2.515
atorial+2.300
allery+2.297
Neg logit contributions
sters-2.008
NEY-1.949
 Cu-1.934
thouse-1.899
 Colo-1.888
Token {
Token ID1391
Feature activation+1.74e+00

Pos logit contributions
river+0.030
 guiActiveUn+0.029
usted+0.028
atorial+0.025
allery+0.025
Neg logit contributions
sters-0.028
NEY-0.028
 Cu-0.027
 Colo-0.027
thouse-0.027
Token Write
Token ID19430
Feature activation-7.92e-01

Pos logit contributions
river+1.151
 guiActiveUn+1.148
usted+1.065
allery+0.960
atorial+0.957
Neg logit contributions
sters-1.455
 Cu-1.434
NEY-1.434
 Colo-1.399
thouse-1.384
Token-
Token ID12
Feature activation+1.32e+01

Pos logit contributions
sters+0.493
 Cu+0.482
NEY+0.480
 Colo+0.469
thouse+0.464
Neg logit contributions
river-0.694
 guiActiveUn-0.678
usted-0.657
atorial-0.604
allery-0.593
TokenWarning
Token ID20361
Feature activation+4.30e+00

Pos logit contributions
river+4.502
usted+4.191
 guiActiveUn+3.468
atorial+2.834
ariat+2.505
Neg logit contributions
 Cu-13.770
 redes-13.686
sters-13.542
thouse-13.505
 Colo-13.449
Token -
Token ID532
Feature activation+4.79e+00

Pos logit contributions
river+3.182
 guiActiveUn+3.068
usted+3.005
atorial+2.678
ariat+2.599
Neg logit contributions
sters-3.107
NEY-3.044
thouse-3.015
 Cu-3.008
 Colo-2.976
TokenMessage
Token ID12837
Feature activation+2.25e+00

Pos logit contributions
river+2.964
 guiActiveUn+2.743
usted+2.726
atorial+2.336
ariat+2.243
Neg logit contributions
sters-4.105
 Cu-4.072
thouse-3.982
 Colo-3.981
NEY-3.950
Token "
Token ID366
Feature activation+3.10e+00

Pos logit contributions
river+1.918
 guiActiveUn+1.912
usted+1.810
atorial+1.662
allery+1.661
Neg logit contributions
sters-1.446
NEY-1.414
 Cu-1.414
 Colo-1.373
thouse-1.358
TokenF
Token ID37
Feature activation+6.15e+00

Pos logit contributions
river+2.386
 guiActiveUn+2.366
usted+2.239
atorial+2.026
allery+2.026
Neg logit contributions
sters-2.259
 Cu-2.210
NEY-2.202
 Colo-2.158
thouse-2.134
Token.
Token ID13
Feature activation-8.63e-01

Pos logit contributions
river+1.696
 guiActiveUn+1.694
usted+1.595
allery+1.456
atorial+1.454
Neg logit contributions
sters-1.515
 Cu-1.487
NEY-1.484
 Colo-1.446
thouse-1.429
Token Photo
Token ID5555
Feature activation-4.14e+00

Pos logit contributions
sters+0.500
 Cu+0.490
NEY+0.486
 Colo+0.472
thouse+0.464
Neg logit contributions
river-0.795
 guiActiveUn-0.795
usted-0.753
allery-0.698
atorial-0.697
Token:
Token ID25
Feature activation+5.67e+00

Pos logit contributions
sters+2.372
 Cu+2.330
NEY+2.300
 Colo+2.197
 Dob+2.121
Neg logit contributions
 guiActiveUn-3.885
river-3.781
usted-3.573
atorial-3.365
allery-3.308
Token Justin
Token ID10799
Feature activation+6.18e+00

Pos logit contributions
river+4.767
 guiActiveUn+4.630
usted+4.455
allery+4.109
atorial+4.077
Neg logit contributions
sters-3.572
NEY-3.510
thouse-3.437
 Cu-3.387
 Colo-3.343
Token Sullivan
Token ID18501
Feature activation+3.85e+00

Pos logit contributions
river+3.840
 guiActiveUn+3.659
usted+3.483
allery+3.096
atorial+3.089
Neg logit contributions
sters-5.313
NEY-5.242
thouse-5.075
 Cu-5.020
 Colo-5.004
Token/
Token ID14
Feature activation+1.19e+01

Pos logit contributions
river+3.142
 guiActiveUn+3.095
usted+2.946
allery+2.715
atorial+2.693
Neg logit contributions
sters-2.554
NEY-2.505
 Cu-2.480
thouse-2.430
 Colo-2.406
TokenGetty
Token ID6633
Feature activation+4.25e+00

Pos logit contributions
river+7.102
 guiActiveUn+6.239
usted+6.232
atorial+5.276
allery+5.267
Neg logit contributions
sters-9.827
 Cu-9.671
thouse-9.600
 Canary-9.477
 Colo-9.409
Token Images
Token ID5382
Feature activation+4.98e+00

Pos logit contributions
river+3.167
 guiActiveUn+3.144
usted+2.970
allery+2.713
atorial+2.700
Neg logit contributions
sters-3.141
NEY-3.089
 Cu-3.079
 Colo-3.007
thouse-2.979
Token
Token ID198
Feature activation-1.08e+00

Pos logit contributions
river+4.052
 guiActiveUn+4.019
usted+3.778
allery+3.511
atorial+3.483
Neg logit contributions
sters-3.310
NEY-3.268
 Cu-3.228
thouse-3.171
 Colo-3.155
Token
Token ID198
Feature activation-1.69e+00

Pos logit contributions
sters+0.687
NEY+0.672
 Cu+0.672
 Colo+0.652
thouse+0.646
Neg logit contributions
river-0.926
 guiActiveUn-0.917
usted-0.873
atorial-0.803
allery-0.801
Token3
Token ID18
Feature activation-2.90e-01

Pos logit contributions
sters+1.054
NEY+1.042
 Cu+1.024
 Colo+0.990
Va+0.974
Neg logit contributions
 guiActiveUn-1.494
river-1.470
usted-1.400
allery-1.309
atorial-1.292
Token 29
Token ID2808
Feature activation-7.05e-03

Pos logit contributions
river+0.078
 guiActiveUn+0.076
usted+0.074
atorial+0.068
allery+0.068
Neg logit contributions
sters-0.045
NEY-0.044
 Cu-0.043
 Colo-0.042
thouse-0.041
Token questioned
Token ID11434
Feature activation+1.30e+00

Pos logit contributions
sters+0.005
 Cu+0.005
NEY+0.005
 Colo+0.004
thouse+0.004
Neg logit contributions
river-0.006
 guiActiveUn-0.006
usted-0.005
allery-0.005
atorial-0.005
Token in
Token ID287
Feature activation+1.82e+00

Pos logit contributions
river+1.112
 guiActiveUn+1.106
usted+1.051
atorial+0.965
allery+0.965
Neg logit contributions
sters-0.839
NEY-0.825
 Cu-0.821
 Colo-0.798
thouse-0.790
Token a
Token ID257
Feature activation+1.20e+00

Pos logit contributions
river+1.629
 guiActiveUn+1.612
usted+1.552
atorial+1.428
allery+1.425
Neg logit contributions
sters-1.075
NEY-1.059
 Cu-1.034
thouse-1.017
 Colo-1.011
Token Reuters
Token ID8428
Feature activation+2.13e+00

Pos logit contributions
river+0.960
 guiActiveUn+0.954
usted+0.905
atorial+0.827
allery+0.822
Neg logit contributions
sters-0.831
NEY-0.820
 Cu-0.812
 Colo-0.792
thouse-0.791
Token/
Token ID14
Feature activation+1.17e+01

Pos logit contributions
river+1.752
 guiActiveUn+1.745
usted+1.657
atorial+1.518
allery+1.512
Neg logit contributions
sters-1.420
NEY-1.398
 Cu-1.387
 Colo-1.349
thouse-1.346
TokenI
Token ID40
Feature activation-1.02e+00

Pos logit contributions
river+6.642
usted+6.113
 guiActiveUn+5.814
atorial+5.132
umbn+4.739
Neg logit contributions
thouse-9.784
NEY-9.724
sters-9.606
 Canary-9.421
 Colo-9.397
Tokenps
Token ID862
Feature activation-1.10e+00

Pos logit contributions
sters+0.731
 Cu+0.709
NEY+0.708
 Colo+0.691
thouse+0.677
Neg logit contributions
 guiActiveUn-0.811
river-0.799
usted-0.749
allery-0.709
atorial-0.690
Tokenos
Token ID418
Feature activation-2.36e+00

Pos logit contributions
sters+0.573
 Cu+0.537
NEY+0.515
 Colo+0.500
thouse+0.488
Neg logit contributions
 guiActiveUn-1.123
river-1.096
usted-1.058
allery-0.992
atorial-0.969
Token poll
Token ID3278
Feature activation-1.73e+00

Pos logit contributions
sters+1.718
 Cu+1.688
NEY+1.655
 Colo+1.643
thouse+1.583
Neg logit contributions
 guiActiveUn-1.838
river-1.830
usted-1.702
allery-1.584
atorial-1.540
Token,
Token ID11
Feature activation-1.77e-01

Pos logit contributions
sters+1.107
 Cu+1.075
NEY+1.061
 Colo+1.036
thouse+1.018
Neg logit contributions
 guiActiveUn-1.503
river-1.498
usted-1.411
allery-1.313
atorial-1.299
Token
Token ID198
Feature activation+9.00e-01

Pos logit contributions
river+0.647
 guiActiveUn+0.620
usted+0.606
atorial+0.556
allery+0.538
Neg logit contributions
sters-0.529
NEY-0.520
 Cu-0.517
 Colo-0.507
thouse-0.505
Tokensudo
Token ID24032
Feature activation+6.38e+00

Pos logit contributions
river+0.702
 guiActiveUn+0.698
usted+0.659
allery+0.600
atorial+0.599
Neg logit contributions
sters-0.648
 Cu-0.636
NEY-0.636
 Colo-0.619
thouse-0.613
Token nano
Token ID38706
Feature activation+6.41e+00

Pos logit contributions
river+5.329
 guiActiveUn+5.141
usted+5.041
atorial+4.511
allery+4.450
Neg logit contributions
sters-4.128
NEY-4.063
thouse-3.921
 Cu-3.920
 Colo-3.906
Token /
Token ID1220
Feature activation+7.20e+00

Pos logit contributions
river+4.887
 guiActiveUn+4.793
usted+4.656
allery+4.163
atorial+4.147
Neg logit contributions
sters-4.578
NEY-4.523
thouse-4.351
 Cu-4.344
 Colo-4.338
Tokenetc
Token ID14784
Feature activation+1.08e+01

Pos logit contributions
river+6.000
 guiActiveUn+5.761
usted+5.668
allery+5.125
atorial+5.107
Neg logit contributions
sters-4.607
NEY-4.537
 Colo-4.467
 Cu-4.441
thouse-4.418
Token/
Token ID14
Feature activation+1.17e+01

Pos logit contributions
river+7.190
usted+6.504
 guiActiveUn+6.375
atorial+5.891
ariat+5.637
Neg logit contributions
 Colo-8.088
NEY-8.072
sters-8.053
thouse-7.935
 Cu-7.857
Tokenpm
Token ID4426
Feature activation+4.04e+00

Pos logit contributions
river+8.565
usted+8.041
 guiActiveUn+7.664
atorial+6.886
allery+6.882
Neg logit contributions
 Colo-8.386
NEY-8.334
sters-8.233
 Cu-8.214
thouse-7.904
Token/
Token ID14
Feature activation+5.80e+00

Pos logit contributions
river+3.275
 guiActiveUn+3.109
usted+3.064
atorial+2.773
allery+2.736
Neg logit contributions
NEY-2.749
sters-2.713
 Colo-2.692
 Cu-2.686
thouse-2.627
Tokenpower
Token ID6477
Feature activation+3.19e+00

Pos logit contributions
river+4.861
 guiActiveUn+4.664
usted+4.576
allery+4.107
atorial+4.097
Neg logit contributions
sters-3.781
NEY-3.781
 Cu-3.737
 Colo-3.726
thouse-3.604
Token.
Token ID13
Feature activation+9.56e-01

Pos logit contributions
river+2.534
 guiActiveUn+2.531
usted+2.382
allery+2.179
atorial+2.176
Neg logit contributions
sters-2.245
 Cu-2.201
NEY-2.197
 Colo-2.138
thouse-2.115
Tokend
Token ID67
Feature activation+3.39e+00

Pos logit contributions
 guiActiveUn+0.695
river+0.691
usted+0.646
allery+0.587
atorial+0.586
Neg logit contributions
sters-0.741
 Cu-0.727
NEY-0.723
 Colo-0.707
thouse-0.700
Token functionality
Token ID11244
Feature activation+1.14e+00

Pos logit contributions
sters+1.935
 Cu+1.900
NEY+1.865
 Colo+1.803
thouse+1.766
Neg logit contributions
 guiActiveUn-3.176
river-3.138
usted-2.996
atorial-2.784
allery-2.780
Token.
Token ID13
Feature activation+1.00e-01

Pos logit contributions
river+0.960
 guiActiveUn+0.955
usted+0.904
allery+0.831
atorial+0.829
Neg logit contributions
sters-0.755
NEY-0.740
 Cu-0.737
 Colo-0.717
thouse-0.710
Token
Token ID198
Feature activation-2.78e-01

Pos logit contributions
river+0.088
 guiActiveUn+0.087
usted+0.083
allery+0.076
atorial+0.076
Neg logit contributions
sters-0.063
 Cu-0.061
NEY-0.061
 Colo-0.059
thouse-0.058
Token
Token ID198
Feature activation+1.19e-02

Pos logit contributions
sters+0.182
NEY+0.179
 Cu+0.178
 Colo+0.174
thouse+0.173
Neg logit contributions
river-0.234
 guiActiveUn-0.228
usted-0.220
atorial-0.202
allery-0.198
Tokensudo
Token ID24032
Feature activation+6.15e+00

Pos logit contributions
 guiActiveUn+0.010
river+0.010
usted+0.009
allery+0.009
atorial+0.009
Neg logit contributions
sters-0.008
NEY-0.008
 Cu-0.008
 Colo-0.007
thouse-0.007
Token mod
Token ID953
Feature activation+1.14e+01

Pos logit contributions
river+5.164
 guiActiveUn+5.032
usted+4.873
atorial+4.370
allery+4.327
Neg logit contributions
sters-3.964
NEY-3.928
 Cu-3.793
thouse-3.781
 Colo-3.776
Tokeninfo
Token ID10951
Feature activation+4.57e+00

Pos logit contributions
river+10.609
 guiActiveUn+9.966
usted+9.760
alsh+8.766
atorial+8.625
Neg logit contributions
sters-5.940
NEY-5.923
 Colo-5.914
 Cu-5.812
 Tud-5.672
Token -
Token ID532
Feature activation+1.81e+00

Pos logit contributions
river+3.823
 guiActiveUn+3.775
usted+3.595
allery+3.253
atorial+3.214
Neg logit contributions
sters-3.047
NEY-2.987
 Cu-2.942
 Colo-2.880
thouse-2.874
Tokenp
Token ID79
Feature activation+3.06e+00

Pos logit contributions
river+1.442
 guiActiveUn+1.426
usted+1.352
allery+1.231
atorial+1.230
Neg logit contributions
sters-1.273
NEY-1.249
 Cu-1.245
 Colo-1.215
thouse-1.199
Token r
Token ID374
Feature activation+4.57e+00

Pos logit contributions
river+2.690
 guiActiveUn+2.650
usted+2.546
allery+2.313
atorial+2.312
Neg logit contributions
sters-1.897
NEY-1.858
 Cu-1.844
 Colo-1.802
thouse-1.787
Tokent
Token ID83
Feature activation+4.07e-01

Pos logit contributions
river+3.720
 guiActiveUn+3.642
usted+3.510
allery+3.157
atorial+3.152
Neg logit contributions
sters-3.126
NEY-3.100
 Cu-3.078
 Colo-3.028
thouse-2.919
Tokeny
Token ID88
Feature activation-2.24e+00

Pos logit contributions
sters+1.710
 Cu+1.669
NEY+1.667
 Colo+1.603
thouse+1.596
Neg logit contributions
 guiActiveUn-2.443
river-2.426
usted-2.294
allery-2.136
atorial-2.116
Tokenatta
Token ID25014
Feature activation+1.12e+00

Pos logit contributions
sters+2.223
 Cu+2.190
NEY+2.189
 Colo+2.138
thouse+2.135
Neg logit contributions
 guiActiveUn-1.134
river-1.125
usted-1.016
allery-0.879
atorial-0.870
Token travelled
Token ID21650
Feature activation-1.21e+00

Pos logit contributions
river+0.949
 guiActiveUn+0.943
usted+0.898
atorial+0.823
allery+0.820
Neg logit contributions
sters-0.726
NEY-0.714
 Cu-0.709
 Colo-0.690
thouse-0.686
Token to
Token ID284
Feature activation+3.73e-01

Pos logit contributions
sters+0.839
 Cu+0.825
NEY+0.818
 Colo+0.798
thouse+0.786
Neg logit contributions
 guiActiveUn-0.976
river-0.969
usted-0.917
allery-0.843
atorial-0.839
Token Mog
Token ID30926
Feature activation+8.04e+00

Pos logit contributions
river+0.343
 guiActiveUn+0.342
usted+0.325
allery+0.301
atorial+0.301
Neg logit contributions
sters-0.216
NEY-0.210
 Cu-0.210
 Colo-0.203
thouse-0.201
Tokenadish
Token ID48563
Feature activation+1.14e+01

Pos logit contributions
river+4.544
usted+4.294
 guiActiveUn+4.280
atorial+3.758
allery+3.693
Neg logit contributions
NEY-7.349
sters-7.231
 Colo-7.225
 Cu-7.071
thouse-6.972
Tokenu
Token ID84
Feature activation+5.64e+00

Pos logit contributions
river+6.068
usted+5.503
 guiActiveUn+5.437
allery+4.721
atorial+4.637
Neg logit contributions
 Colo-10.076
sters-10.042
NEY-10.003
 Cu-9.936
thouse-9.746
Token to
Token ID284
Feature activation+5.27e+00

Pos logit contributions
river+4.379
 guiActiveUn+4.332
usted+4.053
atorial+3.691
allery+3.677
Neg logit contributions
sters-4.013
NEY-3.965
 Cu-3.923
 Colo-3.843
thouse-3.817
Token discuss
Token ID2112
Feature activation-1.22e+00

Pos logit contributions
river+3.980
 guiActiveUn+3.930
usted+3.775
atorial+3.413
allery+3.366
Neg logit contributions
sters-3.765
NEY-3.723
thouse-3.633
 Cu-3.618
 Colo-3.543
Token the
Token ID262
Feature activation+5.49e-01

Pos logit contributions
sters+0.723
 Cu+0.712
NEY+0.702
 Colo+0.683
thouse+0.669
Neg logit contributions
 guiActiveUn-1.104
river-1.101
usted-1.045
allery-0.970
atorial-0.963
Token issue
Token ID2071
Feature activation-1.42e+00

Pos logit contributions
river+0.485
 guiActiveUn+0.483
usted+0.458
allery+0.423
atorial+0.423
Neg logit contributions
sters-0.338
NEY-0.331
 Cu-0.329
 Colo-0.319
thouse-0.317
Token 26
Token ID2608
Feature activation-1.90e+00

Pos logit contributions
river+0.061
 guiActiveUn+0.060
usted+0.058
atorial+0.054
allery+0.053
Neg logit contributions
sters-0.033
NEY-0.032
 Cu-0.032
thouse-0.031
 Colo-0.031
Token,
Token ID11
Feature activation-1.56e+00

Pos logit contributions
sters+1.267
 Cu+1.244
NEY+1.239
 Colo+1.203
thouse+1.187
Neg logit contributions
 guiActiveUn-1.589
river-1.582
usted-1.495
allery-1.379
atorial-1.371
Token 2014
Token ID1946
Feature activation+1.79e+00

Pos logit contributions
sters+1.240
 Cu+1.230
NEY+1.220
 Colo+1.196
thouse+1.173
Neg logit contributions
 guiActiveUn-1.099
river-1.092
usted-1.018
allery-0.925
atorial-0.914
Token.
Token ID13
Feature activation-3.09e-02

Pos logit contributions
river+1.376
 guiActiveUn+1.343
usted+1.280
atorial+1.166
allery+1.158
Neg logit contributions
sters-1.306
NEY-1.289
 Cu-1.281
 Colo-1.249
thouse-1.241
Token REUTERS
Token ID15862
Feature activation+6.70e+00

Pos logit contributions
sters+0.026
 Cu+0.026
NEY+0.026
 Colo+0.025
thouse+0.025
Neg logit contributions
 guiActiveUn-0.020
river-0.020
usted-0.019
allery-0.017
atorial-0.016
Token/
Token ID14
Feature activation+1.11e+01

Pos logit contributions
river+4.842
usted+4.414
 guiActiveUn+4.173
atorial+4.029
ariat+3.889
Neg logit contributions
sters-4.800
NEY-4.711
thouse-4.667
 Colo-4.636
 Cu-4.609
TokenEn
Token ID4834
Feature activation+3.23e+00

Pos logit contributions
river+8.465
usted+7.970
 guiActiveUn+7.954
atorial+7.180
allery+6.862
Neg logit contributions
sters-7.128
 Cu-6.853
 Colo-6.809
NEY-6.794
thouse-6.764
Tokenrique
Token ID33865
Feature activation+5.87e+00

Pos logit contributions
river+0.990
 guiActiveUn+0.810
usted+0.797
atorial+0.624
allery+0.498
Neg logit contributions
sters-3.848
NEY-3.786
 Cu-3.729
 Colo-3.709
 Wink-3.634
Token de
Token ID390
Feature activation+2.34e-01

Pos logit contributions
 guiActiveUn+5.350
river+5.331
usted+5.165
allery+4.759
atorial+4.715
Neg logit contributions
sters-3.079
thouse-2.991
NEY-2.988
Va-2.687
riad-2.658
Token la
Token ID8591
Feature activation-3.61e+00

Pos logit contributions
river+0.213
 guiActiveUn+0.212
usted+0.203
allery+0.188
atorial+0.185
Neg logit contributions
sters-0.136
NEY-0.132
 Cu-0.129
thouse-0.128
 Colo-0.125
Token Os
Token ID8834
Feature activation-3.52e+00

Pos logit contributions
sters+2.400
 Cu+2.384
NEY+2.329
 Colo+2.294
thouse+2.230
Neg logit contributions
 guiActiveUn-3.017
river-3.005
usted-2.835
allery-2.629
atorial-2.623
Token 28
Token ID2579
Feature activation-2.10e+00

Pos logit contributions
sters+0.400
NEY+0.391
 Cu+0.388
 Colo+0.374
thouse+0.372
Neg logit contributions
river-0.785
 guiActiveUn-0.775
usted-0.746
atorial-0.694
allery-0.691
Token,
Token ID11
Feature activation-2.90e+00

Pos logit contributions
sters+1.388
 Cu+1.364
NEY+1.358
 Colo+1.318
thouse+1.299
Neg logit contributions
 guiActiveUn-1.774
river-1.762
usted-1.668
allery-1.540
atorial-1.533
Token 2014
Token ID1946
Feature activation+3.06e+00

Pos logit contributions
sters+2.301
 Cu+2.288
NEY+2.264
 Colo+2.212
 Dob+2.161
Neg logit contributions
 guiActiveUn-2.051
river-2.025
usted-1.879
allery-1.727
atorial-1.688
Token.
Token ID13
Feature activation-8.50e-01

Pos logit contributions
river+2.320
 guiActiveUn+2.262
usted+2.154
atorial+1.963
allery+1.951
Neg logit contributions
sters-2.253
NEY-2.230
 Cu-2.215
 Colo-2.162
thouse-2.144
Token REUTERS
Token ID15862
Feature activation+6.73e+00

Pos logit contributions
sters+0.717
 Cu+0.706
NEY+0.703
 Colo+0.686
thouse+0.677
Neg logit contributions
 guiActiveUn-0.563
river-0.559
usted-0.520
allery-0.465
atorial-0.461
Token/
Token ID14
Feature activation+1.11e+01

Pos logit contributions
river+4.921
usted+4.521
 guiActiveUn+4.379
atorial+4.118
allery+4.030
Neg logit contributions
sters-4.814
NEY-4.685
thouse-4.656
 Cu-4.624
 Colo-4.622
TokenMichael
Token ID13256
Feature activation+2.94e+00

Pos logit contributions
river+7.775
 guiActiveUn+7.153
usted+7.128
atorial+6.404
allery+6.138
Neg logit contributions
 Cu-7.765
sters-7.708
NEY-7.635
thouse-7.619
 Colo-7.606
Token K
Token ID509
Feature activation-2.55e-01

Pos logit contributions
river+2.296
 guiActiveUn+2.259
usted+2.178
allery+2.005
atorial+1.973
Neg logit contributions
sters-2.089
NEY-2.039
 Cu-1.991
thouse-1.969
 Colo-1.959
Tokenlim
Token ID2475
Feature activation-2.57e+00

Pos logit contributions
sters+0.181
 Cu+0.177
NEY+0.177
 Colo+0.172
thouse+0.170
Neg logit contributions
river-0.202
 guiActiveUn-0.202
usted-0.190
allery-0.173
atorial-0.173
Tokenenty
Token ID3787
Feature activation+2.20e+00

Pos logit contributions
sters+2.140
 Cu+2.052
NEY+2.024
thouse+1.991
 Colo+1.975
Neg logit contributions
river-1.762
 guiActiveUn-1.759
usted-1.613
allery-1.458
atorial-1.430
Tokenev
Token ID1990
Feature activation+2.94e-02

Pos logit contributions
river+1.467
 guiActiveUn+1.412
usted+1.348
atorial+1.210
allery+1.199
Neg logit contributions
NEY-1.810
sters-1.808
 Cu-1.771
thouse-1.764
 Colo-1.759
Token'
Token ID6
Feature activation+1.83e+00

Pos logit contributions
sters+2.089
 Cu+2.059
NEY+2.022
 Colo+1.963
thouse+1.926
Neg logit contributions
 guiActiveUn-3.802
river-3.768
usted-3.584
allery-3.333
atorial-3.318
Token Forum
Token ID14867
Feature activation+1.86e+00

Pos logit contributions
river+1.510
 guiActiveUn+1.484
usted+1.428
atorial+1.328
allery+1.323
Neg logit contributions
sters-1.213
NEY-1.199
 Cu-1.161
 Colo-1.137
thouse-1.137
Token for
Token ID329
Feature activation+2.53e+00

Pos logit contributions
river+1.621
 guiActiveUn+1.610
usted+1.531
allery+1.413
atorial+1.411
Neg logit contributions
sters-1.164
NEY-1.140
 Cu-1.136
 Colo-1.103
thouse-1.090
Token the
Token ID262
Feature activation+3.66e+00

Pos logit contributions
river+2.420
 guiActiveUn+2.408
usted+2.297
allery+2.131
atorial+2.128
Neg logit contributions
sters-1.360
NEY-1.328
 Cu-1.318
 Colo-1.276
thouse-1.264
Token 2013
Token ID2211
Feature activation+6.53e+00

Pos logit contributions
river+2.607
 guiActiveUn+2.598
usted+2.443
atorial+2.208
allery+2.204
Neg logit contributions
sters-2.836
NEY-2.792
 Cu-2.776
 Colo-2.720
thouse-2.692
Token/
Token ID14
Feature activation+1.10e+01

Pos logit contributions
river+4.714
 guiActiveUn+4.417
usted+4.366
atorial+4.010
allery+3.870
Neg logit contributions
sters-4.656
NEY-4.651
thouse-4.623
 Cu-4.526
 Colo-4.506
Token14
Token ID1415
Feature activation+9.46e+00

Pos logit contributions
river+5.090
usted+4.618
 guiActiveUn+4.406
atorial+3.880
ariat+3.719
Neg logit contributions
 redes-10.433
 Cu-10.339
sters-10.298
 Colo-10.178
thouse-10.168
Token Barclays
Token ID37985
Feature activation+4.30e+00

Pos logit contributions
river+4.981
 guiActiveUn+4.889
usted+4.466
atorial+4.012
allery+3.904
Neg logit contributions
sters-8.709
NEY-8.531
 Cu-8.444
 Colo-8.391
thouse-8.373
Token Premier
Token ID9952
Feature activation+3.45e+00

Pos logit contributions
river+3.760
 guiActiveUn+3.695
usted+3.498
atorial+3.269
allery+3.227
Neg logit contributions
sters-2.639
NEY-2.549
 Cu-2.511
thouse-2.498
 Colo-2.467
Token League
Token ID4041
Feature activation+4.04e+00

Pos logit contributions
river+2.936
 guiActiveUn+2.735
usted+2.687
atorial+2.416
allery+2.405
Neg logit contributions
sters-2.215
NEY-2.170
thouse-2.087
 Cu-2.073
 Colo-2.063
Token season
Token ID1622
Feature activation+5.14e+00

Pos logit contributions
river+2.357
 guiActiveUn+2.324
usted+2.128
atorial+1.901
allery+1.888
Neg logit contributions
sters-3.661
NEY-3.588
 Cu-3.579
 Colo-3.524
thouse-3.508
Tokenmodule
Token ID21412
Feature activation+7.17e+00

Pos logit contributions
river+4.230
 guiActiveUn+4.071
usted+3.947
allery+3.547
atorial+3.502
Neg logit contributions
sters-4.247
NEY-4.167
 Cu-4.154
 Colo-4.063
thouse-4.029
Token('
Token ID10786
Feature activation+3.53e+00

Pos logit contributions
river+6.516
 guiActiveUn+6.325
usted+6.127
allery+5.635
atorial+5.489
Neg logit contributions
sters-4.018
 Cu-3.784
thouse-3.773
 Colo-3.736
NEY-3.718
Tokenj
Token ID73
Feature activation+2.14e+00

Pos logit contributions
river+2.992
 guiActiveUn+2.924
usted+2.805
allery+2.566
atorial+2.562
Neg logit contributions
sters-2.304
 Cu-2.261
NEY-2.261
 Colo-2.212
thouse-2.173
Tokenq
Token ID80
Feature activation+4.07e+00

Pos logit contributions
river+1.597
 guiActiveUn+1.574
usted+1.492
allery+1.353
atorial+1.352
Neg logit contributions
sters-1.610
NEY-1.586
 Cu-1.585
 Colo-1.548
thouse-1.526
Tokendepend
Token ID45841
Feature activation+9.77e+00

Pos logit contributions
river+3.550
 guiActiveUn+3.489
usted+3.333
allery+3.067
atorial+3.059
Neg logit contributions
sters-2.556
 Cu-2.507
NEY-2.495
 Colo-2.443
thouse-2.394
Tokenency
Token ID1387
Feature activation+1.10e+01

Pos logit contributions
river+7.387
 guiActiveUn+6.822
usted+6.739
allery+6.114
atorial+6.079
Neg logit contributions
sters-6.848
 Cu-6.767
 Colo-6.752
NEY-6.703
Va-6.598
Token',
Token ID3256
Feature activation+6.04e+00

Pos logit contributions
river+8.659
 guiActiveUn+8.156
usted+8.028
allery+7.228
atorial+7.023
Neg logit contributions
sters-7.225
NEY-7.025
 Cu-6.984
 Colo-6.977
thouse-6.839
Token [
Token ID685
Feature activation+3.26e+00

Pos logit contributions
river+5.261
 guiActiveUn+5.169
usted+4.959
allery+4.518
atorial+4.494
Neg logit contributions
sters-3.572
NEY-3.554
thouse-3.452
 Cu-3.443
 Colo-3.357
Token])
Token ID12962
Feature activation+3.12e+00

Pos logit contributions
river+2.956
 guiActiveUn+2.925
usted+2.806
allery+2.573
atorial+2.565
Neg logit contributions
sters-1.909
NEY-1.872
 Cu-1.867
 Colo-1.814
thouse-1.799
Token.
Token ID764
Feature activation+2.20e+00

Pos logit contributions
river+2.423
 guiActiveUn+2.405
usted+2.283
allery+2.067
atorial+2.057
Neg logit contributions
sters-2.243
NEY-2.187
 Cu-2.166
thouse-2.125
 Colo-2.120
Tokendirect
Token ID12942
Feature activation+1.44e+00

Pos logit contributions
river+1.764
 guiActiveUn+1.750
usted+1.664
allery+1.516
atorial+1.509
Neg logit contributions
sters-1.533
NEY-1.505
 Cu-1.502
 Colo-1.463
thouse-1.450
Token wrote
Token ID2630
Feature activation-1.74e+00

Pos logit contributions
 guiActiveUn+0.986
river+0.985
usted+0.933
allery+0.869
atorial+0.866
Neg logit contributions
sters-0.623
 Cu-0.609
NEY-0.609
 Colo-0.586
thouse-0.578
Token:
Token ID25
Feature activation+1.45e+00

Pos logit contributions
sters+1.000
NEY+0.978
 Cu+0.977
 Colo+0.944
thouse+0.933
Neg logit contributions
river-1.614
 guiActiveUn-1.600
usted-1.528
atorial-1.415
allery-1.409
Token
Token ID198
Feature activation+5.49e-01

Pos logit contributions
river+1.191
 guiActiveUn+1.135
usted+1.112
atorial+1.016
allery+0.992
Neg logit contributions
sters-0.974
NEY-0.960
 Cu-0.952
 Colo-0.932
thouse-0.928
Token
Token ID198
Feature activation+1.94e-01

Pos logit contributions
river+0.455
 guiActiveUn+0.435
usted+0.424
atorial+0.390
allery+0.380
Neg logit contributions
sters-0.367
NEY-0.361
 Cu-0.357
 Colo-0.351
thouse-0.350
TokenShow
Token ID15307
Feature activation+3.68e+00

Pos logit contributions
 guiActiveUn+0.171
river+0.169
usted+0.161
allery+0.149
atorial+0.149
Neg logit contributions
sters-0.121
NEY-0.118
 Cu-0.118
 Colo-0.114
thouse-0.113
Token nested
Token ID28376
Feature activation+1.09e+01

Pos logit contributions
river+3.142
 guiActiveUn+3.125
usted+3.046
atorial+2.810
allery+2.769
Neg logit contributions
NEY-2.299
sters-2.291
 Cu-2.185
 Colo-2.149
thouse-2.106
Token quote
Token ID9577
Feature activation+2.51e+00

Pos logit contributions
river+6.093
 guiActiveUn+6.065
usted+5.736
atorial+5.097
allery+4.713
Neg logit contributions
NEY-9.621
 Colo-9.075
sters-8.977
 Dob-8.887
 Cu-8.870
Token +
Token ID1343
Feature activation+1.17e+00

Pos logit contributions
river+2.060
 guiActiveUn+2.028
usted+1.946
atorial+1.786
allery+1.753
Neg logit contributions
NEY-1.695
sters-1.660
 Cu-1.629
 Colo-1.602
thouse-1.597
Token
Token ID198
Feature activation+1.99e+00

Pos logit contributions
river+0.977
 guiActiveUn+0.957
usted+0.918
atorial+0.844
allery+0.829
Neg logit contributions
sters-0.782
NEY-0.762
 Cu-0.759
 Colo-0.741
thouse-0.738
Token
Token ID198
Feature activation+2.17e+00

Pos logit contributions
river+1.595
 guiActiveUn+1.504
usted+1.482
atorial+1.358
allery+1.304
Neg logit contributions
sters-1.368
NEY-1.349
 Cu-1.327
thouse-1.317
 Colo-1.311
TokenOn
Token ID2202
Feature activation-4.50e-01

Pos logit contributions
 guiActiveUn+1.736
river+1.734
usted+1.635
allery+1.499
atorial+1.493
Neg logit contributions
sters-1.512
 Cu-1.484
NEY-1.482
 Colo-1.438
thouse-1.424
Token }
Token ID1782
Feature activation+4.32e-01

Pos logit contributions
sters+1.171
 Cu+1.164
NEY+1.157
 Colo+1.126
thouse+1.101
Neg logit contributions
 guiActiveUn-1.424
river-1.419
usted-1.338
atorial-1.228
allery-1.228
Token }
Token ID1782
Feature activation+8.55e-01

Pos logit contributions
river+0.359
 guiActiveUn+0.358
usted+0.338
allery+0.311
atorial+0.310
Neg logit contributions
sters-0.288
 Cu-0.283
NEY-0.283
 Colo-0.274
thouse-0.271
Token Catch
Token ID25750
Feature activation-1.39e+00

Pos logit contributions
river+0.728
 guiActiveUn+0.725
usted+0.687
allery+0.632
atorial+0.631
Neg logit contributions
sters-0.554
NEY-0.541
 Cu-0.540
 Colo-0.524
thouse-0.520
Token {
Token ID1391
Feature activation+4.91e-01

Pos logit contributions
sters+0.900
 Cu+0.885
NEY+0.884
 Colo+0.856
thouse+0.845
Neg logit contributions
river-1.178
 guiActiveUn-1.177
usted-1.108
allery-1.027
atorial-1.022
Token Write
Token ID19430
Feature activation-1.22e+00

Pos logit contributions
river+0.366
 guiActiveUn+0.366
usted+0.342
allery+0.313
atorial+0.312
Neg logit contributions
sters-0.370
 Cu-0.365
NEY-0.364
 Colo-0.354
thouse-0.349
Token-
Token ID12
Feature activation+1.09e+01

Pos logit contributions
sters+0.740
 Cu+0.723
NEY+0.721
 Colo+0.701
thouse+0.693
Neg logit contributions
river-1.084
 guiActiveUn-1.072
usted-1.027
atorial-0.946
allery-0.938
TokenWarning
Token ID20361
Feature activation+3.66e+00

Pos logit contributions
river+6.923
 guiActiveUn+6.578
usted+6.577
atorial+5.603
ariat+5.245
Neg logit contributions
 Cu-8.683
sters-8.638
thouse-8.455
 Colo-8.446
NEY-8.380
Token -
Token ID532
Feature activation+4.45e+00

Pos logit contributions
 guiActiveUn+3.111
river+3.107
usted+2.942
atorial+2.691
allery+2.689
Neg logit contributions
sters-2.364
 Cu-2.312
NEY-2.311
 Colo-2.243
thouse-2.225
TokenMessage
Token ID12837
Feature activation+2.48e+00

Pos logit contributions
river+2.862
 guiActiveUn+2.712
usted+2.647
atorial+2.285
ariat+2.186
Neg logit contributions
sters-3.745
 Cu-3.697
NEY-3.616
thouse-3.606
 Colo-3.605
Token "
Token ID366
Feature activation+3.48e+00

Pos logit contributions
river+2.160
 guiActiveUn+2.152
usted+2.040
allery+1.886
atorial+1.881
Neg logit contributions
sters-1.554
 Cu-1.522
NEY-1.519
 Colo-1.472
thouse-1.452
TokenF
Token ID37
Feature activation+4.52e+00

Pos logit contributions
river+2.774
 guiActiveUn+2.721
usted+2.600
atorial+2.347
allery+2.342
Neg logit contributions
sters-2.443
 Cu-2.387
NEY-2.364
 Colo-2.340
thouse-2.304
Token.
Token ID13
Feature activation-2.19e+00

Pos logit contributions
sters+0.134
NEY+0.131
 Cu+0.130
 Colo+0.127
thouse+0.126
Neg logit contributions
river-0.166
 guiActiveUn-0.165
usted-0.157
atorial-0.144
allery-0.144
Token (
Token ID357
Feature activation-4.19e+00

Pos logit contributions
sters+1.248
 Cu+1.231
NEY+1.219
 Colo+1.183
thouse+1.156
Neg logit contributions
 guiActiveUn-2.043
river-2.041
usted-1.934
allery-1.800
atorial-1.790
TokenPhoto
Token ID6191
Feature activation-5.39e+00

Pos logit contributions
sters+2.367
NEY+2.358
 Cu+2.314
 Colo+2.232
Va+2.203
Neg logit contributions
 guiActiveUn-3.908
river-3.849
usted-3.646
allery-3.417
atorial-3.397
Token by
Token ID416
Feature activation+5.05e+00

Pos logit contributions
 Cu+3.144
sters+3.123
NEY+3.087
 Colo+2.939
 Dob+2.872
Neg logit contributions
 guiActiveUn-4.869
river-4.808
usted-4.513
atorial-4.228
allery-4.209
Token REUTERS
Token ID15862
Feature activation+5.61e+00

Pos logit contributions
river+4.204
 guiActiveUn+4.128
usted+3.957
allery+3.647
atorial+3.639
Neg logit contributions
sters-3.233
NEY-3.179
thouse-3.107
 Cu-3.086
 Colo-3.035
Token/
Token ID14
Feature activation+1.09e+01

Pos logit contributions
river+4.169
usted+3.794
 guiActiveUn+3.772
atorial+3.502
allery+3.356
Neg logit contributions
sters-3.963
NEY-3.885
thouse-3.844
 Colo-3.796
 Cu-3.791
TokenCar
Token ID9914
Feature activation+1.69e+00

Pos logit contributions
river+7.868
usted+7.290
 guiActiveUn+7.019
atorial+6.487
allery+6.284
Neg logit contributions
sters-7.498
thouse-7.304
 Cu-7.147
NEY-7.144
 Colo-7.030
Tokenlo
Token ID5439
Feature activation-1.16e+00

Pos logit contributions
river+1.723
 guiActiveUn+1.699
usted+1.645
atorial+1.527
allery+1.519
Neg logit contributions
sters-0.810
 Cu-0.780
NEY-0.778
 Colo-0.762
thouse-0.738
Token Alleg
Token ID26326
Feature activation+3.21e-01

Pos logit contributions
sters+0.783
 Cu+0.771
NEY+0.765
 Colo+0.746
thouse+0.734
Neg logit contributions
 guiActiveUn-0.956
river-0.955
usted-0.899
allery-0.828
atorial-0.826
Tokenri
Token ID380
Feature activation+3.13e+00

Pos logit contributions
river+0.239
 guiActiveUn+0.234
usted+0.223
atorial+0.201
allery+0.200
Neg logit contributions
sters-0.244
NEY-0.242
 Cu-0.240
 Colo-0.235
thouse-0.233
Token)
Token ID8
Feature activation+1.55e-01

Pos logit contributions
river+2.498
 guiActiveUn+2.481
usted+2.343
atorial+2.150
allery+2.143
Neg logit contributions
sters-2.168
NEY-2.122
 Cu-2.106
thouse-2.054
 Colo-2.051
Token
Token ID198
Feature activation+7.87e-01

Pos logit contributions
river+0.853
 guiActiveUn+0.849
usted+0.807
atorial+0.743
allery+0.742
Neg logit contributions
sters-0.607
NEY-0.593
 Cu-0.590
 Colo-0.573
thouse-0.569
Token
Token ID198
Feature activation+9.00e-01

Pos logit contributions
river+0.647
 guiActiveUn+0.620
usted+0.606
atorial+0.556
allery+0.538
Neg logit contributions
sters-0.529
NEY-0.520
 Cu-0.517
 Colo-0.507
thouse-0.505
Tokensudo
Token ID24032
Feature activation+6.38e+00

Pos logit contributions
river+0.702
 guiActiveUn+0.698
usted+0.659
allery+0.600
atorial+0.599
Neg logit contributions
sters-0.648
 Cu-0.636
NEY-0.636
 Colo-0.619
thouse-0.613
Token nano
Token ID38706
Feature activation+6.41e+00

Pos logit contributions
river+5.329
 guiActiveUn+5.141
usted+5.041
atorial+4.511
allery+4.450
Neg logit contributions
sters-4.128
NEY-4.063
thouse-3.921
 Cu-3.920
 Colo-3.906
Token /
Token ID1220
Feature activation+7.20e+00

Pos logit contributions
river+4.887
 guiActiveUn+4.793
usted+4.656
allery+4.163
atorial+4.147
Neg logit contributions
sters-4.578
NEY-4.523
thouse-4.351
 Cu-4.344
 Colo-4.338
Tokenetc
Token ID14784
Feature activation+1.08e+01

Pos logit contributions
river+6.000
 guiActiveUn+5.761
usted+5.668
allery+5.125
atorial+5.107
Neg logit contributions
sters-4.607
NEY-4.537
 Colo-4.467
 Cu-4.441
thouse-4.418
Token/
Token ID14
Feature activation+1.17e+01

Pos logit contributions
river+7.190
usted+6.504
 guiActiveUn+6.375
atorial+5.891
ariat+5.637
Neg logit contributions
 Colo-8.088
NEY-8.072
sters-8.053
thouse-7.935
 Cu-7.857
Tokenpm
Token ID4426
Feature activation+4.04e+00

Pos logit contributions
river+8.565
usted+8.041
 guiActiveUn+7.664
atorial+6.886
allery+6.882
Neg logit contributions
 Colo-8.386
NEY-8.334
sters-8.233
 Cu-8.214
thouse-7.904
Token/
Token ID14
Feature activation+5.80e+00

Pos logit contributions
river+3.275
 guiActiveUn+3.109
usted+3.064
atorial+2.773
allery+2.736
Neg logit contributions
NEY-2.749
sters-2.713
 Colo-2.692
 Cu-2.686
thouse-2.627
Tokenpower
Token ID6477
Feature activation+3.19e+00

Pos logit contributions
river+4.861
 guiActiveUn+4.664
usted+4.576
allery+4.107
atorial+4.097
Neg logit contributions
sters-3.781
NEY-3.781
 Cu-3.737
 Colo-3.726
thouse-3.604
Token.
Token ID13
Feature activation+9.56e-01

Pos logit contributions
river+2.534
 guiActiveUn+2.531
usted+2.382
allery+2.179
atorial+2.176
Neg logit contributions
sters-2.245
 Cu-2.201
NEY-2.197
 Colo-2.138
thouse-2.115
Token
Token ID198
Feature activation+3.92e-01

Pos logit contributions
sters+0.776
 Cu+0.764
NEY+0.758
 Colo+0.737
thouse+0.718
Neg logit contributions
 guiActiveUn-1.149
river-1.147
usted-1.085
allery-1.008
atorial-1.003
Token
Token ID198
Feature activation+2.94e-02

Pos logit contributions
river+0.324
 guiActiveUn+0.310
usted+0.303
atorial+0.277
allery+0.270
Neg logit contributions
sters-0.262
NEY-0.258
 Cu-0.257
 Colo-0.252
thouse-0.251
Tokenimpl
Token ID23928
Feature activation+4.87e+00

Pos logit contributions
 guiActiveUn+0.025
river+0.025
usted+0.024
allery+0.022
atorial+0.022
Neg logit contributions
sters-0.019
NEY-0.018
 Cu-0.018
 Colo-0.018
thouse-0.018
Token Board
Token ID5926
Feature activation-8.73e-01

Pos logit contributions
river+4.009
 guiActiveUn+3.930
usted+3.796
atorial+3.476
allery+3.414
Neg logit contributions
sters-3.185
NEY-3.171
 Cu-3.086
thouse-3.055
 Colo-2.995
Token {
Token ID1391
Feature activation+1.52e+00

Pos logit contributions
sters+0.589
 Cu+0.578
NEY+0.575
 Colo+0.561
thouse+0.552
Neg logit contributions
 guiActiveUn-0.719
river-0.719
usted-0.677
allery-0.623
atorial-0.622
Token pub
Token ID2240
Feature activation+1.08e+01

Pos logit contributions
river+1.243
 guiActiveUn+1.238
usted+1.170
allery+1.073
atorial+1.071
Neg logit contributions
sters-1.038
NEY-1.018
 Cu-1.014
 Colo-0.986
thouse-0.980
Token fn
Token ID24714
Feature activation+4.28e+00

Pos logit contributions
river+7.403
 guiActiveUn+7.110
usted+6.854
atorial+6.177
allery+6.067
Neg logit contributions
NEY-8.201
sters-8.012
 Cu-7.992
thouse-7.913
 Colo-7.818
Token copy
Token ID4866
Feature activation+7.63e-01

Pos logit contributions
river+2.840
 guiActiveUn+2.827
usted+2.665
atorial+2.360
allery+2.357
Neg logit contributions
sters-3.524
NEY-3.492
 Cu-3.428
thouse-3.382
 Colo-3.353
Token_
Token ID62
Feature activation+5.04e+00

Pos logit contributions
river+0.662
 guiActiveUn+0.661
usted+0.625
allery+0.578
atorial+0.576
Neg logit contributions
sters-0.483
 Cu-0.472
NEY-0.470
 Colo-0.457
thouse-0.451
Tokenboard
Token ID3526
Feature activation+5.71e-01

Pos logit contributions
river+4.314
 guiActiveUn+4.179
usted+4.061
atorial+3.705
allery+3.652
Neg logit contributions
sters-3.181
NEY-3.181
 Cu-3.173
 Colo-3.075
thouse-3.006
Token (
Token ID357
Feature activation+9.59e-01

Pos logit contributions
river+0.526
 guiActiveUn+0.525
usted+0.498
allery+0.462
atorial+0.461
Neg logit contributions
sters-0.331
 Cu-0.323
NEY-0.321
 Colo-0.311
thouse-0.306
Token of
Token ID286
Feature activation-1.75e+00

Pos logit contributions
river+1.231
 guiActiveUn+1.228
usted+1.165
allery+1.077
atorial+1.075
Neg logit contributions
sters-0.836
 Cu-0.817
NEY-0.817
 Colo-0.790
thouse-0.781
Token the
Token ID262
Feature activation-3.98e-01

Pos logit contributions
sters+1.058
 Cu+1.042
NEY+1.016
 Colo+0.994
thouse+0.969
Neg logit contributions
 guiActiveUn-1.580
river-1.567
usted-1.492
allery-1.374
atorial-1.372
Token capital
Token ID3139
Feature activation+5.51e+00

Pos logit contributions
sters+0.270
 Cu+0.268
NEY+0.264
 Colo+0.257
thouse+0.252
Neg logit contributions
 guiActiveUn-0.327
river-0.325
usted-0.307
allery-0.282
atorial-0.281
Token,
Token ID11
Feature activation+2.47e+00

Pos logit contributions
river+5.576
 guiActiveUn+5.542
usted+5.299
atorial+4.958
allery+4.953
Neg logit contributions
sters-2.608
NEY-2.541
 Colo-2.420
 Cu-2.398
thouse-2.391
Token Mog
Token ID30926
Feature activation+7.89e+00

Pos logit contributions
river+2.679
 guiActiveUn+2.671
usted+2.560
allery+2.401
atorial+2.398
Neg logit contributions
sters-1.030
NEY-0.993
 Cu-0.981
 Colo-0.944
thouse-0.933
Tokenadish
Token ID48563
Feature activation+1.07e+01

Pos logit contributions
river+4.171
usted+3.975
 guiActiveUn+3.833
atorial+3.337
allery+3.186
Neg logit contributions
 Colo-7.592
NEY-7.575
sters-7.431
 Cu-7.306
 Luthor-7.190
Tokenu
Token ID84
Feature activation+4.45e+00

Pos logit contributions
river+5.810
usted+5.439
 guiActiveUn+5.219
allery+4.466
atorial+4.390
Neg logit contributions
sters-9.564
 Colo-9.529
 Canary-9.428
NEY-9.398
 Cu-9.391
Token.
Token ID13
Feature activation+3.49e-01

Pos logit contributions
river+3.583
 guiActiveUn+3.577
usted+3.369
allery+3.082
atorial+3.080
Neg logit contributions
sters-3.078
NEY-3.017
 Cu-3.015
 Colo-2.932
thouse-2.900
Token
Token ID198
Feature activation-3.78e-01

Pos logit contributions
river+0.313
 guiActiveUn+0.313
usted+0.296
allery+0.275
atorial+0.273
Neg logit contributions
sters-0.211
 Cu-0.208
NEY-0.205
 Colo-0.200
thouse-0.196
Token
Token ID198
Feature activation+2.32e-02

Pos logit contributions
sters+0.247
NEY+0.242
 Cu+0.242
 Colo+0.236
thouse+0.234
Neg logit contributions
river-0.319
 guiActiveUn-0.311
usted-0.300
atorial-0.276
allery-0.271
TokenThey
Token ID2990
Feature activation-4.23e-01

Pos logit contributions
 guiActiveUn+0.020
river+0.020
usted+0.019
allery+0.018
atorial+0.018
Neg logit contributions
sters-0.015
NEY-0.014
 Cu-0.014
 Colo-0.014
thouse-0.014
Token struct
Token ID2878
Feature activation+4.20e+00

Pos logit contributions
river+7.499
 guiActiveUn+7.231
usted+6.952
atorial+6.339
allery+6.191
Neg logit contributions
NEY-7.570
sters-7.467
 Cu-7.435
thouse-7.262
 Colo-7.217
Token Guard
Token ID4932
Feature activation+2.73e+00

Pos logit contributions
river+3.617
 guiActiveUn+3.571
usted+3.421
atorial+3.125
allery+3.117
Neg logit contributions
sters-2.659
NEY-2.614
 Cu-2.579
thouse-2.511
 Colo-2.487
Token {
Token ID1391
Feature activation-4.29e-02

Pos logit contributions
river+2.125
 guiActiveUn+2.115
usted+2.000
atorial+1.815
allery+1.814
Neg logit contributions
sters-1.964
NEY-1.925
 Cu-1.922
 Colo-1.868
thouse-1.856
Token...
Token ID2644
Feature activation-2.11e+00

Pos logit contributions
sters+0.028
 Cu+0.027
NEY+0.027
 Colo+0.026
thouse+0.026
Neg logit contributions
 guiActiveUn-0.037
river-0.037
usted-0.034
allery-0.032
atorial-0.032
Token }
Token ID1782
Feature activation+3.81e-01

Pos logit contributions
sters+1.491
 Cu+1.465
NEY+1.446
 Colo+1.426
thouse+1.393
Neg logit contributions
 guiActiveUn-1.676
river-1.665
usted-1.545
allery-1.438
atorial-1.432
Token pub
Token ID2240
Feature activation+1.06e+01

Pos logit contributions
river+0.337
 guiActiveUn+0.336
usted+0.318
atorial+0.295
allery+0.295
Neg logit contributions
sters-0.235
 Cu-0.231
NEY-0.228
 Colo-0.223
thouse-0.218
Token fn
Token ID24714
Feature activation+4.55e+00

Pos logit contributions
river+7.971
 guiActiveUn+7.738
usted+7.466
atorial+6.715
allery+6.634
Neg logit contributions
NEY-7.465
sters-7.391
 Cu-7.309
thouse-7.198
 Colo-7.105
Token pin
Token ID6757
Feature activation+2.56e+00

Pos logit contributions
river+3.579
 guiActiveUn+3.561
usted+3.374
atorial+3.064
allery+3.057
Neg logit contributions
sters-3.226
NEY-3.179
 Cu-3.153
 Colo-3.059
thouse-3.055
Token ()
Token ID7499
Feature activation+1.24e+00

Pos logit contributions
river+2.088
 guiActiveUn+2.065
usted+1.963
atorial+1.792
allery+1.789
Neg logit contributions
sters-1.742
NEY-1.713
 Cu-1.713
 Colo-1.667
thouse-1.644
Token ->
Token ID4613
Feature activation+3.60e+00

Pos logit contributions
river+1.112
 guiActiveUn+1.110
usted+1.053
allery+0.973
atorial+0.972
Neg logit contributions
sters-0.753
 Cu-0.736
NEY-0.735
 Colo-0.712
thouse-0.703
Token Guard
Token ID4932
Feature activation+3.43e+00

Pos logit contributions
river+3.119
 guiActiveUn+3.067
usted+2.956
atorial+2.705
allery+2.674
Neg logit contributions
sters-2.278
NEY-2.244
 Cu-2.191
thouse-2.159
 Colo-2.125
Token-
Token ID12
Feature activation+4.59e+00

Pos logit contributions
river+4.511
 guiActiveUn+4.420
usted+4.221
allery+3.905
atorial+3.859
Neg logit contributions
sters-3.448
NEY-3.368
 Cu-3.367
thouse-3.338
 Colo-3.315
TokenC
Token ID34
Feature activation+2.56e+00

Pos logit contributions
river+3.646
 guiActiveUn+3.501
usted+3.406
allery+3.058
atorial+3.034
Neg logit contributions
sters-3.201
 Cu-3.168
NEY-3.125
 Colo-3.102
thouse-3.086
TokenPS
Token ID3705
Feature activation-1.08e+00

Pos logit contributions
river+2.093
 guiActiveUn+2.076
usted+1.970
allery+1.803
atorial+1.799
Neg logit contributions
sters-1.746
 Cu-1.709
NEY-1.708
 Colo-1.667
thouse-1.650
Token,
Token ID11
Feature activation+3.32e+00

Pos logit contributions
sters+0.713
NEY+0.700
 Cu+0.699
 Colo+0.676
thouse+0.665
Neg logit contributions
 guiActiveUn-0.901
river-0.898
usted-0.848
allery-0.780
atorial-0.780
Token 2012
Token ID2321
Feature activation+2.05e+00

Pos logit contributions
river+2.456
 guiActiveUn+2.398
usted+2.293
atorial+2.061
allery+2.037
Neg logit contributions
sters-2.463
NEY-2.440
thouse-2.400
 Cu-2.399
 Colo-2.335
Token
Token ID1906
Feature activation+1.06e+01

Pos logit contributions
river+1.842
 guiActiveUn+1.830
usted+1.739
atorial+1.608
allery+1.608
Neg logit contributions
sters-1.218
NEY-1.195
 Cu-1.190
 Colo-1.153
thouse-1.146
Token2016
Token ID5304
Feature activation+3.68e+00

Pos logit contributions
river+5.171
 guiActiveUn+4.561
usted+4.516
atorial+3.863
allery+3.556
Neg logit contributions
 Cu-10.036
sters-9.989
thouse-9.881
NEY-9.815
 Colo-9.717
Token)).
Token ID29720
Feature activation+1.68e+00

Pos logit contributions
river+3.835
 guiActiveUn+3.806
usted+3.647
atorial+3.413
allery+3.412
Neg logit contributions
sters-1.626
NEY-1.595
 Cu-1.575
 Colo-1.519
thouse-1.518
Token This
Token ID770
Feature activation+6.14e-01

Pos logit contributions
river+1.436
 guiActiveUn+1.417
usted+1.352
atorial+1.244
allery+1.243
Neg logit contributions
sters-1.069
NEY-1.047
 Cu-1.035
thouse-1.010
 Colo-1.003
Token comparison
Token ID7208
Feature activation+2.32e+00

Pos logit contributions
river+0.504
 guiActiveUn+0.502
usted+0.475
allery+0.435
atorial+0.435
Neg logit contributions
sters-0.415
NEY-0.407
 Cu-0.407
 Colo-0.395
thouse-0.392
Token is
Token ID318
Feature activation+2.52e-01

Pos logit contributions
river+1.951
 guiActiveUn+1.934
usted+1.837
atorial+1.687
allery+1.681
Neg logit contributions
sters-1.501
NEY-1.484
 Cu-1.479
 Colo-1.439
thouse-1.428
Token.
Token ID13
Feature activation-3.06e+00

Pos logit contributions
sters+0.971
 Cu+0.958
NEY+0.942
 Colo+0.923
thouse+0.892
Neg logit contributions
 guiActiveUn-1.244
river-1.230
usted-1.160
allery-1.081
atorial-1.065
Token (
Token ID357
Feature activation-4.41e+00

Pos logit contributions
sters+1.690
 Cu+1.675
NEY+1.646
 Colo+1.603
thouse+1.556
Neg logit contributions
 guiActiveUn-2.901
river-2.897
usted-2.743
allery-2.566
atorial-2.541
TokenPhoto
Token ID6191
Feature activation-5.35e+00

Pos logit contributions
sters+2.314
NEY+2.302
 Cu+2.254
 Colo+2.163
Va+2.154
Neg logit contributions
 guiActiveUn-4.267
river-4.195
usted-3.985
allery-3.732
atorial-3.721
Token by
Token ID416
Feature activation+5.59e+00

Pos logit contributions
 Cu+3.120
sters+3.110
NEY+3.059
 Colo+2.925
 Dob+2.858
Neg logit contributions
 guiActiveUn-4.832
river-4.769
usted-4.482
atorial-4.196
allery-4.180
Token REUTERS
Token ID15862
Feature activation+4.88e+00

Pos logit contributions
river+4.521
 guiActiveUn+4.436
usted+4.247
allery+3.912
atorial+3.890
Neg logit contributions
sters-3.677
NEY-3.636
thouse-3.554
 Cu-3.518
 Colo-3.460
Token/
Token ID14
Feature activation+1.05e+01

Pos logit contributions
river+3.681
usted+3.373
 guiActiveUn+3.357
atorial+3.110
allery+2.980
Neg logit contributions
sters-3.428
NEY-3.363
thouse-3.319
 Colo-3.297
 Cu-3.295
TokenGary
Token ID33820
Feature activation+3.51e+00

Pos logit contributions
river+7.875
usted+7.307
 guiActiveUn+7.058
atorial+6.503
allery+6.321
Neg logit contributions
sters-7.082
thouse-6.969
NEY-6.842
 Cu-6.790
 Colo-6.718
Token Cameron
Token ID10821
Feature activation+3.13e-01

Pos logit contributions
river+1.628
 guiActiveUn+1.479
usted+1.475
ariat+1.224
atorial+1.218
Neg logit contributions
sters-3.410
thouse-3.347
NEY-3.329
riad-3.267
 Colo-3.225
Token/
Token ID14
Feature activation+7.86e+00

Pos logit contributions
 guiActiveUn+0.259
river+0.258
usted+0.244
allery+0.223
atorial+0.223
Neg logit contributions
sters-0.211
 Cu-0.207
NEY-0.206
 Colo-0.201
thouse-0.198
TokenFile
Token ID8979
Feature activation+1.72e+00

Pos logit contributions
river+5.772
usted+5.334
 guiActiveUn+5.298
atorial+4.823
allery+4.758
Neg logit contributions
sters-5.734
NEY-5.614
 Cu-5.608
 Colo-5.437
thouse-5.410
Token photo
Token ID4590
Feature activation+1.33e-01

Pos logit contributions
river+1.604
 guiActiveUn+1.588
usted+1.517
allery+1.408
atorial+1.405
Neg logit contributions
sters-0.974
 Cu-0.950
NEY-0.948
 Colo-0.916
thouse-0.906
Tokenmod
Token ID4666
Feature activation+8.69e+00

Pos logit contributions
river+5.836
usted+5.561
 guiActiveUn+5.551
allery+4.973
atorial+4.967
Neg logit contributions
NEY-3.958
sters-3.885
 Cu-3.823
 Colo-3.691
thouse-3.591
Token +
Token ID1343
Feature activation+6.36e+00

Pos logit contributions
river+7.396
 guiActiveUn+7.284
usted+6.967
atorial+6.360
allery+6.262
Neg logit contributions
sters-5.230
NEY-5.152
 Colo-5.037
thouse-5.028
 Cu-4.958
Tokenx
Token ID87
Feature activation+1.62e+00

Pos logit contributions
river+5.564
 guiActiveUn+5.399
usted+5.279
allery+4.856
atorial+4.820
Neg logit contributions
sters-3.730
NEY-3.641
 Cu-3.640
 Colo-3.578
thouse-3.472
Token /
Token ID1220
Feature activation+8.38e+00

Pos logit contributions
river+1.360
 guiActiveUn+1.353
usted+1.283
allery+1.176
atorial+1.174
Neg logit contributions
sters-1.067
NEY-1.042
 Cu-1.040
 Colo-1.013
thouse-1.003
Tokenetc
Token ID14784
Feature activation+1.01e+01

Pos logit contributions
river+6.897
 guiActiveUn+6.612
usted+6.501
allery+5.850
atorial+5.828
Neg logit contributions
sters-5.381
NEY-5.256
 Colo-5.237
 Cu-5.172
thouse-5.088
Token/
Token ID14
Feature activation+1.05e+01

Pos logit contributions
river+6.858
usted+6.269
 guiActiveUn+6.217
atorial+5.614
ariat+5.408
Neg logit contributions
sters-7.545
 Colo-7.496
NEY-7.482
thouse-7.347
 Cu-7.315
Tokenpm
Token ID4426
Feature activation+2.29e+00

Pos logit contributions
river+7.914
usted+7.430
 guiActiveUn+7.105
atorial+6.358
allery+6.349
Neg logit contributions
 Colo-7.438
sters-7.438
 Cu-7.346
NEY-7.343
thouse-7.002
Token/
Token ID14
Feature activation+5.44e+00

Pos logit contributions
river+1.947
 guiActiveUn+1.909
usted+1.833
allery+1.677
atorial+1.674
Neg logit contributions
sters-1.473
NEY-1.461
 Cu-1.445
 Colo-1.421
thouse-1.401
Tokenpower
Token ID6477
Feature activation+2.51e+00

Pos logit contributions
river+4.582
 guiActiveUn+4.387
usted+4.305
allery+3.857
atorial+3.853
Neg logit contributions
sters-3.558
NEY-3.532
 Cu-3.521
 Colo-3.488
thouse-3.376
Token.
Token ID13
Feature activation-1.29e-01

Pos logit contributions
 guiActiveUn+2.012
river+2.010
usted+1.893
allery+1.734
atorial+1.733
Neg logit contributions
sters-1.746
 Cu-1.711
NEY-1.703
 Colo-1.662
thouse-1.641
Tokend
Token ID67
Feature activation-8.99e-01

Pos logit contributions
sters+0.104
NEY+0.103
 Cu+0.102
 Colo+0.100
thouse+0.099
Neg logit contributions
river-0.090
 guiActiveUn-0.089
usted-0.084
atorial-0.075
allery-0.075
Token the
Token ID262
Feature activation+1.39e+00

Pos logit contributions
river+0.977
 guiActiveUn+0.961
usted+0.922
allery+0.845
atorial+0.843
Neg logit contributions
sters-0.751
NEY-0.738
 Cu-0.730
thouse-0.710
 Colo-0.709
Token potential
Token ID2785
Feature activation+5.64e+00

Pos logit contributions
river+0.876
 guiActiveUn+0.868
usted+0.809
atorial+0.718
allery+0.717
Neg logit contributions
sters-1.210
NEY-1.192
 Cu-1.188
 Colo-1.164
thouse-1.160
Token or
Token ID393
Feature activation+3.41e+00

Pos logit contributions
river+4.187
 guiActiveUn+4.170
usted+3.923
atorial+3.568
allery+3.554
Neg logit contributions
sters-4.167
NEY-4.102
 Cu-4.095
 Colo-3.999
thouse-3.972
Token 3
Token ID513
Feature activation+3.47e+00

Pos logit contributions
river+2.559
 guiActiveUn+2.544
usted+2.412
atorial+2.207
allery+2.186
Neg logit contributions
sters-2.500
 Cu-2.469
NEY-2.464
 Colo-2.404
thouse-2.368
Token har
Token ID3971
Feature activation+1.15e-01

Pos logit contributions
river+2.885
 guiActiveUn+2.868
usted+2.726
atorial+2.509
allery+2.489
Neg logit contributions
sters-2.270
NEY-2.231
 Cu-2.216
thouse-2.150
 Colo-2.148
Tokenv
Token ID85
Feature activation-1.16e+01

Pos logit contributions
river+0.112
 guiActiveUn+0.111
usted+0.106
atorial+0.099
allery+0.099
Neg logit contributions
sters-0.061
NEY-0.059
 Cu-0.059
 Colo-0.057
thouse-0.056
Tokenests
Token ID3558
Feature activation+2.26e+00

Pos logit contributions
sters+9.366
NEY+8.841
 Cu+8.746
 Colo+8.492
thouse+8.360
Neg logit contributions
 guiActiveUn-7.813
river-7.400
usted-6.731
allery-6.107
umbn-6.076
Token a
Token ID257
Feature activation+1.68e+00

Pos logit contributions
river+1.937
 guiActiveUn+1.923
usted+1.828
atorial+1.681
allery+1.679
Neg logit contributions
sters-1.438
NEY-1.413
 Cu-1.400
 Colo-1.364
thouse-1.352
Token year
Token ID614
Feature activation+1.99e+00

Pos logit contributions
river+1.210
 guiActiveUn+1.199
usted+1.121
atorial+1.016
allery+1.015
Neg logit contributions
sters-1.313
NEY-1.293
 Cu-1.285
 Colo-1.258
thouse-1.253
Token,
Token ID11
Feature activation+1.22e+00

Pos logit contributions
river+1.660
 guiActiveUn+1.651
usted+1.563
allery+1.434
atorial+1.433
Neg logit contributions
sters-1.320
NEY-1.294
 Cu-1.290
 Colo-1.254
thouse-1.241
Token unlike
Token ID5023
Feature activation-2.49e+00

Pos logit contributions
river+1.036
 guiActiveUn+1.032
usted+0.977
allery+0.899
atorial+0.897
Neg logit contributions
sters-0.792
NEY-0.775
 Cu-0.774
 Colo-0.751
thouse-0.744
Token B
Token ID347
Feature activation+5.82e-01

Pos logit contributions
river+2.075
 guiActiveUn+2.043
usted+1.964
allery+1.818
atorial+1.815
Neg logit contributions
sters-1.275
NEY-1.242
 Cu-1.211
thouse-1.195
 Colo-1.181
Tokené
Token ID2634
Feature activation-2.18e+00

Pos logit contributions
river+0.421
 guiActiveUn+0.419
usted+0.394
allery+0.356
atorial+0.356
Neg logit contributions
sters-0.451
NEY-0.443
 Cu-0.443
 Colo-0.432
thouse-0.427
Tokennes
Token ID2516
Feature activation-6.82e-01

Pos logit contributions
sters+1.438
 Cu+1.399
NEY+1.385
 Colo+1.345
thouse+1.340
Neg logit contributions
 guiActiveUn-1.856
river-1.832
usted-1.736
allery-1.597
atorial-1.591
Token (
Token ID357
Feature activation-2.12e-01

Pos logit contributions
sters+0.470
 Cu+0.462
NEY+0.458
 Colo+0.445
thouse+0.442
Neg logit contributions
 guiActiveUn-0.557
river-0.552
usted-0.523
allery-0.481
atorial-0.479
TokenK
Token ID42
Feature activation-1.38e+00

Pos logit contributions
sters+0.132
NEY+0.129
 Cu+0.129
 Colo+0.124
thouse+0.123
Neg logit contributions
 guiActiveUn-0.187
river-0.186
usted-0.176
allery-0.163
atorial-0.163
Tokenop
Token ID404
Feature activation-1.11e+01

Pos logit contributions
sters+1.026
 Cu+1.006
NEY+1.006
 Colo+0.976
thouse+0.968
Neg logit contributions
 guiActiveUn-1.039
river-1.032
usted-0.969
allery-0.881
atorial-0.880
Tokeni
Token ID72
Feature activation-1.85e+00

Pos logit contributions
sters+9.519
 Cu+9.331
NEY+9.184
thouse+9.049
 Colo+8.966
Neg logit contributions
 guiActiveUn-6.504
river-6.031
usted-5.666
allery-5.102
atorial-4.967
Token?
Token ID30
Feature activation+1.05e+00

Pos logit contributions
sters+1.189
 Cu+1.161
NEY+1.153
 Colo+1.114
thouse+1.102
Neg logit contributions
 guiActiveUn-1.590
river-1.576
usted-1.489
allery-1.375
atorial-1.372
Tokená
Token ID6557
Feature activation+3.86e+00

Pos logit contributions
river+0.680
 guiActiveUn+0.675
usted+0.628
allery+0.562
atorial+0.561
Neg logit contributions
sters-0.895
NEY-0.881
 Cu-0.880
 Colo-0.861
thouse-0.853
Tokenr
Token ID81
Feature activation-3.39e+00

Pos logit contributions
river+2.795
 guiActiveUn+2.726
usted+2.572
atorial+2.331
allery+2.326
Neg logit contributions
sters-2.976
NEY-2.954
 Cu-2.926
 Colo-2.874
thouse-2.833
Token 41
Token ID6073
Feature activation-8.72e-02

Pos logit contributions
sters+1.792
 Cu+1.751
NEY+1.703
 Colo+1.663
thouse+1.643
Neg logit contributions
 guiActiveUn-3.310
river-3.265
usted-3.116
atorial-2.928
allery-2.918
Token with
Token ID351
Feature activation+6.01e-01

Pos logit contributions
river+1.920
 guiActiveUn+1.908
usted+1.812
atorial+1.669
allery+1.664
Neg logit contributions
sters-1.414
NEY-1.386
 Cu-1.383
 Colo-1.346
thouse-1.333
Token all
Token ID477
Feature activation+3.75e+00

Pos logit contributions
river+0.527
 guiActiveUn+0.526
usted+0.498
allery+0.460
atorial+0.459
Neg logit contributions
sters-0.374
 Cu-0.366
NEY-0.366
 Colo-0.354
thouse-0.350
Token this
Token ID428
Feature activation-4.06e+00

Pos logit contributions
river+3.188
 guiActiveUn+3.154
usted+3.027
allery+2.769
atorial+2.757
Neg logit contributions
sters-2.392
NEY-2.357
 Cu-2.331
 Colo-2.263
thouse-2.237
Token Al
Token ID978
Feature activation-3.14e+00

Pos logit contributions
 Cu+2.488
sters+2.483
NEY+2.416
 Colo+2.377
thouse+2.312
Neg logit contributions
 guiActiveUn-3.565
river-3.532
usted-3.332
allery-3.072
atorial-3.070
Token J
Token ID449
Feature activation-1.94e+00

Pos logit contributions
sters+2.014
 Cu+1.973
NEY+1.944
thouse+1.903
 Colo+1.902
Neg logit contributions
 guiActiveUn-2.713
river-2.701
usted-2.529
allery-2.357
atorial-2.339
Tokenour
Token ID454
Feature activation-1.10e+01

Pos logit contributions
sters+1.441
 Cu+1.422
NEY+1.416
 Colo+1.377
thouse+1.362
Neg logit contributions
 guiActiveUn-1.458
river-1.452
usted-1.354
allery-1.243
atorial-1.232
Tokeng
Token ID70
Feature activation-3.72e+00

Pos logit contributions
sters+7.349
NEY+7.335
 Cu+7.270
thouse+7.173
 Colo+6.795
Neg logit contributions
 guiActiveUn-8.378
river-8.118
usted-7.649
allery-7.138
atorial-7.060
Tokenensen
Token ID18756
Feature activation+5.46e-01

Pos logit contributions
sters+2.779
 Cu+2.728
NEY+2.710
 Colo+2.616
thouse+2.591
Neg logit contributions
 guiActiveUn-2.855
river-2.766
usted-2.562
allery-2.348
atorial-2.314
Token and
Token ID290
Feature activation+1.25e+00

Pos logit contributions
river+0.492
 guiActiveUn+0.490
usted+0.466
atorial+0.431
allery+0.431
Neg logit contributions
sters-0.326
NEY-0.319
 Cu-0.317
 Colo-0.308
thouse-0.304
Token Ge
Token ID2269
Feature activation-4.94e+00

Pos logit contributions
river+1.116
 guiActiveUn+1.111
usted+1.055
allery+0.976
atorial+0.975
Neg logit contributions
sters-0.760
NEY-0.742
 Cu-0.739
 Colo-0.715
thouse-0.711
Tokenza
Token ID4496
Feature activation-3.64e+00

Pos logit contributions
sters+3.808
 Cu+3.701
NEY+3.695
 Colo+3.607
thouse+3.534
Neg logit contributions
 guiActiveUn-3.632
river-3.520
usted-3.292
allery-2.991
atorial-2.973
Tokenra
Token ID430
Feature activation+1.09e+00

Pos logit contributions
 guiActiveUn+0.310
river+0.307
usted+0.290
allery+0.267
atorial+0.266
Neg logit contributions
sters-0.277
 Cu-0.273
NEY-0.272
 Colo-0.263
thouse-0.261
Token,
Token ID11
Feature activation+1.06e+00

Pos logit contributions
river+1.005
 guiActiveUn+0.997
usted+0.951
atorial+0.880
allery+0.879
Neg logit contributions
sters-0.627
NEY-0.612
 Cu-0.609
 Colo-0.590
thouse-0.584
Token God
Token ID1793
Feature activation-1.57e+00

Pos logit contributions
river+0.997
 guiActiveUn+0.987
usted+0.943
atorial+0.874
allery+0.872
Neg logit contributions
sters-0.590
NEY-0.575
 Cu-0.569
 Colo-0.550
thouse-0.549
Token of
Token ID286
Feature activation-1.07e+00

Pos logit contributions
sters+0.871
 Cu+0.861
NEY+0.850
 Colo+0.821
thouse+0.812
Neg logit contributions
 guiActiveUn-1.481
river-1.464
usted-1.396
allery-1.303
atorial-1.296
Token Har
Token ID2113
Feature activation+5.17e-01

Pos logit contributions
sters+0.606
 Cu+0.600
NEY+0.591
 Colo+0.575
thouse+0.560
Neg logit contributions
 guiActiveUn-1.004
river-0.997
usted-0.948
allery-0.882
atorial-0.879
Tokenv
Token ID85
Feature activation-1.09e+01

Pos logit contributions
river+0.430
 guiActiveUn+0.423
usted+0.403
atorial+0.370
allery+0.370
Neg logit contributions
sters-0.346
NEY-0.343
 Cu-0.340
 Colo-0.331
thouse-0.326
Tokenests
Token ID3558
Feature activation+1.22e+00

Pos logit contributions
sters+9.281
 Cu+8.845
NEY+8.677
riad+8.500
thouse+8.440
Neg logit contributions
 guiActiveUn-7.062
river-6.490
usted-5.997
allery-5.462
umbn-5.328
Token
Token ID198
Feature activation-9.38e-01

Pos logit contributions
river+1.053
 guiActiveUn+1.048
usted+0.994
allery+0.916
atorial+0.915
Neg logit contributions
sters-0.772
NEY-0.755
 Cu-0.753
 Colo-0.731
thouse-0.723
Token
Token ID198
Feature activation-2.69e+00

Pos logit contributions
sters+0.607
NEY+0.595
 Cu+0.593
 Colo+0.578
thouse+0.573
Neg logit contributions
river-0.800
 guiActiveUn-0.785
usted-0.752
atorial-0.692
allery-0.685
TokenHot
Token ID21352
Feature activation-2.74e+00

Pos logit contributions
sters+1.727
NEY+1.704
 Cu+1.690
 Colo+1.631
Va+1.622
Neg logit contributions
 guiActiveUn-2.304
river-2.257
usted-2.151
allery-2.010
atorial-1.986
Token Soup
Token ID34011
Feature activation-3.24e+00

Pos logit contributions
sters+1.689
 Cu+1.664
NEY+1.621
 Colo+1.580
thouse+1.556
Neg logit contributions
 guiActiveUn-2.460
river-2.404
usted-2.287
allery-2.141
atorial-2.115
Token no
Token ID645
Feature activation-1.57e+00

Pos logit contributions
sters+0.588
 Cu+0.578
NEY+0.573
 Colo+0.558
thouse+0.547
Neg logit contributions
 guiActiveUn-0.788
river-0.786
usted-0.744
allery-0.685
atorial-0.682
Token matter
Token ID2300
Feature activation-1.41e+00

Pos logit contributions
sters+0.904
 Cu+0.883
NEY+0.878
 Colo+0.852
thouse+0.830
Neg logit contributions
 guiActiveUn-1.450
river-1.446
usted-1.377
allery-1.274
atorial-1.271
Token how
Token ID703
Feature activation-2.54e+00

Pos logit contributions
sters+0.923
 Cu+0.908
NEY+0.901
 Colo+0.879
thouse+0.863
Neg logit contributions
 guiActiveUn-1.192
river-1.183
usted-1.121
allery-1.029
atorial-1.024
Token young
Token ID1862
Feature activation-6.75e+00

Pos logit contributions
sters+1.698
 Cu+1.668
NEY+1.652
 Colo+1.614
thouse+1.580
Neg logit contributions
 guiActiveUn-2.132
river-2.104
usted-1.989
allery-1.839
atorial-1.808
Token or
Token ID393
Feature activation-3.04e+00

Pos logit contributions
sters+4.055
 Cu+3.892
 Colo+3.659
NEY+3.649
 Dob+3.577
Neg logit contributions
 guiActiveUn-6.185
river-5.887
usted-5.734
allery-5.300
atorial-5.216
Token adorable
Token ID29012
Feature activation-1.09e+01

Pos logit contributions
sters+2.116
 Cu+2.078
NEY+2.073
 Colo+2.023
thouse+1.992
Neg logit contributions
 guiActiveUn-2.468
river-2.420
usted-2.290
allery-2.110
atorial-2.072
Token the
Token ID262
Feature activation-4.79e+00

Pos logit contributions
sters+5.964
 Cu+5.897
 Colo+5.528
 Dob+5.377
NEY+5.300
Neg logit contributions
 guiActiveUn-10.212
river-9.537
usted-9.406
allery-8.652
atorial-8.448
Token crit
Token ID1955
Feature activation+2.30e+00

Pos logit contributions
sters+3.225
 Cu+3.162
NEY+3.086
 Colo+3.035
 Canary+2.944
Neg logit contributions
 guiActiveUn-4.031
river-3.941
usted-3.772
allery-3.434
atorial-3.399
Tokenters
Token ID1010
Feature activation-4.56e-01

Pos logit contributions
river+2.183
 guiActiveUn+2.167
usted+2.067
atorial+1.920
allery+1.920
Neg logit contributions
sters-1.247
 Cu-1.231
NEY-1.229
 Colo-1.184
thouse-1.164
Token that
Token ID326
Feature activation-1.02e+00

Pos logit contributions
sters+0.307
 Cu+0.300
NEY+0.298
 Colo+0.291
thouse+0.286
Neg logit contributions
 guiActiveUn-0.379
river-0.377
usted-0.356
allery-0.328
atorial-0.326
Token Gon
Token ID35371
Feature activation+1.61e-01

Pos logit contributions
sters+0.713
 Cu+0.697
NEY+0.693
 Colo+0.677
thouse+0.664
Neg logit contributions
 guiActiveUn-0.822
river-0.817
usted-0.771
allery-0.705
atorial-0.702
Token,
Token ID11
Feature activation-1.57e+00

Pos logit contributions
sters+2.086
 Cu+2.059
NEY+2.054
 Colo+1.975
thouse+1.974
Neg logit contributions
 guiActiveUn-2.930
river-2.928
usted-2.763
atorial-2.557
allery-2.547
Token telecommunications
Token ID27473
Feature activation-2.56e+00

Pos logit contributions
sters+0.850
 Cu+0.836
NEY+0.833
 Colo+0.802
thouse+0.790
Neg logit contributions
 guiActiveUn-1.504
river-1.501
usted-1.426
atorial-1.328
allery-1.326
Token companies
Token ID2706
Feature activation-2.40e+00

Pos logit contributions
sters+1.505
 Cu+1.469
NEY+1.448
 Colo+1.407
thouse+1.369
Neg logit contributions
 guiActiveUn-2.363
river-2.351
usted-2.223
allery-2.071
atorial-2.060
Token were
Token ID547
Feature activation-2.55e+00

Pos logit contributions
sters+1.631
 Cu+1.595
NEY+1.578
 Colo+1.547
thouse+1.500
Neg logit contributions
 guiActiveUn-1.987
river-1.976
usted-1.839
allery-1.722
atorial-1.705
Token granted
Token ID7520
Feature activation-3.28e+00

Pos logit contributions
sters+1.790
 Cu+1.752
NEY+1.749
 Colo+1.698
thouse+1.659
Neg logit contributions
 guiActiveUn-2.064
river-2.022
usted-1.879
atorial-1.764
allery-1.762
Token retro
Token ID12175
Feature activation-1.02e+01

Pos logit contributions
sters+2.043
 Cu+1.996
NEY+1.976
 Colo+1.913
thouse+1.858
Neg logit contributions
 guiActiveUn-2.904
river-2.876
usted-2.718
allery-2.516
atorial-2.507
Tokenactive
Token ID5275
Feature activation+1.10e+00

Pos logit contributions
sters+4.803
NEY+4.537
 Cu+4.423
 Colo+4.264
thouse+4.159
Neg logit contributions
 guiActiveUn-9.981
river-9.938
usted-9.375
allery-8.971
atorial-8.806
Token immunity
Token ID16989
Feature activation+2.02e+00

Pos logit contributions
river+0.949
 guiActiveUn+0.944
usted+0.897
allery+0.825
atorial+0.825
Neg logit contributions
sters-0.697
NEY-0.684
 Cu-0.681
 Colo-0.663
thouse-0.659
Token for
Token ID329
Feature activation-2.67e+00

Pos logit contributions
river+1.705
 guiActiveUn+1.686
usted+1.604
atorial+1.471
allery+1.470
Neg logit contributions
sters-1.314
NEY-1.292
 Cu-1.288
 Colo-1.254
thouse-1.240
Token violating
Token ID18134
Feature activation-7.45e+00

Pos logit contributions
sters+1.779
 Cu+1.745
NEY+1.739
 Colo+1.685
thouse+1.646
Neg logit contributions
 guiActiveUn-2.232
river-2.228
usted-2.098
allery-1.934
atorial-1.931
Token the
Token ID262
Feature activation-1.39e+00

Pos logit contributions
sters+3.971
 Cu+3.960
NEY+3.858
 Colo+3.740
 Sec+3.600
Neg logit contributions
 guiActiveUn-7.060
river-7.055
usted-6.599
allery-6.259
atorial-6.192
Token the
Token ID262
Feature activation-4.07e-01

Pos logit contributions
sters+0.416
 Cu+0.408
NEY+0.406
 Colo+0.397
thouse+0.391
Neg logit contributions
 guiActiveUn-0.448
river-0.448
usted-0.419
allery-0.383
atorial-0.381
Token remarks
Token ID10252
Feature activation-3.05e+00

Pos logit contributions
sters+0.270
NEY+0.265
 Cu+0.264
 Colo+0.256
thouse+0.255
Neg logit contributions
river-0.340
 guiActiveUn-0.338
usted-0.321
atorial-0.294
allery-0.294
Token caused
Token ID4073
Feature activation+7.57e-01

Pos logit contributions
sters+1.823
 Cu+1.751
NEY+1.719
 Colo+1.674
thouse+1.628
Neg logit contributions
 guiActiveUn-2.785
river-2.762
usted-2.588
allery-2.436
atorial-2.401
Token,
Token ID11
Feature activation-1.85e+00

Pos logit contributions
river+0.632
 guiActiveUn+0.629
usted+0.595
allery+0.546
atorial+0.545
Neg logit contributions
sters-0.503
NEY-0.493
 Cu-0.492
 Colo-0.478
thouse-0.474
Token K
Token ID509
Feature activation-1.48e+00

Pos logit contributions
sters+1.077
 Cu+1.053
NEY+1.046
 Colo+1.016
thouse+0.995
Neg logit contributions
 guiActiveUn-1.698
river-1.696
usted-1.609
allery-1.493
atorial-1.487
Tokenvy
Token ID7670
Feature activation-1.02e+01

Pos logit contributions
sters+1.110
NEY+1.089
 Cu+1.088
 Colo+1.058
thouse+1.049
Neg logit contributions
 guiActiveUn-1.106
river-1.104
usted-1.034
allery-0.939
atorial-0.938
Tokenat
Token ID265
Feature activation-2.96e+00

Pos logit contributions
 Cu+5.115
sters+5.037
thouse+4.656
NEY+4.598
 Dob+4.597
Neg logit contributions
 guiActiveUn-10.005
river-9.736
usted-9.135
allery-8.600
umbn-8.575
Token said
Token ID531
Feature activation-3.43e+00

Pos logit contributions
sters+1.807
 Cu+1.770
NEY+1.757
 Colo+1.708
thouse+1.675
Neg logit contributions
river-2.624
 guiActiveUn-2.616
usted-2.471
allery-2.302
atorial-2.286
Token:
Token ID25
Feature activation-7.65e-01

Pos logit contributions
sters+2.043
 Cu+2.001
NEY+1.949
 Colo+1.921
 Dob+1.857
Neg logit contributions
 guiActiveUn-3.120
river-3.089
usted-2.946
allery-2.750
atorial-2.712
Token "
Token ID366
Feature activation-2.40e+00

Pos logit contributions
sters+0.460
 Cu+0.454
NEY+0.452
 Colo+0.438
thouse+0.428
Neg logit contributions
river-0.687
 guiActiveUn-0.684
usted-0.646
allery-0.603
atorial-0.597
TokenApparently
Token ID30402
Feature activation-4.39e+00

Pos logit contributions
sters+1.544
NEY+1.511
 Cu+1.505
 Colo+1.460
thouse+1.428
Neg logit contributions
 guiActiveUn-2.072
river-2.045
usted-1.937
allery-1.808
atorial-1.785
Token this
Token ID428
Feature activation-1.86e+00

Pos logit contributions
sters+1.418
 Cu+1.405
NEY+1.382
 Colo+1.355
thouse+1.315
Neg logit contributions
 guiActiveUn-2.102
river-2.092
usted-1.971
allery-1.842
atorial-1.835
Token mourn
Token ID25722
Feature activation-7.82e+00

Pos logit contributions
sters+1.232
 Cu+1.217
NEY+1.194
 Colo+1.175
thouse+1.146
Neg logit contributions
 guiActiveUn-1.555
river-1.547
usted-1.462
allery-1.354
atorial-1.337
Tokenful
Token ID913
Feature activation-2.64e+00

Pos logit contributions
sters+3.996
 Cu+3.882
NEY+3.863
 Colo+3.662
 Dob+3.621
Neg logit contributions
 guiActiveUn-7.580
river-7.408
usted-7.073
allery-6.803
atorial-6.526
Token,
Token ID11
Feature activation-1.04e+00

Pos logit contributions
sters+1.882
 Cu+1.861
NEY+1.830
 Colo+1.805
thouse+1.754
Neg logit contributions
 guiActiveUn-2.069
river-2.063
usted-1.950
allery-1.787
atorial-1.765
Token highly
Token ID4047
Feature activation-2.56e+00

Pos logit contributions
sters+0.721
 Cu+0.708
NEY+0.703
 Colo+0.687
thouse+0.676
Neg logit contributions
 guiActiveUn-0.846
river-0.844
usted-0.794
allery-0.733
atorial-0.725
Token distraught
Token ID48629
Feature activation-1.02e+01

Pos logit contributions
sters+1.748
 Cu+1.720
NEY+1.710
 Colo+1.674
thouse+1.633
Neg logit contributions
river-2.090
 guiActiveUn-2.089
usted-1.967
allery-1.827
atorial-1.793
Token dummy
Token ID31548
Feature activation-3.80e+00

Pos logit contributions
 Cu+6.699
sters+6.568
 Colo+6.522
 Dob+6.297
 Canary+6.246
Neg logit contributions
 guiActiveUn-8.105
river-7.826
usted-7.601
allery-7.172
atorial-6.843
Token might
Token ID1244
Feature activation-2.11e+00

Pos logit contributions
sters+2.325
 Cu+2.260
NEY+2.191
 Colo+2.161
thouse+2.094
Neg logit contributions
 guiActiveUn-3.397
river-3.350
usted-3.178
allery-3.006
atorial-2.940
Token be
Token ID307
Feature activation-2.19e+00

Pos logit contributions
sters+1.367
 Cu+1.339
NEY+1.331
 Colo+1.291
thouse+1.274
Neg logit contributions
 guiActiveUn-1.791
river-1.789
usted-1.692
allery-1.563
atorial-1.542
Token the
Token ID262
Feature activation-2.30e+00

Pos logit contributions
sters+1.251
 Cu+1.228
NEY+1.218
 Colo+1.184
thouse+1.158
Neg logit contributions
 guiActiveUn-2.040
river-2.031
usted-1.924
allery-1.794
atorial-1.779
Token closest
Token ID11706
Feature activation-2.82e+00

Pos logit contributions
sters+1.361
 Cu+1.335
NEY+1.319
 Colo+1.285
thouse+1.259
Neg logit contributions
river-2.099
 guiActiveUn-2.093
usted-1.985
allery-1.841
atorial-1.833
Token pro
Token ID386
Feature activation-4.54e+00

Pos logit contributions
river+1.637
 guiActiveUn+1.617
usted+1.544
atorial+1.419
allery+1.415
Neg logit contributions
sters-1.230
NEY-1.207
 Cu-1.197
 Colo-1.164
thouse-1.152
Token-
Token ID12
Feature activation+5.54e-01

Pos logit contributions
sters+2.646
 Cu+2.566
NEY+2.501
 Colo+2.432
thouse+2.366
Neg logit contributions
 guiActiveUn-4.163
river-4.122
usted-3.905
allery-3.658
atorial-3.635
Tokenlab
Token ID23912
Feature activation+2.92e-01

Pos logit contributions
 guiActiveUn+0.427
river+0.427
usted+0.401
allery+0.366
atorial+0.365
Neg logit contributions
sters-0.404
 Cu-0.395
NEY-0.395
 Colo-0.384
thouse-0.380
Tokenour
Token ID454
Feature activation-3.66e-01

Pos logit contributions
 guiActiveUn+0.252
river+0.252
usted+0.239
allery+0.220
atorial+0.219
Neg logit contributions
sters-0.186
NEY-0.181
 Cu-0.181
 Colo-0.175
thouse-0.173
Token,
Token ID11
Feature activation+6.72e-01

Pos logit contributions
sters+0.247
 Cu+0.242
NEY+0.241
 Colo+0.233
thouse+0.231
Neg logit contributions
 guiActiveUn-0.301
river-0.301
usted-0.285
allery-0.261
atorial-0.261
Token pro
Token ID386
Feature activation-1.01e+01

Pos logit contributions
river+0.545
 guiActiveUn+0.545
usted+0.514
allery+0.470
atorial+0.469
Neg logit contributions
sters-0.461
 Cu-0.452
NEY-0.452
 Colo-0.439
thouse-0.434
Token-
Token ID12
Feature activation-1.79e+00

Pos logit contributions
sters+5.101
 Cu+4.784
NEY+4.672
 Colo+4.485
Va+4.322
Neg logit contributions
 guiActiveUn-9.657
river-9.332
usted-9.072
allery-8.446
atorial-8.369
Tokenworker
Token ID28816
Feature activation-1.45e+00

Pos logit contributions
sters+1.277
NEY+1.242
 Cu+1.239
 Colo+1.194
thouse+1.187
Neg logit contributions
 guiActiveUn-1.432
river-1.394
usted-1.325
allery-1.227
atorial-1.219
Token,
Token ID11
Feature activation+9.20e-01

Pos logit contributions
sters+0.965
 Cu+0.948
NEY+0.941
 Colo+0.912
thouse+0.898
Neg logit contributions
 guiActiveUn-1.221
river-1.213
usted-1.154
allery-1.057
atorial-1.056
Token pro
Token ID386
Feature activation-7.95e+00

Pos logit contributions
river+0.783
 guiActiveUn+0.782
usted+0.739
allery+0.680
atorial+0.679
Neg logit contributions
sters-0.597
 Cu-0.585
NEY-0.584
 Colo-0.567
thouse-0.560
Token-
Token ID12
Feature activation-4.28e-01

Pos logit contributions
sters+4.088
 Cu+3.870
NEY+3.828
 Colo+3.676
thouse+3.556
Neg logit contributions
 guiActiveUn-7.597
river-7.441
usted-7.199
allery-6.716
atorial-6.666
Token who
Token ID508
Feature activation+7.97e-01

Pos logit contributions
river+2.392
 guiActiveUn+2.361
usted+2.268
atorial+2.063
allery+2.039
Neg logit contributions
sters-1.942
NEY-1.922
 Cu-1.893
 Colo-1.841
thouse-1.832
Token was
Token ID373
Feature activation+1.09e+00

Pos logit contributions
river+0.656
 guiActiveUn+0.653
usted+0.620
atorial+0.567
allery+0.566
Neg logit contributions
sters-0.535
NEY-0.526
 Cu-0.524
 Colo-0.509
thouse-0.505
Token imprisoned
Token ID21125
Feature activation-3.92e-01

Pos logit contributions
river+0.845
 guiActiveUn+0.837
usted+0.796
atorial+0.719
allery+0.717
Neg logit contributions
sters-0.785
NEY-0.771
 Cu-0.767
 Colo-0.747
thouse-0.745
Token after
Token ID706
Feature activation-2.48e+00

Pos logit contributions
sters+0.238
 Cu+0.232
NEY+0.232
 Colo+0.225
thouse+0.222
Neg logit contributions
river-0.350
 guiActiveUn-0.350
usted-0.331
allery-0.307
atorial-0.306
Token authorities
Token ID4773
Feature activation-2.13e+00

Pos logit contributions
sters+1.680
 Cu+1.656
NEY+1.629
 Colo+1.608
thouse+1.570
Neg logit contributions
 guiActiveUn-2.051
river-2.037
usted-1.912
allery-1.782
atorial-1.760
Token falsely
Token ID24566
Feature activation-9.99e+00

Pos logit contributions
sters+1.396
 Cu+1.365
NEY+1.350
 Colo+1.323
thouse+1.296
Neg logit contributions
 guiActiveUn-1.817
river-1.798
usted-1.685
allery-1.576
atorial-1.567
Token identified
Token ID5174
Feature activation-4.38e+00

Pos logit contributions
sters+6.606
 Cu+6.108
 Colo+5.955
NEY+5.911
 Dob+5.806
Neg logit contributions
river-8.105
 guiActiveUn-8.033
usted-7.170
allery-7.073
atorial-7.065
Token him
Token ID683
Feature activation-3.45e+00

Pos logit contributions
sters+3.058
 Cu+3.045
 Colo+2.963
NEY+2.942
 Dob+2.865
Neg logit contributions
 guiActiveUn-3.534
river-3.421
usted-3.214
allery-3.013
atorial-2.977
Token as
Token ID355
Feature activation-4.48e+00

Pos logit contributions
sters+2.027
 Cu+1.977
NEY+1.913
 Colo+1.913
thouse+1.866
Neg logit contributions
 guiActiveUn-3.132
river-3.104
usted-2.909
allery-2.780
atorial-2.737
Token an
Token ID281
Feature activation-7.02e-01

Pos logit contributions
 Cu+2.400
sters+2.387
 Colo+2.315
NEY+2.312
 Dob+2.219
Neg logit contributions
 guiActiveUn-4.285
river-4.261
usted-4.016
allery-3.823
atorial-3.753
Token illegal
Token ID5293
Feature activation+6.50e-01

Pos logit contributions
sters+0.454
 Cu+0.450
NEY+0.445
 Colo+0.438
thouse+0.426
Neg logit contributions
 guiActiveUn-0.596
river-0.594
usted-0.557
allery-0.518
atorial-0.515
Token
Token ID198
Feature activation-9.71e-01

Pos logit contributions
sters+0.385
 Cu+0.377
NEY+0.376
 Colo+0.366
thouse+0.363
Neg logit contributions
river-0.508
 guiActiveUn-0.501
usted-0.479
atorial-0.440
allery-0.436
Token
Token ID447
Feature activation+1.51e+00

Pos logit contributions
sters+0.604
NEY+0.594
 Cu+0.588
 Colo+0.569
thouse+0.563
Neg logit contributions
 guiActiveUn-0.856
river-0.849
usted-0.804
allery-0.750
atorial-0.743
Token
Token ID250
Feature activation+8.61e-01

Pos logit contributions
river+1.298
 guiActiveUn+1.292
usted+1.227
atorial+1.132
allery+1.127
Neg logit contributions
sters-0.956
 Cu-0.935
NEY-0.932
 Colo-0.905
thouse-0.888
TokenGrant
Token ID45431
Feature activation+1.53e+00

Pos logit contributions
river+0.741
 guiActiveUn+0.740
usted+0.700
allery+0.645
atorial+0.644
Neg logit contributions
sters-0.550
 Cu-0.538
NEY-0.538
 Colo-0.521
thouse-0.515
Tokening
Token ID278
Feature activation+3.45e+00

Pos logit contributions
river+1.372
 guiActiveUn+1.365
usted+1.303
atorial+1.197
allery+1.195
Neg logit contributions
sters-0.912
NEY-0.896
 Cu-0.892
 Colo-0.863
thouse-0.851
Token retro
Token ID12175
Feature activation-9.92e+00

Pos logit contributions
river+3.035
 guiActiveUn+2.983
usted+2.860
atorial+2.631
allery+2.613
Neg logit contributions
sters-2.078
NEY-2.064
 Cu-2.010
thouse-1.982
 Colo-1.970
Tokenactive
Token ID5275
Feature activation+1.28e+00

Pos logit contributions
sters+5.071
NEY+4.683
 Cu+4.669
thouse+4.472
 Colo+4.469
Neg logit contributions
 guiActiveUn-9.320
river-9.286
usted-8.790
allery-8.424
atorial-8.203
Token immunity
Token ID16989
Feature activation+3.32e+00

Pos logit contributions
river+1.080
 guiActiveUn+1.074
usted+1.019
atorial+0.935
allery+0.934
Neg logit contributions
sters-0.837
NEY-0.822
 Cu-0.818
 Colo-0.794
thouse-0.790
Token to
Token ID284
Feature activation-1.13e+00

Pos logit contributions
river+2.656
 guiActiveUn+2.602
usted+2.496
atorial+2.267
allery+2.253
Neg logit contributions
sters-2.278
NEY-2.261
 Cu-2.241
 Colo-2.182
thouse-2.178
Token companies
Token ID2706
Feature activation-7.02e-01

Pos logit contributions
sters+0.705
 Cu+0.693
NEY+0.688
 Colo+0.668
thouse+0.655
Neg logit contributions
 guiActiveUn-0.986
river-0.984
usted-0.929
allery-0.859
atorial-0.858
Token that
Token ID326
Feature activation-8.92e-01

Pos logit contributions
sters+0.471
 Cu+0.462
NEY+0.458
 Colo+0.447
thouse+0.437
Neg logit contributions
 guiActiveUn-0.584
river-0.583
usted-0.547
allery-0.509
atorial-0.504
Token raids
Token ID20371
Feature activation+6.12e-01

Pos logit contributions
river+1.012
 guiActiveUn+1.012
usted+0.941
allery+0.844
atorial+0.842
Neg logit contributions
sters-1.252
 Cu-1.231
NEY-1.229
 Colo-1.200
thouse-1.191
Token.
Token ID13
Feature activation-1.12e-01

Pos logit contributions
 guiActiveUn+0.493
river+0.493
usted+0.464
allery+0.427
atorial+0.425
Neg logit contributions
sters-0.425
 Cu-0.417
NEY-0.415
 Colo-0.404
thouse-0.399
Token
Token ID198
Feature activation-8.09e-01

Pos logit contributions
sters+0.069
 Cu+0.067
NEY+0.067
 Colo+0.065
thouse+0.064
Neg logit contributions
 guiActiveUn-0.100
river-0.100
usted-0.095
allery-0.088
atorial-0.087
Token
Token ID198
Feature activation+2.17e-01

Pos logit contributions
sters+0.523
NEY+0.513
 Cu+0.511
 Colo+0.498
thouse+0.493
Neg logit contributions
river-0.690
 guiActiveUn-0.677
usted-0.649
atorial-0.597
allery-0.591
TokenK
Token ID42
Feature activation-1.02e+00

Pos logit contributions
 guiActiveUn+0.186
river+0.185
usted+0.175
allery+0.162
atorial+0.161
Neg logit contributions
sters-0.141
NEY-0.138
 Cu-0.137
 Colo-0.133
thouse-0.131
Tokenhy
Token ID12114
Feature activation-9.90e+00

Pos logit contributions
sters+0.803
NEY+0.788
 Cu+0.786
 Colo+0.765
thouse+0.759
Neg logit contributions
 guiActiveUn-0.719
river-0.718
usted-0.668
allery-0.608
atorial-0.605
Tokenber
Token ID527
Feature activation-2.63e+00

Pos logit contributions
sters+4.727
NEY+4.316
 Cu+4.210
thouse+4.030
riad+3.918
Neg logit contributions
 guiActiveUn-10.087
river-9.627
usted-9.227
allery-8.889
atorial-8.686
Token raid
Token ID9513
Feature activation+1.55e+00

Pos logit contributions
sters+1.665
 Cu+1.646
NEY+1.625
 Colo+1.593
thouse+1.561
Neg logit contributions
 guiActiveUn-2.284
river-2.256
usted-2.126
allery-1.987
atorial-1.957
Token
Token ID198
Feature activation+2.70e-02

Pos logit contributions
river+1.318
 guiActiveUn+1.308
usted+1.249
atorial+1.142
allery+1.141
Neg logit contributions
sters-0.993
NEY-0.980
 Cu-0.975
 Colo-0.949
thouse-0.940
Token
Token ID198
Feature activation-6.47e-01

Pos logit contributions
river+0.022
 guiActiveUn+0.022
usted+0.021
atorial+0.019
allery+0.019
Neg logit contributions
sters-0.018
NEY-0.018
 Cu-0.018
 Colo-0.017
thouse-0.017
TokenMilitary
Token ID37837
Feature activation+5.65e-01

Pos logit contributions
sters+0.423
NEY+0.416
 Cu+0.410
 Colo+0.398
thouse+0.393
Neg logit contributions
 guiActiveUn-0.552
river-0.545
usted-0.515
allery-0.482
atorial-0.477
Tokens
Token ID82
Feature activation-1.96e+00

Pos logit contributions
river+1.327
 guiActiveUn+1.326
usted+1.259
allery+1.171
atorial+1.167
Neg logit contributions
sters-0.791
 Cu-0.772
NEY-0.770
 Colo-0.744
thouse-0.732
Token)}
Token ID38165
Feature activation-2.11e+00

Pos logit contributions
sters+0.929
NEY+0.903
 Cu+0.902
 Colo+0.867
thouse+0.851
Neg logit contributions
river-2.017
 guiActiveUn-2.001
usted-1.921
atorial-1.790
allery-1.788
Token 30
Token ID1542
Feature activation-2.77e+00

Pos logit contributions
sters+0.972
 Cu+0.946
NEY+0.933
 Colo+0.901
thouse+0.882
Neg logit contributions
river-2.192
 guiActiveUn-2.190
usted-2.091
allery-1.965
atorial-1.953
Token.
Token ID13
Feature activation-4.10e+00

Pos logit contributions
sters+1.932
 Cu+1.894
NEY+1.887
 Colo+1.836
thouse+1.812
Neg logit contributions
 guiActiveUn-2.246
river-2.225
usted-2.096
allery-1.937
atorial-1.916
Token K
Token ID509
Feature activation-3.81e+00

Pos logit contributions
 Cu+2.186
sters+2.168
NEY+2.092
 Colo+2.075
 Dob+2.015
Neg logit contributions
 guiActiveUn-3.983
river-3.947
usted-3.754
allery-3.515
atorial-3.481
Tokenf
Token ID69
Feature activation-9.86e+00

Pos logit contributions
sters+2.629
 Cu+2.562
NEY+2.554
 Colo+2.461
thouse+2.437
Neg logit contributions
 guiActiveUn-3.131
river-3.061
usted-2.882
allery-2.675
atorial-2.652
Token2
Token ID17
Feature activation-2.87e+00

Pos logit contributions
sters+5.275
 Cu+5.204
NEY+5.079
Va+5.025
 Dob+4.972
Neg logit contributions
 guiActiveUn-9.380
river-8.863
usted-8.261
allery-8.172
umbn-8.022
Token {
Token ID1391
Feature activation-4.11e+00

Pos logit contributions
 Cu+1.846
sters+1.845
NEY+1.785
 Colo+1.760
 Dob+1.720
Neg logit contributions
 guiActiveUn-2.452
river-2.447
usted-2.296
allery-2.157
atorial-2.118
Token(
Token ID7
Feature activation+1.17e+00

Pos logit contributions
sters+2.111
NEY+2.056
 Cu+2.045
 Colo+1.949
thouse+1.928
Neg logit contributions
 guiActiveUn-4.103
river-4.029
usted-3.856
allery-3.662
atorial-3.583
Token4
Token ID19
Feature activation+1.38e+00

Pos logit contributions
river+0.889
 guiActiveUn+0.880
usted+0.831
allery+0.754
atorial+0.754
Neg logit contributions
sters-0.869
 Cu-0.853
NEY-0.853
 Colo-0.831
thouse-0.824
Tokens
Token ID82
Feature activation-1.35e+00

Pos logit contributions
 guiActiveUn+1.321
river+1.321
usted+1.254
allery+1.171
atorial+1.164
Neg logit contributions
sters-0.752
 Cu-0.733
NEY-0.730
 Colo-0.705
thouse-0.691
Token1
Token ID16
Feature activation+5.85e-01

Pos logit contributions
river+0.163
 guiActiveUn+0.162
usted+0.153
atorial+0.139
allery+0.138
Neg logit contributions
sters-0.156
 Cu-0.154
NEY-0.154
 Colo-0.150
thouse-0.148
Token when
Token ID618
Feature activation+1.09e+00

Pos logit contributions
river+0.496
 guiActiveUn+0.493
usted+0.469
allery+0.429
atorial+0.429
Neg logit contributions
sters-0.380
NEY-0.373
 Cu-0.372
 Colo-0.360
thouse-0.359
Token leading
Token ID3756
Feature activation-3.76e+00

Pos logit contributions
river+0.925
 guiActiveUn+0.921
usted+0.872
allery+0.803
atorial+0.801
Neg logit contributions
sters-0.706
NEY-0.693
 Cu-0.689
 Colo-0.669
thouse-0.665
Token after
Token ID706
Feature activation-2.42e+00

Pos logit contributions
sters+2.222
 Cu+2.183
 Colo+2.113
NEY+2.065
thouse+2.001
Neg logit contributions
 guiActiveUn-3.502
river-3.382
usted-3.256
allery-3.044
atorial-3.020
Token eight
Token ID3624
Feature activation-2.61e+00

Pos logit contributions
sters+1.427
 Cu+1.409
NEY+1.378
 Colo+1.346
thouse+1.314
Neg logit contributions
 guiActiveUn-2.220
river-2.195
usted-2.089
atorial-1.931
allery-1.924
Token innings
Token ID16267
Feature activation-9.82e+00

Pos logit contributions
sters+1.316
 Cu+1.300
NEY+1.259
 Colo+1.255
thouse+1.190
Neg logit contributions
 guiActiveUn-2.625
river-2.576
usted-2.469
allery-2.298
atorial-2.281
Token.
Token ID13
Feature activation-1.43e+00

Pos logit contributions
 Cu+5.400
sters+5.371
 Colo+5.175
NEY+4.950
 Sec+4.768
Neg logit contributions
 guiActiveUn-9.111
river-8.769
usted-8.326
umbn-7.909
atorial-7.903
Token
Token ID198
Feature activation-1.25e+00

Pos logit contributions
sters+0.871
 Cu+0.856
NEY+0.850
 Colo+0.825
thouse+0.811
Neg logit contributions
river-1.280
 guiActiveUn-1.279
usted-1.211
allery-1.120
atorial-1.117
Token
Token ID198
Feature activation-1.50e+00

Pos logit contributions
sters+0.806
 Cu+0.788
NEY+0.788
 Colo+0.767
thouse+0.761
Neg logit contributions
river-1.069
 guiActiveUn-1.053
usted-1.007
atorial-0.925
allery-0.919
TokenThat
Token ID2504
Feature activation-1.64e+00

Pos logit contributions
sters+0.946
NEY+0.932
 Cu+0.923
 Colo+0.892
thouse+0.879
Neg logit contributions
 guiActiveUn-1.308
river-1.296
usted-1.227
allery-1.140
atorial-1.135
Token
Token ID447
Feature activation+1.39e-01

Pos logit contributions
sters+1.064
 Cu+1.046
NEY+1.037
 Colo+1.012
thouse+0.996
Neg logit contributions
 guiActiveUn-1.402
river-1.399
usted-1.319
allery-1.215
atorial-1.213
Token chambers
Token ID23204
Feature activation-1.67e-01

Pos logit contributions
river+1.715
 guiActiveUn+1.707
usted+1.613
atorial+1.481
allery+1.468
Neg logit contributions
sters-1.453
NEY-1.433
 Cu-1.420
 Colo-1.386
thouse-1.385
Token in
Token ID287
Feature activation-9.80e-01

Pos logit contributions
sters+0.107
 Cu+0.105
NEY+0.104
 Colo+0.101
thouse+0.100
Neg logit contributions
river-0.144
 guiActiveUn-0.144
usted-0.136
allery-0.126
atorial-0.125
Token the
Token ID262
Feature activation-1.41e+00

Pos logit contributions
sters+0.575
 Cu+0.563
NEY+0.561
 Colo+0.544
thouse+0.535
Neg logit contributions
river-0.895
 guiActiveUn-0.894
usted-0.848
allery-0.786
atorial-0.784
Token Mass
Token ID5674
Feature activation-4.96e+00

Pos logit contributions
sters+0.879
 Cu+0.865
NEY+0.856
 Colo+0.836
thouse+0.816
Neg logit contributions
river-1.241
 guiActiveUn-1.239
usted-1.174
allery-1.084
atorial-1.079
Token and
Token ID290
Feature activation-1.99e+00

Pos logit contributions
sters+3.172
 Cu+3.121
NEY+3.048
 Colo+3.009
thouse+2.918
Neg logit contributions
 guiActiveUn-4.200
river-4.179
usted-3.946
allery-3.666
atorial-3.627
Token Velocity
Token ID43137
Feature activation-9.74e+00

Pos logit contributions
sters+1.107
 Cu+1.093
NEY+1.078
 Colo+1.052
thouse+1.020
Neg logit contributions
 guiActiveUn-1.878
river-1.875
usted-1.781
allery-1.653
atorial-1.650
Token course
Token ID1781
Feature activation-3.35e+00

Pos logit contributions
 Cu+6.433
sters+6.412
 Colo+6.129
 Fle+6.025
NEY+5.986
Neg logit contributions
river-7.677
 guiActiveUn-7.614
usted-7.314
allery-6.830
umbn-6.801
Token in
Token ID287
Feature activation+5.87e-01

Pos logit contributions
sters+1.805
 Cu+1.752
NEY+1.724
 Colo+1.658
thouse+1.638
Neg logit contributions
 guiActiveUn-3.240
river-3.214
usted-3.052
allery-2.858
atorial-2.834
Token under
Token ID739
Feature activation+4.01e+00

Pos logit contributions
river+0.528
 guiActiveUn+0.525
usted+0.500
allery+0.462
atorial+0.462
Neg logit contributions
sters-0.349
NEY-0.342
 Cu-0.338
thouse-0.328
 Colo-0.327
Token 60
Token ID3126
Feature activation+5.20e-01

Pos logit contributions
river+3.693
 guiActiveUn+3.612
usted+3.480
atorial+3.227
allery+3.216
Neg logit contributions
NEY-2.225
sters-2.225
 Cu-2.197
 Colo-2.127
thouse-2.112
Token seconds
Token ID4201
Feature activation-4.75e+00

Pos logit contributions
river+0.455
 guiActiveUn+0.454
usted+0.430
allery+0.397
atorial+0.396
Neg logit contributions
sters-0.325
 Cu-0.318
NEY-0.317
 Colo-0.308
thouse-0.304
Tokenating
Token ID803
Feature activation+1.76e+00

Pos logit contributions
sters+1.516
 Cu+1.495
NEY+1.487
 Colo+1.452
thouse+1.445
Neg logit contributions
 guiActiveUn-1.157
river-1.132
usted-1.054
allery-0.949
atorial-0.904
Token Ev
Token ID4319
Feature activation-2.14e-01

Pos logit contributions
river+1.626
 guiActiveUn+1.596
usted+1.538
atorial+1.423
allery+1.422
Neg logit contributions
sters-1.006
NEY-0.990
 Cu-0.962
thouse-0.934
 Colo-0.934
Tokengen
Token ID5235
Feature activation+1.27e+00

Pos logit contributions
sters+0.113
 Cu+0.109
NEY+0.108
 Colo+0.106
thouse+0.103
Neg logit contributions
 guiActiveUn-0.210
river-0.208
usted-0.199
allery-0.186
atorial-0.184
Tokeny
Token ID88
Feature activation-1.21e+00

Pos logit contributions
river+0.694
 guiActiveUn+0.694
usted+0.635
allery+0.553
atorial+0.551
Neg logit contributions
sters-1.213
 Cu-1.196
NEY-1.192
 Colo-1.172
thouse-1.160
Token K
Token ID509
Feature activation-2.98e+00

Pos logit contributions
sters+0.739
 Cu+0.728
NEY+0.715
 Colo+0.707
thouse+0.686
Neg logit contributions
river-1.081
 guiActiveUn-1.081
usted-1.022
atorial-0.949
allery-0.942
Tokenuz
Token ID10277
Feature activation-9.69e+00

Pos logit contributions
sters+1.739
NEY+1.668
 Cu+1.655
 Colo+1.593
thouse+1.550
Neg logit contributions
 guiActiveUn-2.745
river-2.694
usted-2.567
allery-2.391
atorial-2.381
Tokennet
Token ID3262
Feature activation+6.23e-02

Pos logit contributions
sters+3.347
 Cu+3.026
NEY+2.748
 Dob+2.687
thouse+2.661
Neg logit contributions
 guiActiveUn-10.833
river-10.765
usted-10.116
allery-9.750
umbn-9.557
Tokensov
Token ID47272
Feature activation+1.13e+00

Pos logit contributions
 guiActiveUn+0.056
river+0.056
usted+0.053
allery+0.049
atorial+0.049
Neg logit contributions
sters-0.037
 Cu-0.036
NEY-0.036
 Colo-0.035
thouse-0.034
Token pass
Token ID1208
Feature activation+1.73e+00

Pos logit contributions
river+0.927
 guiActiveUn+0.920
usted+0.873
allery+0.799
atorial+0.798
Neg logit contributions
sters-0.766
NEY-0.753
 Cu-0.751
 Colo-0.729
thouse-0.720
Token,
Token ID11
Feature activation+1.06e+00

Pos logit contributions
river+1.424
 guiActiveUn+1.410
usted+1.339
allery+1.226
atorial+1.224
Neg logit contributions
sters-1.163
NEY-1.145
 Cu-1.141
 Colo-1.108
thouse-1.095
Token before
Token ID878
Feature activation+4.10e+00

Pos logit contributions
river+0.880
 guiActiveUn+0.870
usted+0.830
allery+0.759
atorial+0.758
Neg logit contributions
sters-0.705
NEY-0.694
 Cu-0.688
 Colo-0.668
thouse-0.664
Token
Token ID198
Feature activation-4.25e-01

Pos logit contributions
sters+0.305
NEY+0.298
 Cu+0.298
 Colo+0.288
thouse+0.285
Neg logit contributions
river-0.421
 guiActiveUn-0.420
usted-0.398
allery-0.367
atorial-0.366
TokenI
Token ID40
Feature activation-5.48e-01

Pos logit contributions
sters+0.274
NEY+0.268
 Cu+0.267
 Colo+0.259
thouse+0.256
Neg logit contributions
river-0.364
 guiActiveUn-0.363
usted-0.343
allery-0.317
atorial-0.316
Token gave
Token ID2921
Feature activation+3.15e-01

Pos logit contributions
sters+0.367
 Cu+0.359
NEY+0.359
 Colo+0.349
thouse+0.345
Neg logit contributions
river-0.455
 guiActiveUn-0.454
usted-0.429
allery-0.394
atorial-0.393
Token the
Token ID262
Feature activation-2.72e-01

Pos logit contributions
river+0.286
 guiActiveUn+0.285
usted+0.271
allery+0.250
atorial+0.250
Neg logit contributions
sters-0.187
NEY-0.183
 Cu-0.182
 Colo-0.176
thouse-0.174
Token st
Token ID336
Feature activation+2.34e+00

Pos logit contributions
sters+0.173
NEY+0.170
 Cu+0.170
 Colo+0.164
thouse+0.163
Neg logit contributions
river-0.234
 guiActiveUn-0.233
usted-0.221
allery-0.203
atorial-0.203
Tokenon
Token ID261
Feature activation-9.68e+00

Pos logit contributions
river+1.805
 guiActiveUn+1.775
usted+1.686
atorial+1.529
allery+1.526
Neg logit contributions
sters-1.705
NEY-1.697
 Cu-1.680
 Colo-1.643
thouse-1.610
Tokenework
Token ID6433
Feature activation+3.56e+00

Pos logit contributions
sters+7.397
 Cu+6.967
NEY+6.966
thouse+6.796
 Dob+6.543
Neg logit contributions
 guiActiveUn-6.955
river-6.673
usted-6.254
allery-5.844
atorial-5.542
Token a
Token ID257
Feature activation-1.11e+00

Pos logit contributions
river+3.132
 guiActiveUn+3.089
usted+2.958
atorial+2.731
allery+2.722
Neg logit contributions
sters-2.148
NEY-2.145
 Cu-2.101
 Colo-2.066
thouse-2.042
Token light
Token ID1657
Feature activation-6.39e-01

Pos logit contributions
sters+0.720
 Cu+0.709
NEY+0.700
 Colo+0.682
thouse+0.668
Neg logit contributions
river-0.943
 guiActiveUn-0.941
usted-0.886
allery-0.820
atorial-0.813
Token,
Token ID11
Feature activation+6.87e-01

Pos logit contributions
sters+0.431
 Cu+0.422
NEY+0.422
 Colo+0.410
thouse+0.405
Neg logit contributions
river-0.527
 guiActiveUn-0.526
usted-0.497
allery-0.456
atorial-0.455
Token m
Token ID285
Feature activation+3.13e-01

Pos logit contributions
river+0.574
 guiActiveUn+0.571
usted+0.542
atorial+0.497
allery+0.497
Neg logit contributions
sters-0.455
NEY-0.446
 Cu-0.444
 Colo-0.431
thouse-0.428
Token even
Token ID772
Feature activation-5.76e+00

Pos logit contributions
sters+0.919
 Cu+0.899
NEY+0.889
 Colo+0.866
thouse+0.843
Neg logit contributions
 guiActiveUn-1.343
river-1.329
usted-1.265
allery-1.169
atorial-1.167
Token the
Token ID262
Feature activation-4.02e+00

Pos logit contributions
sters+3.308
 Cu+3.208
NEY+3.075
 Colo+3.059
 Dob+2.977
Neg logit contributions
 guiActiveUn-5.515
river-5.239
usted-5.091
allery-4.746
atorial-4.727
Token millionaire
Token ID45172
Feature activation-4.52e+00

Pos logit contributions
sters+2.512
 Cu+2.471
NEY+2.414
 Colo+2.360
 Canary+2.287
Neg logit contributions
 guiActiveUn-3.567
river-3.519
usted-3.338
allery-3.105
atorial-3.091
Token owners
Token ID4393
Feature activation-4.13e+00

Pos logit contributions
sters+2.916
 Cu+2.826
NEY+2.721
 Colo+2.708
 Dob+2.643
Neg logit contributions
 guiActiveUn-4.023
river-3.872
usted-3.700
allery-3.455
atorial-3.417
Token and
Token ID290
Feature activation-6.32e+00

Pos logit contributions
sters+2.625
 Cu+2.500
NEY+2.455
 Colo+2.448
 Dob+2.348
Neg logit contributions
 guiActiveUn-3.680
river-3.574
usted-3.362
allery-3.164
atorial-3.105
Token shareholders
Token ID19195
Feature activation-9.67e+00

Pos logit contributions
sters+3.804
 Cu+3.678
 Colo+3.541
NEY+3.530
 Dob+3.436
Neg logit contributions
 guiActiveUn-5.862
river-5.611
usted-5.348
atorial-4.996
allery-4.942
Token of
Token ID286
Feature activation-4.02e+00

Pos logit contributions
sters+6.061
 Cu+5.664
 Colo+5.543
NEY+5.469
 Dob+5.365
Neg logit contributions
 guiActiveUn-8.559
river-8.013
usted-7.435
allery-7.147
umbn-7.137
Token Mor
Token ID3461
Feature activation+2.08e+00

Pos logit contributions
sters+2.434
 Cu+2.386
NEY+2.318
 Colo+2.284
 Canary+2.230
Neg logit contributions
 guiActiveUn-3.683
river-3.567
usted-3.411
atorial-3.177
allery-3.175
Tokenneau
Token ID46533
Feature activation+3.32e+00

Pos logit contributions
river+2.193
 guiActiveUn+2.133
usted+2.099
atorial+1.968
allery+1.944
Neg logit contributions
sters-0.897
NEY-0.887
 Cu-0.879
 Colo-0.844
thouse-0.819
Token She
Token ID1375
Feature activation-1.85e+00

Pos logit contributions
river+2.621
 guiActiveUn+2.601
usted+2.472
allery+2.269
atorial+2.250
Neg logit contributions
sters-2.304
NEY-2.289
 Cu-2.252
 Colo-2.210
thouse-2.210
Tokenpell
Token ID23506
Feature activation+1.55e+00

Pos logit contributions
sters+1.270
 Cu+1.244
NEY+1.244
 Colo+1.208
thouse+1.195
Neg logit contributions
river-1.503
 guiActiveUn-1.499
usted-1.414
allery-1.296
atorial-1.294
Token,
Token ID11
Feature activation+1.78e-01

Pos logit contributions
 guiActiveUn+0.719
river+0.719
usted+0.679
allery+0.624
atorial+0.622
Neg logit contributions
sters-0.575
 Cu-0.562
NEY-0.561
 Colo-0.546
thouse-0.538
Token this
Token ID428
Feature activation+1.98e-01

Pos logit contributions
river+0.165
 guiActiveUn+0.165
usted+0.157
allery+0.145
atorial+0.145
Neg logit contributions
sters-0.102
 Cu-0.099
NEY-0.099
 Colo-0.096
thouse-0.094
Token
Token ID39073
Feature activation-1.00e+00

Pos logit contributions
river+0.164
 guiActiveUn+0.164
usted+0.154
allery+0.142
atorial+0.142
Neg logit contributions
sters-0.132
 Cu-0.130
NEY-0.129
 Colo-0.126
thouse-0.124
Tokenj
Token ID73
Feature activation+1.69e+00

Pos logit contributions
sters+0.669
 Cu+0.651
NEY+0.647
 Colo+0.631
thouse+0.625
Neg logit contributions
 guiActiveUn-0.839
river-0.836
usted-0.790
allery-0.726
atorial-0.724
Tokenà
Token ID24247
Feature activation-3.10e+00

Pos logit contributions
river+0.899
 guiActiveUn+0.896
usted+0.820
atorial+0.716
allery+0.710
Neg logit contributions
sters-1.637
NEY-1.607
 Cu-1.591
 Colo-1.571
thouse-1.567
Token v
Token ID410
Feature activation-9.64e+00

Pos logit contributions
sters+1.347
 Cu+1.331
NEY+1.312
 Colo+1.255
thouse+1.223
Neg logit contributions
 guiActiveUn-3.281
river-3.279
usted-3.127
allery-2.942
atorial-2.934
Tokenu
Token ID84
Feature activation-2.65e+00

Pos logit contributions
 Cu+6.054
 Colo+5.783
sters+5.779
Va+5.652
riad+5.417
Neg logit contributions
 guiActiveUn-8.087
river-7.511
usted-7.267
atorial-6.700
allery-6.694
Token isn
Token ID2125
Feature activation-2.40e+00

Pos logit contributions
sters+1.672
 Cu+1.633
NEY+1.622
 Colo+1.573
thouse+1.553
Neg logit contributions
 guiActiveUn-2.296
river-2.282
usted-2.147
allery-2.003
atorial-1.968
Token
Token ID447
Feature activation+8.33e-01

Pos logit contributions
sters+1.385
 Cu+1.352
NEY+1.351
 Colo+1.305
thouse+1.288
Neg logit contributions
river-2.214
 guiActiveUn-2.214
usted-2.100
allery-1.949
atorial-1.942
Token
Token ID247
Feature activation+9.32e-02

Pos logit contributions
river+0.688
 guiActiveUn+0.678
usted+0.650
atorial+0.599
allery+0.591
Neg logit contributions
sters-0.566
NEY-0.547
 Cu-0.545
 Colo-0.526
thouse-0.523
Tokent
Token ID83
Feature activation-2.18e+00

Pos logit contributions
river+0.083
 guiActiveUn+0.083
usted+0.079
atorial+0.073
allery+0.073
Neg logit contributions
sters-0.056
NEY-0.055
 Cu-0.055
 Colo-0.053
thouse-0.052
Token the
Token ID262
Feature activation+1.72e+00

Pos logit contributions
river+1.702
 guiActiveUn+1.688
usted+1.619
atorial+1.496
allery+1.494
Neg logit contributions
sters-1.079
NEY-1.064
 Cu-1.050
thouse-1.023
 Colo-1.022
Token anti
Token ID3098
Feature activation-4.95e+00

Pos logit contributions
river+1.434
 guiActiveUn+1.422
usted+1.356
atorial+1.249
allery+1.244
Neg logit contributions
sters-1.130
NEY-1.118
 Cu-1.104
thouse-1.081
 Colo-1.081
Token-
Token ID12
Feature activation-3.18e-01

Pos logit contributions
sters+2.775
 Cu+2.671
NEY+2.636
 Colo+2.543
thouse+2.487
Neg logit contributions
 guiActiveUn-4.713
river-4.632
usted-4.391
allery-4.151
atorial-4.052
Tokenwar
Token ID5767
Feature activation-1.53e+00

Pos logit contributions
sters+0.216
 Cu+0.211
NEY+0.210
 Colo+0.204
thouse+0.202
Neg logit contributions
 guiActiveUn-0.262
river-0.261
usted-0.245
allery-0.227
atorial-0.225
Token,
Token ID11
Feature activation+4.45e-01

Pos logit contributions
sters+0.967
 Cu+0.940
NEY+0.933
 Colo+0.903
thouse+0.891
Neg logit contributions
 guiActiveUn-1.349
river-1.346
usted-1.269
allery-1.173
atorial-1.167
Token anti
Token ID3098
Feature activation-9.64e+00

Pos logit contributions
river+0.327
 guiActiveUn+0.326
usted+0.306
allery+0.277
atorial+0.277
Neg logit contributions
sters-0.341
 Cu-0.335
NEY-0.334
 Colo-0.326
thouse-0.323
Token-
Token ID12
Feature activation-2.62e+00

Pos logit contributions
sters+4.680
 Cu+4.473
NEY+4.282
 Colo+4.118
Va+4.065
Neg logit contributions
 guiActiveUn-10.027
river-9.362
usted-9.013
allery-8.828
umbn-8.511
Tokennuclear
Token ID43131
Feature activation-3.47e+00

Pos logit contributions
sters+1.096
 Cu+1.045
NEY+1.035
thouse+0.962
 Colo+0.959
Neg logit contributions
 guiActiveUn-2.856
river-2.826
usted-2.688
allery-2.567
atorial-2.522
Token,
Token ID11
Feature activation-1.69e+00

Pos logit contributions
sters+2.259
 Cu+2.202
NEY+2.143
 Colo+2.099
 Canary+2.038
Neg logit contributions
 guiActiveUn-3.005
river-2.977
usted-2.801
allery-2.590
atorial-2.556
Token peace
Token ID4167
Feature activation-2.32e+00

Pos logit contributions
sters+1.348
 Cu+1.325
NEY+1.314
 Colo+1.284
thouse+1.267
Neg logit contributions
 guiActiveUn-1.190
river-1.189
usted-1.101
allery-0.997
atorial-0.990
Token movement
Token ID3356
Feature activation+1.21e+00

Pos logit contributions
sters+1.141
 Cu+1.083
NEY+1.066
 Colo+1.025
thouse+1.005
Neg logit contributions
 guiActiveUn-2.369
river-2.355
usted-2.244
allery-2.108
atorial-2.079
TokenDoS
Token ID46498
Feature activation+4.01e-01

Pos logit contributions
sters+0.906
NEY+0.888
 Cu+0.879
 Colo+0.847
thouse+0.841
Neg logit contributions
 guiActiveUn-1.211
river-1.195
usted-1.131
allery-1.053
atorial-1.049
Token Mit
Token ID11707
Feature activation-8.10e-01

Pos logit contributions
river+0.297
 guiActiveUn+0.296
usted+0.277
allery+0.252
atorial+0.251
Neg logit contributions
sters-0.304
 Cu-0.299
NEY-0.298
 Colo-0.291
thouse-0.288
Tokenigation
Token ID7065
Feature activation+1.64e+00

Pos logit contributions
sters+0.544
 Cu+0.531
NEY+0.528
 Colo+0.516
thouse+0.509
Neg logit contributions
 guiActiveUn-0.673
river-0.671
usted-0.630
allery-0.580
atorial-0.579
Token
Token ID784
Feature activation-1.31e+00

Pos logit contributions
river+1.446
 guiActiveUn+1.427
usted+1.372
atorial+1.261
allery+1.259
Neg logit contributions
sters-0.991
NEY-0.980
 Cu-0.957
thouse-0.943
 Colo-0.937
Token No
Token ID1400
Feature activation-2.09e+00

Pos logit contributions
sters+0.785
 Cu+0.773
NEY+0.764
 Colo+0.743
thouse+0.727
Neg logit contributions
 guiActiveUn-1.186
river-1.182
usted-1.118
allery-1.039
atorial-1.037
Token Silver
Token ID7698
Feature activation+7.64e+00

Pos logit contributions
sters+1.249
 Cu+1.226
NEY+1.207
 Colo+1.177
thouse+1.144
Neg logit contributions
 guiActiveUn-1.886
river-1.883
usted-1.776
allery-1.651
atorial-1.649
Token Bullet
Token ID18003
Feature activation-3.33e-02

Pos logit contributions
river+6.866
 guiActiveUn+6.545
usted+6.475
atorial+5.897
allery+5.794
Neg logit contributions
NEY-4.455
sters-4.317
 Colo-4.093
thouse-4.008
 Cu-3.967
Token
Token ID198
Feature activation+1.38e+00

Pos logit contributions
sters+0.021
 Cu+0.020
NEY+0.020
 Colo+0.020
thouse+0.019
Neg logit contributions
river-0.029
 guiActiveUn-0.029
usted-0.027
allery-0.025
atorial-0.025
Token
Token ID198
Feature activation-1.36e+00

Pos logit contributions
river+1.119
 guiActiveUn+1.052
usted+1.042
atorial+0.953
allery+0.917
Neg logit contributions
sters-0.944
NEY-0.931
 Cu-0.921
 Colo-0.909
thouse-0.909
TokenDue
Token ID22229
Feature activation+1.32e+00

Pos logit contributions
sters+0.861
NEY+0.844
 Cu+0.840
 Colo+0.809
thouse+0.799
Neg logit contributions
 guiActiveUn-1.183
river-1.169
usted-1.105
allery-1.033
atorial-1.024
Token to
Token ID284
Feature activation+7.08e-01

Pos logit contributions
river+0.986
 guiActiveUn+0.972
usted+0.919
atorial+0.834
allery+0.829
Neg logit contributions
sters-0.980
NEY-0.966
 Cu-0.960
 Colo-0.944
thouse-0.938
Token living
Token ID2877
Feature activation+2.34e+00

Pos logit contributions
river+1.401
 guiActiveUn+1.399
usted+1.324
allery+1.222
atorial+1.220
Neg logit contributions
sters-1.011
 Cu-0.988
NEY-0.988
 Colo-0.957
thouse-0.945
Token together
Token ID1978
Feature activation+1.46e+00

Pos logit contributions
river+1.915
 guiActiveUn+1.809
usted+1.770
atorial+1.635
allery+1.582
Neg logit contributions
NEY-1.592
sters-1.580
 Cu-1.557
thouse-1.513
 Colo-1.512
Token.
Token ID13
Feature activation-2.31e+00

Pos logit contributions
 guiActiveUn+1.171
river+1.168
usted+1.104
allery+1.008
atorial+1.007
Neg logit contributions
sters-1.016
 Cu-0.998
NEY-0.995
 Colo-0.970
thouse-0.958
Token The
Token ID383
Feature activation+5.60e-01

Pos logit contributions
sters+1.258
 Cu+1.242
NEY+1.213
 Colo+1.183
thouse+1.160
Neg logit contributions
 guiActiveUn-2.206
river-2.172
usted-2.083
allery-1.933
atorial-1.932
Token epic
Token ID12191
Feature activation-3.08e-01

Pos logit contributions
river+0.350
 guiActiveUn+0.350
usted+0.323
allery+0.288
atorial+0.287
Neg logit contributions
sters-0.489
 Cu-0.481
NEY-0.481
 Colo-0.470
thouse-0.467
Token ghost
Token ID10905
Feature activation+7.35e+00

Pos logit contributions
sters+0.194
 Cu+0.189
NEY+0.189
 Colo+0.182
thouse+0.180
Neg logit contributions
 guiActiveUn-0.268
river-0.268
usted-0.253
allery-0.235
atorial-0.234
Token invasion
Token ID11796
Feature activation-3.06e+00

Pos logit contributions
river+4.975
 guiActiveUn+4.618
usted+4.387
atorial+4.197
allery+3.920
Neg logit contributions
NEY-5.789
sters-5.740
thouse-5.730
 Wink-5.522
 Canary-5.499
Token of
Token ID286
Feature activation-3.48e+00

Pos logit contributions
sters+1.711
 Cu+1.670
NEY+1.664
 Colo+1.606
thouse+1.583
Neg logit contributions
 guiActiveUn-2.889
river-2.883
usted-2.738
allery-2.551
atorial-2.538
Token the
Token ID262
Feature activation-5.50e-01

Pos logit contributions
sters+1.759
 Cu+1.720
NEY+1.710
 Colo+1.645
thouse+1.618
Neg logit contributions
 guiActiveUn-3.465
river-3.448
usted-3.288
allery-3.075
atorial-3.065
Token big
Token ID1263
Feature activation+5.61e+00

Pos logit contributions
sters+0.346
 Cu+0.339
NEY+0.336
 Colo+0.327
thouse+0.322
Neg logit contributions
 guiActiveUn-0.482
river-0.479
usted-0.453
allery-0.419
atorial-0.416
Token Apple
Token ID4196
Feature activation+3.37e+00

Pos logit contributions
river+5.326
 guiActiveUn+5.148
usted+5.051
allery+4.683
atorial+4.640
Neg logit contributions
sters-3.036
NEY-2.937
 Colo-2.829
 Cu-2.797
thouse-2.784
Token has
Token ID468
Feature activation+1.29e+00

Pos logit contributions
river+0.477
 guiActiveUn+0.476
usted+0.448
allery+0.407
atorial+0.406
Neg logit contributions
sters-0.455
 Cu-0.446
NEY-0.446
 Colo-0.435
thouse-0.430
Token learned
Token ID4499
Feature activation-4.16e-01

Pos logit contributions
river+0.954
 guiActiveUn+0.947
usted+0.898
atorial+0.808
allery+0.806
Neg logit contributions
sters-0.978
NEY-0.963
 Cu-0.960
 Colo-0.934
thouse-0.926
Token.
Token ID13
Feature activation-1.05e+00

Pos logit contributions
sters+0.284
 Cu+0.278
NEY+0.278
 Colo+0.270
thouse+0.269
Neg logit contributions
 guiActiveUn-0.338
river-0.338
usted-0.317
allery-0.294
atorial-0.293
Token
Token ID198
Feature activation+2.61e-02

Pos logit contributions
sters+0.634
 Cu+0.622
NEY+0.619
 Colo+0.600
thouse+0.591
Neg logit contributions
river-0.939
 guiActiveUn-0.938
usted-0.887
allery-0.824
atorial-0.819
Token
Token ID198
Feature activation+1.32e-01

Pos logit contributions
river+0.022
 guiActiveUn+0.021
usted+0.020
atorial+0.019
allery+0.018
Neg logit contributions
sters-0.017
NEY-0.017
 Cu-0.017
 Colo-0.017
thouse-0.017
TokenReg
Token ID8081
Feature activation+7.33e+00

Pos logit contributions
river+0.115
 guiActiveUn+0.115
usted+0.109
allery+0.101
atorial+0.101
Neg logit contributions
sters-0.083
NEY-0.081
 Cu-0.081
 Colo-0.079
thouse-0.078
Tokenulators
Token ID24325
Feature activation+3.05e+00

Pos logit contributions
river+5.972
 guiActiveUn+5.735
usted+5.731
atorial+5.212
allery+5.176
Neg logit contributions
sters-4.729
NEY-4.726
 Cu-4.633
 Colo-4.626
 Canary-4.421
Token are
Token ID389
Feature activation+1.13e+00

Pos logit contributions
river+2.516
 guiActiveUn+2.480
usted+2.404
atorial+2.167
allery+2.153
Neg logit contributions
sters-2.006
NEY-1.991
 Cu-1.949
thouse-1.913
 Colo-1.905
Token apparently
Token ID5729
Feature activation-1.28e+00

Pos logit contributions
river+0.910
 guiActiveUn+0.906
usted+0.857
allery+0.783
atorial+0.782
Neg logit contributions
sters-0.782
NEY-0.767
 Cu-0.765
 Colo-0.744
thouse-0.737
Token interested
Token ID4609
Feature activation+8.29e-01

Pos logit contributions
sters+0.907
 Cu+0.890
NEY+0.881
 Colo+0.862
thouse+0.850
Neg logit contributions
 guiActiveUn-1.017
river-1.008
usted-0.943
allery-0.877
atorial-0.868
Token in
Token ID287
Feature activation-1.16e+00

Pos logit contributions
 guiActiveUn+0.727
river+0.726
usted+0.685
allery+0.634
atorial+0.632
Neg logit contributions
sters-0.519
 Cu-0.509
NEY-0.506
 Colo-0.491
thouse-0.484
Token to
Token ID284
Feature activation+3.52e+00

Pos logit contributions
river+4.013
 guiActiveUn+3.888
usted+3.689
atorial+3.344
allery+3.336
Neg logit contributions
sters-3.865
 Cu-3.832
NEY-3.802
 Colo-3.701
thouse-3.688
Token 75
Token ID5441
Feature activation+1.94e+00

Pos logit contributions
river+3.179
 guiActiveUn+3.156
usted+3.002
allery+2.783
atorial+2.776
Neg logit contributions
sters-2.062
NEY-2.045
 Cu-2.006
thouse-1.953
 Colo-1.923
Token%
Token ID4
Feature activation+2.72e+00

Pos logit contributions
river+1.863
 guiActiveUn+1.859
usted+1.771
allery+1.645
atorial+1.644
Neg logit contributions
sters-1.045
 Cu-1.019
NEY-1.018
 Colo-0.981
thouse-0.967
Token of
Token ID286
Feature activation+5.10e+00

Pos logit contributions
river+2.497
 guiActiveUn+2.492
usted+2.362
allery+2.192
atorial+2.191
Neg logit contributions
sters-1.573
 Cu-1.536
NEY-1.533
 Colo-1.482
thouse-1.462
Token the
Token ID262
Feature activation+4.87e+00

Pos logit contributions
river+4.392
 guiActiveUn+4.311
usted+4.110
allery+3.821
atorial+3.780
Neg logit contributions
sters-3.210
NEY-3.148
 Cu-3.116
thouse-3.037
 Colo-3.013
Token cost
Token ID1575
Feature activation+7.20e+00

Pos logit contributions
river+3.645
 guiActiveUn+3.598
usted+3.399
allery+3.098
atorial+3.089
Neg logit contributions
sters-3.619
NEY-3.554
 Cu-3.524
thouse-3.444
 Colo-3.430
Token of
Token ID286
Feature activation+5.56e-01

Pos logit contributions
river+5.965
 guiActiveUn+5.860
usted+5.562
atorial+5.160
allery+5.037
Neg logit contributions
NEY-4.482
 Cu-4.446
sters-4.445
 Colo-4.316
thouse-4.306
Token repairing
Token ID39005
Feature activation-6.24e+00

Pos logit contributions
 guiActiveUn+0.480
river+0.480
usted+0.454
allery+0.419
atorial+0.418
Neg logit contributions
sters-0.353
 Cu-0.346
NEY-0.345
 Colo-0.335
thouse-0.330
Token their
Token ID511
Feature activation-1.06e+00

Pos logit contributions
sters+4.081
 Cu+3.988
NEY+3.911
 Colo+3.861
 Canary+3.754
Neg logit contributions
 guiActiveUn-5.279
river-5.022
usted-4.781
atorial-4.473
allery-4.405
Token sidewalks
Token ID38282
Feature activation-4.24e+00

Pos logit contributions
sters+0.849
 Cu+0.834
NEY+0.829
 Colo+0.812
thouse+0.798
Neg logit contributions
 guiActiveUn-0.750
river-0.745
usted-0.693
atorial-0.627
allery-0.626
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
sters+2.586
 Cu+2.491
NEY+2.484
 Colo+2.413
thouse+2.354
Neg logit contributions
 guiActiveUn-3.758
river-3.661
usted-3.514
allery-3.295
atorial-3.254
Token 10
Token ID838
Feature activation-6.55e+00

Pos logit contributions
river+0.333
 guiActiveUn+0.323
usted+0.315
atorial+0.292
allery+0.286
Neg logit contributions
sters-0.204
NEY-0.201
 Cu-0.194
thouse-0.190
 Colo-0.190
Token of
Token ID286
Feature activation-1.04e+00

Pos logit contributions
sters+3.236
 Cu+3.185
NEY+3.103
 Colo+2.970
thouse+2.903
Neg logit contributions
 guiActiveUn-6.762
river-6.488
usted-6.202
allery-5.997
atorial-5.784
Token 15
Token ID1315
Feature activation-8.79e-01

Pos logit contributions
sters+0.518
NEY+0.506
 Cu+0.503
 Colo+0.486
thouse+0.479
Neg logit contributions
river-1.039
 guiActiveUn-1.028
usted-0.986
atorial-0.921
allery-0.913
Token Photo
Token ID5555
Feature activation-5.00e+00

Pos logit contributions
sters+0.496
NEY+0.482
 Cu+0.479
 Colo+0.462
thouse+0.461
Neg logit contributions
river-0.823
 guiActiveUn-0.812
usted-0.778
atorial-0.721
allery-0.720
Token:
Token ID25
Feature activation+4.42e+00

Pos logit contributions
sters+2.616
 Cu+2.561
NEY+2.529
 Colo+2.429
thouse+2.356
Neg logit contributions
 guiActiveUn-5.018
river-4.839
usted-4.652
allery-4.405
atorial-4.330
Token Erin
Token ID28894
Feature activation+7.24e+00

Pos logit contributions
river+3.914
 guiActiveUn+3.859
usted+3.689
allery+3.419
atorial+3.385
Neg logit contributions
sters-2.680
NEY-2.618
 Cu-2.565
thouse-2.511
 Colo-2.495
Token Bre
Token ID3719
Feature activation-3.19e-03

Pos logit contributions
river+5.415
usted+4.975
 guiActiveUn+4.820
atorial+4.496
ariat+4.442
Neg logit contributions
sters-5.015
NEY-4.820
thouse-4.747
ADRA-4.506
Va-4.449
Tokenth
Token ID400
Feature activation+3.27e-01

Pos logit contributions
sters+0.002
NEY+0.002
 Cu+0.002
 Colo+0.002
thouse+0.002
Neg logit contributions
river-0.003
 guiActiveUn-0.003
usted-0.003
atorial-0.003
allery-0.003
Tokenauer
Token ID16261
Feature activation+4.34e-01

Pos logit contributions
river+0.158
 guiActiveUn+0.153
usted+0.142
atorial+0.121
allery+0.119
Neg logit contributions
sters-0.334
NEY-0.331
 Cu-0.330
 Colo-0.324
thouse-0.320
Token,
Token ID11
Feature activation+3.72e+00

Pos logit contributions
river+0.335
 guiActiveUn+0.324
usted+0.310
atorial+0.283
allery+0.279
Neg logit contributions
sters-0.314
NEY-0.307
 Cu-0.303
thouse-0.298
 Colo-0.296
Token The
Token ID383
Feature activation+4.22e+00

Pos logit contributions
river+2.984
usted+2.740
 guiActiveUn+2.732
atorial+2.485
ariat+2.407
Neg logit contributions
sters-2.535
NEY-2.462
thouse-2.368
 Cu-2.344
 Colo-2.331
Token would
Token ID561
Feature activation-8.72e-01

Pos logit contributions
river+2.534
 guiActiveUn+2.519
usted+2.382
atorial+2.203
allery+2.183
Neg logit contributions
NEY-2.051
sters-2.048
 Cu-2.045
 Colo-1.992
thouse-1.978
Token have
Token ID423
Feature activation+1.25e+00

Pos logit contributions
sters+0.598
 Cu+0.587
NEY+0.585
 Colo+0.568
thouse+0.561
Neg logit contributions
river-0.710
 guiActiveUn-0.710
usted-0.669
allery-0.614
atorial-0.610
Token ignited
Token ID40442
Feature activation+2.09e-02

Pos logit contributions
river+0.947
 guiActiveUn+0.936
usted+0.887
atorial+0.805
allery+0.803
Neg logit contributions
sters-0.921
NEY-0.906
 Cu-0.902
 Colo-0.878
thouse-0.878
Token.
Token ID13
Feature activation+3.91e-01

Pos logit contributions
 guiActiveUn+0.019
river+0.019
usted+0.018
allery+0.016
atorial+0.016
Neg logit contributions
sters-0.013
 Cu-0.013
NEY-0.012
 Colo-0.012
thouse-0.012
Token
Token ID198
Feature activation+5.04e-01

Pos logit contributions
river+0.346
 guiActiveUn+0.343
usted+0.327
atorial+0.302
allery+0.300
Neg logit contributions
sters-0.239
NEY-0.235
 Cu-0.232
 Colo-0.225
thouse-0.224
Token
Token ID198
Feature activation+1.85e+00

Pos logit contributions
river+0.415
 guiActiveUn+0.396
usted+0.388
atorial+0.357
allery+0.346
Neg logit contributions
sters-0.338
NEY-0.333
 Cu-0.330
thouse-0.324
 Colo-0.324
TokenQ
Token ID48
Feature activation+8.14e-02

Pos logit contributions
river+1.637
 guiActiveUn+1.618
usted+1.549
atorial+1.432
allery+1.419
Neg logit contributions
sters-1.130
 Cu-1.108
NEY-1.089
 Colo-1.070
thouse-1.058
Token:
Token ID25
Feature activation+1.61e+00

Pos logit contributions
river+0.072
 guiActiveUn+0.069
usted+0.068
atorial+0.062
allery+0.061
Neg logit contributions
sters-0.049
NEY-0.049
 Cu-0.048
 Colo-0.047
thouse-0.047
Token It
Token ID632
Feature activation-1.24e+00

Pos logit contributions
river+1.404
 guiActiveUn+1.379
usted+1.327
atorial+1.231
allery+1.217
Neg logit contributions
sters-0.996
NEY-0.970
 Cu-0.948
thouse-0.946
 Colo-0.923
Token would
Token ID561
Feature activation-1.88e+00

Pos logit contributions
sters+0.786
 Cu+0.768
NEY+0.763
 Colo+0.743
thouse+0.731
Neg logit contributions
 guiActiveUn-1.072
river-1.071
usted-1.008
allery-0.934
atorial-0.928
Token have
Token ID423
Feature activation+4.46e-01

Pos logit contributions
sters+1.205
 Cu+1.176
NEY+1.174
 Colo+1.134
thouse+1.119
Neg logit contributions
 guiActiveUn-1.616
river-1.614
usted-1.526
allery-1.408
atorial-1.395
Token;
Token ID26
Feature activation-1.35e+00

Pos logit contributions
sters+0.795
 Cu+0.776
NEY+0.776
 Colo+0.750
thouse+0.740
Neg logit contributions
 guiActiveUn-1.012
river-1.006
usted-0.953
allery-0.876
atorial-0.872
Token what
Token ID644
Feature activation-1.35e+00

Pos logit contributions
sters+0.814
 Cu+0.803
NEY+0.796
 Colo+0.774
thouse+0.754
Neg logit contributions
 guiActiveUn-1.210
river-1.202
usted-1.139
allery-1.054
atorial-1.052
Token would
Token ID561
Feature activation-1.57e+00

Pos logit contributions
sters+0.851
 Cu+0.835
NEY+0.830
 Colo+0.807
thouse+0.794
Neg logit contributions
 guiActiveUn-1.178
river-1.177
usted-1.113
allery-1.026
atorial-1.025
Token you
Token ID345
Feature activation+6.17e-01

Pos logit contributions
sters+0.933
 Cu+0.920
NEY+0.909
 Colo+0.882
thouse+0.856
Neg logit contributions
 guiActiveUn-1.433
river-1.429
usted-1.353
allery-1.252
atorial-1.249
Token give
Token ID1577
Feature activation+3.39e+00

Pos logit contributions
river+0.531
 guiActiveUn+0.530
usted+0.501
allery+0.462
atorial+0.461
Neg logit contributions
sters-0.394
 Cu-0.386
NEY-0.385
 Colo-0.373
thouse-0.369
Token up
Token ID510
Feature activation+5.38e+00

Pos logit contributions
river+2.916
 guiActiveUn+2.824
usted+2.724
allery+2.512
atorial+2.511
Neg logit contributions
sters-2.110
NEY-2.087
thouse-2.049
 Cu-2.030
 Colo-1.996
Token for
Token ID329
Feature activation+3.02e+00

Pos logit contributions
river+4.383
 guiActiveUn+4.173
usted+4.065
atorial+3.735
allery+3.678
Neg logit contributions
NEY-3.534
sters-3.511
 Cu-3.451
 Colo-3.423
thouse-3.415
Token your
Token ID534
Feature activation-2.06e-01

Pos logit contributions
river+2.748
 guiActiveUn+2.690
usted+2.594
allery+2.400
atorial+2.398
Neg logit contributions
sters-1.737
NEY-1.691
 Cu-1.664
thouse-1.652
 Colo-1.633
Token loved
Token ID6151
Feature activation+1.71e+00

Pos logit contributions
sters+0.143
 Cu+0.140
NEY+0.140
 Colo+0.136
thouse+0.135
Neg logit contributions
river-0.165
 guiActiveUn-0.165
usted-0.155
allery-0.142
atorial-0.142
Token ones
Token ID3392
Feature activation+6.81e-01

Pos logit contributions
river+1.289
 guiActiveUn+1.272
usted+1.203
atorial+1.093
allery+1.089
Neg logit contributions
sters-1.276
 Cu-1.254
NEY-1.252
 Colo-1.227
thouse-1.219
Token?
Token ID30
Feature activation+1.64e+00

Pos logit contributions
river+0.604
 guiActiveUn+0.602
usted+0.571
allery+0.527
atorial+0.527
Neg logit contributions
sters-0.416
 Cu-0.407
NEY-0.406
 Colo-0.393
thouse-0.389
Token series
Token ID2168
Feature activation+1.89e+00

Pos logit contributions
river+0.090
 guiActiveUn+0.090
usted+0.085
allery+0.078
atorial+0.078
Neg logit contributions
sters-0.074
 Cu-0.073
NEY-0.073
 Colo-0.071
thouse-0.070
Token of
Token ID286
Feature activation-2.23e-01

Pos logit contributions
river+1.632
 guiActiveUn+1.622
usted+1.552
atorial+1.418
allery+1.417
Neg logit contributions
sters-1.185
NEY-1.172
 Cu-1.163
 Colo-1.129
thouse-1.122
Token 5
Token ID642
Feature activation+4.10e+00

Pos logit contributions
sters+0.144
 Cu+0.141
NEY+0.140
 Colo+0.136
thouse+0.134
Neg logit contributions
river-0.191
 guiActiveUn-0.191
usted-0.180
allery-0.166
atorial-0.166
Token commercials
Token ID30503
Feature activation-8.47e-01

Pos logit contributions
river+3.465
 guiActiveUn+3.427
usted+3.270
allery+3.005
atorial+2.978
Neg logit contributions
sters-2.640
NEY-2.603
 Cu-2.574
thouse-2.517
 Colo-2.514
Token run
Token ID1057
Feature activation+1.28e-01

Pos logit contributions
sters+0.539
 Cu+0.526
NEY+0.520
 Colo+0.507
thouse+0.498
Neg logit contributions
 guiActiveUn-0.736
river-0.735
usted-0.692
allery-0.641
atorial-0.641
Token any
Token ID597
Feature activation+1.07e+00

Pos logit contributions
river+0.114
 guiActiveUn+0.114
usted+0.108
allery+0.100
atorial+0.099
Neg logit contributions
sters-0.078
 Cu-0.077
NEY-0.077
 Colo-0.074
thouse-0.073
Token old
Token ID1468
Feature activation+4.47e-01

Pos logit contributions
river+0.901
 guiActiveUn+0.898
usted+0.850
allery+0.782
atorial+0.781
Neg logit contributions
sters-0.697
 Cu-0.682
NEY-0.682
 Colo-0.661
thouse-0.654
Token time
Token ID640
Feature activation+2.96e-02

Pos logit contributions
river+0.392
 guiActiveUn+0.391
usted+0.370
allery+0.342
atorial+0.341
Neg logit contributions
sters-0.278
NEY-0.272
 Cu-0.272
 Colo-0.263
thouse-0.260
Token on
Token ID319
Feature activation-1.78e+00

Pos logit contributions
river+0.025
 guiActiveUn+0.025
usted+0.024
allery+0.022
atorial+0.022
Neg logit contributions
sters-0.019
 Cu-0.019
NEY-0.019
 Colo-0.018
thouse-0.018
Token Canadian
Token ID5398
Feature activation-1.29e+00

Pos logit contributions
sters+1.024
 Cu+1.001
NEY+0.992
 Colo+0.964
thouse+0.939
Neg logit contributions
 guiActiveUn-1.653
river-1.641
usted-1.553
atorial-1.449
allery-1.446
Token TV
Token ID3195
Feature activation-3.87e-01

Pos logit contributions
sters+0.726
 Cu+0.710
NEY+0.707
 Colo+0.682
thouse+0.672
Neg logit contributions
 guiActiveUn-1.208
river-1.207
usted-1.144
allery-1.065
atorial-1.062
Token mean
Token ID1612
Feature activation+1.68e+00

Pos logit contributions
river+0.678
 guiActiveUn+0.674
usted+0.639
atorial+0.583
allery+0.583
Neg logit contributions
sters-0.587
NEY-0.575
 Cu-0.575
 Colo-0.559
thouse-0.553
Token
Token ID851
Feature activation-1.66e+00

Pos logit contributions
river+1.399
 guiActiveUn+1.395
usted+1.318
allery+1.211
atorial+1.211
Neg logit contributions
sters-1.113
NEY-1.090
 Cu-1.088
 Colo-1.055
thouse-1.047
Token for
Token ID329
Feature activation+2.62e+00

Pos logit contributions
sters+1.068
 Cu+1.058
NEY+1.042
 Colo+1.024
thouse+0.996
Neg logit contributions
 guiActiveUn-1.422
river-1.420
usted-1.340
allery-1.236
atorial-1.228
Token example
Token ID1672
Feature activation-1.23e+00

Pos logit contributions
river+2.033
 guiActiveUn+2.019
usted+1.903
allery+1.751
atorial+1.743
Neg logit contributions
sters-1.861
NEY-1.829
 Cu-1.815
 Colo-1.766
thouse-1.762
Token,
Token ID11
Feature activation+1.46e+00

Pos logit contributions
sters+0.784
 Cu+0.778
NEY+0.768
 Colo+0.752
thouse+0.734
Neg logit contributions
 guiActiveUn-1.058
river-1.055
usted-1.003
allery-0.922
atorial-0.916
Token I
Token ID314
Feature activation+1.94e+00

Pos logit contributions
river+1.254
 guiActiveUn+1.242
usted+1.182
atorial+1.091
allery+1.089
Neg logit contributions
sters-0.928
NEY-0.909
 Cu-0.900
thouse-0.873
 Colo-0.872
Token don
Token ID836
Feature activation+3.60e-01

Pos logit contributions
river+1.603
 guiActiveUn+1.582
usted+1.512
atorial+1.384
allery+1.379
Neg logit contributions
sters-1.295
 Cu-1.269
NEY-1.269
 Colo-1.232
thouse-1.218
Token
Token ID447
Feature activation+1.87e+00

Pos logit contributions
river+0.316
 guiActiveUn+0.307
usted+0.296
atorial+0.275
allery+0.269
Neg logit contributions
sters-0.224
 Cu-0.219
NEY-0.219
 Colo-0.213
thouse-0.210
Token
Token ID247
Feature activation+3.11e-01

Pos logit contributions
river+1.542
 guiActiveUn+1.502
usted+1.457
atorial+1.350
allery+1.313
Neg logit contributions
sters-1.277
NEY-1.234
 Cu-1.231
 Colo-1.192
thouse-1.181
Tokent
Token ID83
Feature activation+7.29e-01

Pos logit contributions
river+0.275
 guiActiveUn+0.269
usted+0.259
atorial+0.240
allery+0.238
Neg logit contributions
sters-0.191
NEY-0.188
 Cu-0.188
 Colo-0.182
thouse-0.178
Token know
Token ID760
Feature activation+5.19e+00

Pos logit contributions
river+0.596
 guiActiveUn+0.593
usted+0.561
allery+0.514
atorial+0.514
Neg logit contributions
sters-0.496
 Cu-0.486
NEY-0.486
 Colo-0.472
thouse-0.467
Tokeniked
Token ID17951
Feature activation+1.91e+00

Pos logit contributions
river+1.105
 guiActiveUn+1.065
usted+1.015
allery+0.853
atorial+0.846
Neg logit contributions
sters-2.107
NEY-2.085
 Cu-2.078
 Colo-2.040
thouse-2.025
Token counter
Token ID3753
Feature activation-5.68e+00

Pos logit contributions
river+1.645
 guiActiveUn+1.591
usted+1.522
atorial+1.398
allery+1.395
Neg logit contributions
sters-1.219
NEY-1.198
 Cu-1.181
thouse-1.160
 Colo-1.155
Token-
Token ID12
Feature activation+9.17e-01

Pos logit contributions
sters+3.375
 Cu+3.254
NEY+3.227
 Colo+3.098
thouse+3.047
Neg logit contributions
 guiActiveUn-5.161
river-4.860
usted-4.731
allery-4.487
atorial-4.414
Tokenclock
Token ID15750
Feature activation-3.10e+00

Pos logit contributions
river+0.783
 guiActiveUn+0.778
usted+0.738
allery+0.678
atorial+0.677
Neg logit contributions
sters-0.593
 Cu-0.581
NEY-0.580
 Colo-0.564
thouse-0.556
Tokenwise
Token ID3083
Feature activation+8.41e-02

Pos logit contributions
sters+1.593
 Cu+1.553
NEY+1.532
thouse+1.474
 Colo+1.465
Neg logit contributions
 guiActiveUn-3.050
river-2.990
usted-2.843
allery-2.713
atorial-2.688
Token for
Token ID329
Feature activation+1.31e+00

Pos logit contributions
river+0.072
 guiActiveUn+0.071
usted+0.067
allery+0.062
atorial+0.062
Neg logit contributions
sters-0.055
NEY-0.054
 Cu-0.053
 Colo-0.052
thouse-0.051
Token the
Token ID262
Feature activation+1.24e+00

Pos logit contributions
river+1.208
 guiActiveUn+1.187
usted+1.137
allery+1.051
atorial+1.049
Neg logit contributions
sters-0.758
NEY-0.747
 Cu-0.737
 Colo-0.717
thouse-0.714
Token full
Token ID1336
Feature activation+1.63e+00

Pos logit contributions
river+1.046
 guiActiveUn+1.032
usted+0.982
atorial+0.902
allery+0.901
Neg logit contributions
sters-0.807
NEY-0.793
 Cu-0.789
 Colo-0.765
thouse-0.763
Token loop
Token ID9052
Feature activation-8.04e-01

Pos logit contributions
river+1.387
 guiActiveUn+1.361
usted+1.296
allery+1.194
atorial+1.194
Neg logit contributions
sters-1.060
NEY-1.042
 Cu-1.033
thouse-1.005
 Colo-1.000
Token.
Token ID13
Feature activation+1.20e+00

Pos logit contributions
sters+0.532
 Cu+0.520
NEY+0.519
 Colo+0.504
thouse+0.498
Neg logit contributions
 guiActiveUn-0.676
river-0.673
usted-0.636
allery-0.586
atorial-0.585
Token The
Token ID383
Feature activation+5.03e-01

Pos logit contributions
river+1.075
 guiActiveUn+1.061
usted+1.014
allery+0.934
atorial+0.932
Neg logit contributions
sters-0.716
NEY-0.699
 Cu-0.693
 Colo-0.673
thouse-0.672
Token is
Token ID318
Feature activation-4.08e+00

Pos logit contributions
sters+3.474
 Cu+3.426
NEY+3.390
 Colo+3.302
thouse+3.213
Neg logit contributions
 guiActiveUn-4.814
river-4.709
usted-4.452
allery-4.177
atorial-4.086
Token part
Token ID636
Feature activation-1.29e+00

Pos logit contributions
sters+2.545
 Cu+2.523
NEY+2.508
 Colo+2.443
thouse+2.378
Neg logit contributions
 guiActiveUn-3.581
river-3.521
usted-3.311
allery-3.108
atorial-3.063
Token of
Token ID286
Feature activation-4.40e-01

Pos logit contributions
sters+0.702
NEY+0.688
 Cu+0.686
 Colo+0.659
thouse+0.650
Neg logit contributions
 guiActiveUn-1.234
river-1.230
usted-1.165
allery-1.094
atorial-1.085
Token the
Token ID262
Feature activation+5.90e-02

Pos logit contributions
sters+0.235
 Cu+0.230
NEY+0.229
 Colo+0.221
thouse+0.217
Neg logit contributions
river-0.424
 guiActiveUn-0.423
usted-0.403
allery-0.375
atorial-0.374
Token search
Token ID2989
Feature activation+1.24e-02

Pos logit contributions
river+0.044
 guiActiveUn+0.044
usted+0.042
allery+0.038
atorial+0.038
Neg logit contributions
sters-0.044
 Cu-0.043
NEY-0.043
 Colo-0.042
thouse-0.042
Token space
Token ID2272
Feature activation-1.84e+00

Pos logit contributions
river+0.011
 guiActiveUn+0.010
usted+0.010
allery+0.009
atorial+0.009
Neg logit contributions
sters-0.008
 Cu-0.008
NEY-0.008
 Colo-0.008
thouse-0.008
Token.
Token ID13
Feature activation-1.80e+00

Pos logit contributions
sters+1.214
 Cu+1.191
NEY+1.184
 Colo+1.151
thouse+1.131
Neg logit contributions
 guiActiveUn-1.542
river-1.536
usted-1.450
allery-1.335
atorial-1.329
Token
Token ID198
Feature activation-1.46e+00

Pos logit contributions
sters+1.089
 Cu+1.072
NEY+1.063
 Colo+1.034
thouse+1.011
Neg logit contributions
river-1.604
 guiActiveUn-1.604
usted-1.516
allery-1.408
atorial-1.400
Token
Token ID198
Feature activation-2.00e+00

Pos logit contributions
sters+0.931
NEY+0.912
 Cu+0.910
 Colo+0.884
thouse+0.876
Neg logit contributions
river-1.253
 guiActiveUn-1.241
usted-1.182
atorial-1.087
allery-1.083
TokenWhile
Token ID3633
Feature activation-2.64e+00

Pos logit contributions
sters+1.279
NEY+1.256
 Cu+1.238
 Colo+1.197
thouse+1.192
Neg logit contributions
 guiActiveUn-1.720
river-1.701
usted-1.613
allery-1.502
atorial-1.490
Token[
Token ID58
Feature activation-6.61e-01

Pos logit contributions
sters+1.663
 Cu+1.638
NEY+1.630
 Colo+1.588
thouse+1.552
Neg logit contributions
 guiActiveUn-2.292
river-2.277
usted-2.162
allery-2.001
atorial-1.986
Token religious
Token ID4158
Feature activation-9.01e-01

Pos logit contributions
sters+1.432
 Cu+1.417
NEY+1.390
 Colo+1.352
thouse+1.330
Neg logit contributions
 guiActiveUn-2.209
river-2.200
usted-2.083
allery-1.939
atorial-1.922
Token studies
Token ID3640
Feature activation+5.72e-01

Pos logit contributions
sters+0.766
 Cu+0.756
NEY+0.752
 Colo+0.736
thouse+0.727
Neg logit contributions
river-0.586
 guiActiveUn-0.586
usted-0.542
allery-0.486
atorial-0.483
Token at
Token ID379
Feature activation+1.59e+00

Pos logit contributions
 guiActiveUn+0.528
river+0.528
usted+0.501
allery+0.465
atorial+0.464
Neg logit contributions
sters-0.329
 Cu-0.322
NEY-0.321
 Colo-0.310
thouse-0.305
Token the
Token ID262
Feature activation+1.07e+00

Pos logit contributions
river+1.483
 guiActiveUn+1.464
usted+1.401
allery+1.299
atorial+1.295
Neg logit contributions
sters-0.898
NEY-0.880
 Cu-0.867
thouse-0.840
 Colo-0.839
Token University
Token ID2059
Feature activation+3.18e+00

Pos logit contributions
river+0.711
 guiActiveUn+0.707
usted+0.660
allery+0.591
atorial+0.590
Neg logit contributions
sters-0.893
NEY-0.878
 Cu-0.876
 Colo-0.856
thouse-0.850
Token of
Token ID286
Feature activation+4.33e-01

Pos logit contributions
river+2.662
usted+2.457
 guiActiveUn+2.452
atorial+2.266
ariat+2.196
Neg logit contributions
sters-2.033
NEY-1.990
thouse-1.943
 Cu-1.938
 Colo-1.912
Token Pennsylvania
Token ID9589
Feature activation+2.70e+00

Pos logit contributions
river+0.424
 guiActiveUn+0.416
usted+0.401
atorial+0.373
allery+0.373
Neg logit contributions
sters-0.226
NEY-0.220
 Cu-0.215
thouse-0.211
 Colo-0.207
Token.
Token ID13
Feature activation+6.56e-03

Pos logit contributions
river+2.135
 guiActiveUn+2.117
usted+2.011
allery+1.828
atorial+1.825
Neg logit contributions
sters-1.896
NEY-1.863
 Cu-1.842
 Colo-1.806
thouse-1.788
Token<|endoftext|>
Token ID50256
Feature activation+1.16e+00

Pos logit contributions
river+0.006
 guiActiveUn+0.006
usted+0.005
allery+0.005
atorial+0.005
Neg logit contributions
sters-0.004
 Cu-0.004
NEY-0.004
 Colo-0.004
thouse-0.004
TokenThe
Token ID464
Feature activation-4.29e-01

Pos logit contributions
river+0.987
 guiActiveUn+0.980
usted+0.930
allery+0.854
atorial+0.854
Neg logit contributions
sters-0.751
 Cu-0.736
NEY-0.733
 Colo-0.713
thouse-0.705
Token Trump
Token ID1301
Feature activation+1.30e+00

Pos logit contributions
sters+0.265
 Cu+0.260
NEY+0.258
 Colo+0.251
thouse+0.247
Neg logit contributions
river-0.378
 guiActiveUn-0.377
usted-0.357
allery-0.330
atorial-0.329
Token in
Token ID287
Feature activation+4.59e+00

Pos logit contributions
sters+0.755
 Cu+0.741
NEY+0.732
 Colo+0.710
thouse+0.704
Neg logit contributions
 guiActiveUn-1.036
river-1.033
usted-0.978
allery-0.907
atorial-0.900
Token their
Token ID511
Feature activation+3.15e+00

Pos logit contributions
river+3.711
 guiActiveUn+3.673
usted+3.490
allery+3.205
atorial+3.190
Neg logit contributions
sters-3.092
NEY-3.058
 Cu-2.998
 Colo-2.939
thouse-2.924
Token lives
Token ID3160
Feature activation+1.79e+00

Pos logit contributions
river+2.181
 guiActiveUn+2.163
usted+2.030
atorial+1.826
allery+1.818
Neg logit contributions
sters-2.512
NEY-2.473
 Cu-2.457
 Colo-2.419
thouse-2.397
Token.
Token ID13
Feature activation-5.62e-01

Pos logit contributions
river+1.448
 guiActiveUn+1.442
usted+1.361
allery+1.246
atorial+1.245
Neg logit contributions
sters-1.229
NEY-1.205
 Cu-1.205
 Colo-1.172
thouse-1.159
Token Teaching
Token ID38094
Feature activation+3.13e+00

Pos logit contributions
sters+0.340
NEY+0.332
 Cu+0.331
 Colo+0.321
thouse+0.318
Neg logit contributions
river-0.503
 guiActiveUn-0.500
usted-0.476
allery-0.439
atorial-0.439
Token your
Token ID534
Feature activation-1.35e+00

Pos logit contributions
river+2.647
 guiActiveUn+2.617
usted+2.512
allery+2.296
atorial+2.292
Neg logit contributions
sters-1.978
NEY-1.956
 Cu-1.933
 Colo-1.906
thouse-1.903
Token children
Token ID1751
Feature activation-2.32e+00

Pos logit contributions
sters+0.992
 Cu+0.974
NEY+0.966
 Colo+0.942
thouse+0.922
Neg logit contributions
 guiActiveUn-1.046
river-1.042
usted-0.977
allery-0.895
atorial-0.892
Token to
Token ID284
Feature activation-1.93e-01

Pos logit contributions
sters+1.505
 Cu+1.477
NEY+1.468
 Colo+1.416
thouse+1.379
Neg logit contributions
 guiActiveUn-1.990
river-1.962
usted-1.854
allery-1.722
atorial-1.711
Token sew
Token ID34249
Feature activation-2.26e+00

Pos logit contributions
sters+0.135
 Cu+0.133
NEY+0.133
 Colo+0.129
thouse+0.128
Neg logit contributions
river-0.153
 guiActiveUn-0.153
usted-0.144
allery-0.132
atorial-0.132
Token is
Token ID318
Feature activation-3.49e-01

Pos logit contributions
sters+1.440
 Cu+1.403
NEY+1.394
 Colo+1.343
thouse+1.324
Neg logit contributions
 guiActiveUn-1.977
river-1.947
usted-1.849
allery-1.711
atorial-1.694
Token a
Token ID257
Feature activation-4.65e-01

Pos logit contributions
sters+0.212
 Cu+0.208
NEY+0.207
 Colo+0.201
thouse+0.197
Neg logit contributions
 guiActiveUn-0.312
river-0.311
usted-0.294
allery-0.273
atorial-0.272
Token in
Token ID287
Feature activation+1.06e+00

Pos logit contributions
sters+0.937
 Cu+0.915
NEY+0.914
 Colo+0.880
thouse+0.875
Neg logit contributions
 guiActiveUn-1.290
river-1.284
usted-1.217
allery-1.124
atorial-1.119
Token Ra
Token ID7567
Feature activation+1.99e+00

Pos logit contributions
river+0.947
 guiActiveUn+0.937
usted+0.896
atorial+0.826
allery+0.824
Neg logit contributions
sters-0.639
NEY-0.624
 Cu-0.616
thouse-0.600
 Colo-0.598
Tokenising
Token ID1710
Feature activation+4.89e-01

Pos logit contributions
river+1.488
 guiActiveUn+1.477
usted+1.407
allery+1.259
atorial+1.258
Neg logit contributions
sters-1.484
NEY-1.466
 Cu-1.460
 Colo-1.432
thouse-1.412
Token the
Token ID262
Feature activation-1.29e+00

Pos logit contributions
river+0.467
 guiActiveUn+0.464
usted+0.443
allery+0.412
atorial+0.411
Neg logit contributions
sters-0.265
NEY-0.260
 Cu-0.258
 Colo-0.249
thouse-0.247
Token Floor
Token ID22343
Feature activation-2.01e+00

Pos logit contributions
sters+0.710
 Cu+0.701
NEY+0.678
 Colo+0.674
 Canary+0.639
Neg logit contributions
 guiActiveUn-1.225
river-1.217
usted-1.165
atorial-1.082
allery-1.079
Token),
Token ID828
Feature activation+6.74e-01

Pos logit contributions
sters+1.269
 Cu+1.256
NEY+1.237
 Colo+1.204
thouse+1.176
Neg logit contributions
 guiActiveUn-1.754
river-1.738
usted-1.661
allery-1.523
atorial-1.513
Token perhaps
Token ID3737
Feature activation-1.19e+00

Pos logit contributions
river+0.600
 guiActiveUn+0.594
usted+0.567
allery+0.523
atorial+0.523
Neg logit contributions
sters-0.408
NEY-0.401
 Cu-0.395
thouse-0.385
 Colo-0.384
Token $
Token ID720
Feature activation+3.77e+00

Pos logit contributions
sters+0.727
 Cu+0.711
NEY+0.710
 Colo+0.688
thouse+0.679
Neg logit contributions
river-1.064
 guiActiveUn-1.062
usted-1.007
allery-0.930
atorial-0.929
Token600
Token ID8054
Feature activation+2.93e-01

Pos logit contributions
river+2.926
 guiActiveUn+2.829
usted+2.715
atorial+2.448
allery+2.418
Neg logit contributions
sters-2.674
 Cu-2.660
NEY-2.653
 Colo-2.604
thouse-2.587
Token is
Token ID318
Feature activation-9.36e-01

Pos logit contributions
river+0.254
 guiActiveUn+0.253
usted+0.240
allery+0.221
atorial+0.221
Neg logit contributions
sters-0.186
 Cu-0.182
NEY-0.182
 Colo-0.176
thouse-0.174
Token paid
Token ID3432
Feature activation+3.98e-01

Pos logit contributions
sters+0.624
 Cu+0.611
NEY+0.611
 Colo+0.593
thouse+0.586
Neg logit contributions
river-0.778
 guiActiveUn-0.776
usted-0.734
allery-0.674
atorial-0.673
Token McCabe
Token ID45395
Feature activation+3.25e+00

Pos logit contributions
river+2.023
 guiActiveUn+1.975
usted+1.911
allery+1.811
atorial+1.801
Neg logit contributions
sters-1.020
NEY-1.000
 Cu-0.990
thouse-0.958
 Colo-0.951
Token,
Token ID11
Feature activation-1.83e+00

Pos logit contributions
river+2.606
 guiActiveUn+2.602
usted+2.455
allery+2.243
atorial+2.242
Neg logit contributions
sters-2.244
NEY-2.190
 Cu-2.189
 Colo-2.126
thouse-2.118
Token brings
Token ID6774
Feature activation-1.18e+00

Pos logit contributions
sters+1.181
 Cu+1.164
NEY+1.151
 Colo+1.127
thouse+1.105
Neg logit contributions
river-1.568
 guiActiveUn-1.567
usted-1.469
allery-1.373
atorial-1.356
Token his
Token ID465
Feature activation+9.35e-01

Pos logit contributions
sters+0.700
 Cu+0.689
NEY+0.684
 Colo+0.664
thouse+0.650
Neg logit contributions
 guiActiveUn-1.067
river-1.061
usted-1.005
allery-0.934
atorial-0.927
Token own
Token ID898
Feature activation+1.39e+00

Pos logit contributions
river+0.714
 guiActiveUn+0.711
usted+0.670
atorial+0.610
allery+0.608
Neg logit contributions
sters-0.686
NEY-0.673
 Cu-0.672
 Colo-0.654
thouse-0.649
Token political
Token ID1964
Feature activation+5.51e-01

Pos logit contributions
river+1.138
 guiActiveUn+1.128
usted+1.069
atorial+0.983
allery+0.976
Neg logit contributions
sters-0.940
NEY-0.923
 Cu-0.916
 Colo-0.891
thouse-0.887
Token baggage
Token ID30466
Feature activation+3.92e+00

Pos logit contributions
river+0.461
 guiActiveUn+0.460
usted+0.435
atorial+0.400
allery+0.399
Neg logit contributions
sters-0.363
NEY-0.356
 Cu-0.356
 Colo-0.345
thouse-0.342
Token?
Token ID30
Feature activation-4.73e-01

Pos logit contributions
river+3.262
 guiActiveUn+3.208
usted+3.059
atorial+2.818
allery+2.787
Neg logit contributions
sters-2.590
NEY-2.552
 Cu-2.526
thouse-2.469
 Colo-2.469
Token With
Token ID2080
Feature activation+2.96e+00

Pos logit contributions
sters+0.294
NEY+0.287
 Cu+0.287
 Colo+0.278
thouse+0.275
Neg logit contributions
river-0.416
 guiActiveUn-0.414
usted-0.393
allery-0.362
atorial-0.362
Token background
Token ID4469
Feature activation+2.91e+00

Pos logit contributions
river+2.601
 guiActiveUn+2.582
usted+2.479
atorial+2.279
allery+2.268
Neg logit contributions
sters-1.788
NEY-1.762
 Cu-1.729
thouse-1.699
 Colo-1.686
Token checks
Token ID8794
Feature activation+1.16e+00

Pos logit contributions
river+2.418
 guiActiveUn+2.401
usted+2.277
atorial+2.079
allery+2.075
Neg logit contributions
sters-1.934
NEY-1.904
 Cu-1.889
thouse-1.843
 Colo-1.839
Token actually
Token ID1682
Feature activation-1.98e+00

Pos logit contributions
sters+2.428
 Cu+2.390
NEY+2.369
 Colo+2.283
 Canary+2.224
Neg logit contributions
 guiActiveUn-3.366
river-3.337
usted-3.150
allery-2.945
atorial-2.905
Token keeping
Token ID5291
Feature activation+1.16e+00

Pos logit contributions
sters+1.274
 Cu+1.254
NEY+1.245
 Colo+1.208
thouse+1.177
Neg logit contributions
 guiActiveUn-1.701
river-1.694
usted-1.595
allery-1.478
atorial-1.467
Token your
Token ID534
Feature activation-2.74e+00

Pos logit contributions
river+1.098
 guiActiveUn+1.091
usted+1.042
allery+0.967
atorial+0.965
Neg logit contributions
sters-0.643
NEY-0.630
 Cu-0.626
 Colo-0.605
thouse-0.602
Token c
Token ID269
Feature activation+7.47e-01

Pos logit contributions
sters+1.668
 Cu+1.634
NEY+1.608
 Colo+1.576
thouse+1.530
Neg logit contributions
 guiActiveUn-2.455
river-2.444
usted-2.313
allery-2.151
atorial-2.137
Token6
Token ID21
Feature activation-3.51e-01

Pos logit contributions
 guiActiveUn+0.571
river+0.569
usted+0.532
allery+0.486
atorial+0.484
Neg logit contributions
sters-0.553
 Cu-0.541
NEY-0.538
 Colo-0.527
thouse-0.520
Token from
Token ID422
Feature activation-5.87e+00

Pos logit contributions
sters+0.256
NEY+0.252
 Cu+0.251
 Colo+0.245
thouse+0.242
Neg logit contributions
river-0.269
 guiActiveUn-0.268
usted-0.253
allery-0.230
atorial-0.230
Token getting
Token ID1972
Feature activation-1.14e+00

Pos logit contributions
sters+4.127
 Cu+4.098
NEY+3.998
 Colo+3.928
 Dob+3.839
Neg logit contributions
 guiActiveUn-4.631
river-4.600
usted-4.234
allery-4.039
atorial-3.916
Token out
Token ID503
Feature activation+5.67e-01

Pos logit contributions
sters+0.973
 Cu+0.958
NEY+0.953
 Colo+0.933
thouse+0.918
Neg logit contributions
 guiActiveUn-0.736
river-0.735
usted-0.675
allery-0.611
atorial-0.606
Token of
Token ID286
Feature activation-1.17e+00

Pos logit contributions
river+0.502
 guiActiveUn+0.501
usted+0.475
allery+0.438
atorial+0.438
Neg logit contributions
sters-0.347
 Cu-0.340
NEY-0.339
 Colo-0.328
thouse-0.325
Token park
Token ID3952
Feature activation+1.99e+00

Pos logit contributions
sters+0.736
 Cu+0.720
NEY+0.718
 Colo+0.697
thouse+0.685
Neg logit contributions
 guiActiveUn-1.021
river-1.020
usted-0.964
allery-0.892
atorial-0.889
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
river+1.592
 guiActiveUn+1.578
usted+1.492
allery+1.360
atorial+1.358
Neg logit contributions
sters-1.379
NEY-1.360
 Cu-1.359
 Colo-1.323
thouse-1.311
Token definition
Token ID6770
Feature activation+2.39e-01

Pos logit contributions
river+0.831
 guiActiveUn+0.829
usted+0.784
atorial+0.722
allery+0.722
Neg logit contributions
sters-0.620
NEY-0.608
 Cu-0.607
 Colo-0.588
thouse-0.583
Token with
Token ID351
Feature activation-9.54e-01

Pos logit contributions
river+0.221
 guiActiveUn+0.221
usted+0.210
allery+0.195
atorial+0.194
Neg logit contributions
sters-0.137
 Cu-0.134
NEY-0.134
 Colo-0.129
thouse-0.128
Token a
Token ID257
Feature activation-4.77e-01

Pos logit contributions
sters+0.571
 Cu+0.564
NEY+0.554
 Colo+0.544
thouse+0.528
Neg logit contributions
 guiActiveUn-0.863
river-0.860
usted-0.818
allery-0.753
atorial-0.752
Token sometimes
Token ID3360
Feature activation-7.89e-01

Pos logit contributions
sters+0.311
 Cu+0.306
NEY+0.304
 Colo+0.296
thouse+0.291
Neg logit contributions
river-0.404
 guiActiveUn-0.404
usted-0.382
allery-0.352
atorial-0.350
Token st
Token ID336
Feature activation+1.14e+00

Pos logit contributions
sters+0.514
 Cu+0.505
NEY+0.503
 Colo+0.490
thouse+0.482
Neg logit contributions
 guiActiveUn-0.668
river-0.665
usted-0.630
allery-0.582
atorial-0.575
Tokenil
Token ID346
Feature activation-7.88e+00

Pos logit contributions
river+0.838
 guiActiveUn+0.832
usted+0.784
atorial+0.710
allery+0.709
Neg logit contributions
sters-0.878
NEY-0.864
 Cu-0.862
 Colo-0.842
thouse-0.831
Tokented
Token ID1513
Feature activation+8.74e-01

Pos logit contributions
 Cu+3.501
sters+3.496
NEY+3.427
thouse+3.301
 Colo+3.180
Neg logit contributions
 guiActiveUn-8.086
river-7.879
usted-7.464
allery-7.166
atorial-6.895
Token view
Token ID1570
Feature activation-2.59e+00

Pos logit contributions
river+0.753
 guiActiveUn+0.751
usted+0.710
atorial+0.656
allery+0.655
Neg logit contributions
sters-0.556
NEY-0.544
 Cu-0.542
 Colo-0.526
thouse-0.522
Token.
Token ID13
Feature activation+2.45e+00

Pos logit contributions
sters+1.467
 Cu+1.433
NEY+1.430
 Colo+1.372
thouse+1.366
Neg logit contributions
 guiActiveUn-2.394
river-2.375
usted-2.284
allery-2.122
atorial-2.068
Token I
Token ID314
Feature activation+1.78e+00

Pos logit contributions
river+2.113
 guiActiveUn+2.076
usted+1.984
atorial+1.841
allery+1.826
Neg logit contributions
sters-1.539
NEY-1.501
 Cu-1.477
thouse-1.444
 Colo-1.431
Token think
Token ID892
Feature activation-3.28e+00

Pos logit contributions
river+1.388
 guiActiveUn+1.368
usted+1.306
atorial+1.187
allery+1.179
Neg logit contributions
sters-1.281
NEY-1.260
 Cu-1.257
 Colo-1.223
thouse-1.209
Token303
Token ID22572
Feature activation-1.09e+00

Pos logit contributions
river+0.291
 guiActiveUn+0.289
usted+0.272
allery+0.248
atorial+0.247
Neg logit contributions
sters-0.280
 Cu-0.275
NEY-0.275
 Colo-0.268
thouse-0.265
Tokens
Token ID82
Feature activation-4.34e-01

Pos logit contributions
sters+0.604
NEY+0.591
 Cu+0.591
 Colo+0.571
thouse+0.563
Neg logit contributions
river-1.022
 guiActiveUn-1.015
usted-0.968
atorial-0.898
allery-0.896
Token)}
Token ID38165
Feature activation-9.54e-01

Pos logit contributions
sters+0.215
 Cu+0.210
NEY+0.210
 Colo+0.204
thouse+0.199
Neg logit contributions
river-0.436
 guiActiveUn-0.425
usted-0.413
atorial-0.383
allery-0.379
Token 35
Token ID3439
Feature activation-3.26e+00

Pos logit contributions
sters+0.420
 Cu+0.408
NEY+0.405
 Colo+0.389
thouse+0.380
Neg logit contributions
river-1.011
 guiActiveUn-1.009
usted-0.964
allery-0.906
atorial-0.903
Token.
Token ID13
Feature activation-4.19e+00

Pos logit contributions
sters+2.252
 Cu+2.212
NEY+2.200
 Colo+2.142
thouse+2.111
Neg logit contributions
 guiActiveUn-2.666
river-2.632
usted-2.481
allery-2.298
atorial-2.268
Token ex
Token ID409
Feature activation-5.57e+00

Pos logit contributions
 Cu+2.245
sters+2.222
NEY+2.142
 Colo+2.125
 Dob+2.065
Neg logit contributions
 guiActiveUn-4.073
river-4.033
usted-3.836
allery-3.591
atorial-3.556
Tokenf
Token ID69
Feature activation-2.05e+00

Pos logit contributions
sters+3.847
 Cu+3.720
NEY+3.659
thouse+3.619
 Colo+3.545
Neg logit contributions
 guiActiveUn-4.566
river-4.394
usted-4.133
allery-3.923
umbn-3.784
Token4
Token ID19
Feature activation-3.61e+00

Pos logit contributions
sters+1.427
 Cu+1.396
NEY+1.395
 Colo+1.350
thouse+1.344
Neg logit contributions
 guiActiveUn-1.657
river-1.649
usted-1.542
allery-1.429
atorial-1.418
Token {
Token ID1391
Feature activation-3.08e+00

Pos logit contributions
 Cu+2.274
sters+2.253
NEY+2.183
 Colo+2.163
 Dob+2.111
Neg logit contributions
 guiActiveUn-3.110
river-3.102
usted-2.913
allery-2.763
atorial-2.698
Token(
Token ID7
Feature activation+1.50e+00

Pos logit contributions
sters+1.630
NEY+1.587
 Cu+1.584
 Colo+1.517
thouse+1.500
Neg logit contributions
 guiActiveUn-3.009
river-2.985
usted-2.846
allery-2.674
atorial-2.644
Token17
Token ID1558
Feature activation+5.04e-01

Pos logit contributions
river+1.143
 guiActiveUn+1.130
usted+1.068
allery+0.970
atorial+0.968
Neg logit contributions
sters-1.103
 Cu-1.084
NEY-1.084
 Colo-1.056
thouse-1.048
Token.
Token ID13
Feature activation+1.53e+00

Pos logit contributions
sters+0.984
 Cu+0.973
NEY+0.959
 Colo+0.935
thouse+0.919
Neg logit contributions
 guiActiveUn-1.297
river-1.285
usted-1.215
atorial-1.118
allery-1.116
Token
Token ID447
Feature activation+1.70e+00

Pos logit contributions
river+1.289
 guiActiveUn+1.275
usted+1.213
atorial+1.116
allery+1.114
Neg logit contributions
sters-1.000
NEY-0.974
 Cu-0.966
thouse-0.941
 Colo-0.940
Token
Token ID251
Feature activation+3.88e-01

Pos logit contributions
 guiActiveUn+1.445
river+1.443
usted+1.369
atorial+1.260
allery+1.258
Neg logit contributions
sters-1.094
 Cu-1.067
NEY-1.059
 Colo-1.027
thouse-1.019
Token
Token ID198
Feature activation+2.48e+00

Pos logit contributions
river+0.340
 guiActiveUn+0.339
usted+0.321
allery+0.296
atorial+0.296
Neg logit contributions
sters-0.243
NEY-0.237
 Cu-0.237
 Colo-0.229
thouse-0.227
Token
Token ID198
Feature activation+1.98e+00

Pos logit contributions
river+1.959
usted+1.816
 guiActiveUn+1.808
atorial+1.663
ariat+1.574
Neg logit contributions
sters-1.724
NEY-1.703
 Cu-1.687
thouse-1.673
 Colo-1.665
TokenV
Token ID53
Feature activation-6.51e+00

Pos logit contributions
river+1.683
 guiActiveUn+1.656
usted+1.579
atorial+1.447
allery+1.445
Neg logit contributions
sters-1.292
 Cu-1.262
NEY-1.254
 Colo-1.226
thouse-1.210
Tokenu
Token ID84
Feature activation-2.94e+00

Pos logit contributions
 Cu+4.696
sters+4.675
NEY+4.551
 Colo+4.469
thouse+4.448
Neg logit contributions
 guiActiveUn-4.921
river-4.758
usted-4.378
atorial-4.065
allery-4.050
Tokenong
Token ID506
Feature activation+2.69e+00

Pos logit contributions
sters+2.508
 Cu+2.470
NEY+2.467
 Colo+2.411
thouse+2.389
Neg logit contributions
 guiActiveUn-1.914
river-1.883
usted-1.739
allery-1.574
atorial-1.548
Token says
Token ID1139
Feature activation+5.91e-01

Pos logit contributions
river+2.308
 guiActiveUn+2.283
usted+2.173
allery+2.003
atorial+1.994
Neg logit contributions
sters-1.711
NEY-1.676
 Cu-1.645
 Colo-1.614
thouse-1.606
Token,
Token ID11
Feature activation+1.35e+00

Pos logit contributions
river+0.507
 guiActiveUn+0.504
usted+0.478
allery+0.440
atorial+0.439
Neg logit contributions
sters-0.379
NEY-0.371
 Cu-0.370
 Colo-0.359
thouse-0.356
Token
Token ID564
Feature activation-2.16e+00

Pos logit contributions
river+1.182
 guiActiveUn+1.179
usted+1.119
atorial+1.031
allery+1.029
Neg logit contributions
sters-0.831
NEY-0.811
 Cu-0.808
 Colo-0.784
thouse-0.779
Token
Token ID250
Feature activation+1.40e+00

Pos logit contributions
sters+0.701
 Cu+0.684
NEY+0.683
 Colo+0.661
thouse+0.653
Neg logit contributions
river-1.039
 guiActiveUn-1.036
usted-0.984
atorial-0.908
allery-0.908
TokenShe
Token ID3347
Feature activation+1.25e+00

Pos logit contributions
river+1.211
 guiActiveUn+1.196
usted+1.140
atorial+1.046
allery+1.045
Neg logit contributions
sters-0.897
 Cu-0.876
NEY-0.873
 Colo-0.853
thouse-0.840
Token opened
Token ID4721
Feature activation-1.27e+00

Pos logit contributions
river+1.053
 guiActiveUn+1.047
usted+0.994
allery+0.912
atorial+0.911
Neg logit contributions
sters-0.823
NEY-0.807
 Cu-0.806
 Colo-0.782
thouse-0.774
Token up
Token ID510
Feature activation+1.51e+00

Pos logit contributions
sters+0.687
 Cu+0.678
NEY+0.669
 Colo+0.648
thouse+0.634
Neg logit contributions
 guiActiveUn-1.217
river-1.205
usted-1.151
atorial-1.068
allery-1.067
Token her
Token ID607
Feature activation-5.60e-01

Pos logit contributions
river+1.402
 guiActiveUn+1.396
usted+1.328
allery+1.233
atorial+1.230
Neg logit contributions
sters-0.859
NEY-0.837
 Cu-0.836
 Colo-0.808
thouse-0.798
Token backup
Token ID11559
Feature activation-7.84e+00

Pos logit contributions
sters+0.400
 Cu+0.394
NEY+0.389
 Colo+0.381
thouse+0.375
Neg logit contributions
 guiActiveUn-0.444
river-0.442
usted-0.414
allery-0.379
atorial-0.377
Token envelope
Token ID22878
Feature activation-4.49e+00

Pos logit contributions
sters+5.123
 Cu+4.984
 Colo+4.790
NEY+4.789
 Canary+4.658
Neg logit contributions
 guiActiveUn-6.570
river-6.338
usted-5.994
allery-5.528
atorial-5.518
Token to
Token ID284
Feature activation-1.97e-01

Pos logit contributions
sters+2.754
 Cu+2.688
NEY+2.646
 Colo+2.602
thouse+2.558
Neg logit contributions
 guiActiveUn-3.982
river-3.873
usted-3.692
atorial-3.410
allery-3.401
Token confirm
Token ID6216
Feature activation+3.09e+00

Pos logit contributions
sters+0.128
 Cu+0.125
NEY+0.125
 Colo+0.121
thouse+0.120
Neg logit contributions
river-0.168
 guiActiveUn-0.168
usted-0.159
atorial-0.146
allery-0.146
Token her
Token ID607
Feature activation+3.17e-02

Pos logit contributions
river+2.721
 guiActiveUn+2.686
usted+2.561
allery+2.363
atorial+2.359
Neg logit contributions
sters-1.912
NEY-1.871
 Cu-1.838
 Colo-1.790
thouse-1.781
Token memory
Token ID4088
Feature activation+6.69e-01

Pos logit contributions
 guiActiveUn+0.026
river+0.026
usted+0.025
allery+0.023
atorial+0.023
Neg logit contributions
sters-0.021
 Cu-0.021
NEY-0.021
 Colo-0.020
thouse-0.020