TOP ACTIVATIONS
MAX = 12.840

When an O CC RP reporter ph oned And rey uk
Press is reporting that AT & T , the defendant in
the river to become un nav ig able this summer .
this into perspective , AT & T 's spending for three
All these years we have navig ated the Bar re and
buy you ? While AT & T 's powerhouse FISA lobbyist
gain , wildlife sightings , navig ational challenges , even solitude
who made sure Thomas safely navig ated urban for
in May 1996 , CBS correspondent Leslie St ahl asked Clinton
spring . New York Times reporter Jonathan We isman wrote in
locations which are empty . Compl iment with previous ser ach
the F TC Compl aint Assistant to
a licensing division of AT & T / Western Electric ,
Two years ago Rolling Stone reporter Michael Hastings writing in America
housing market from real estate reporter , Tara Perkins , and
BT , O 2 and Virgin having blocked addresses on it
- C razy Air plane Pilot - 08 Election - J
. For 2007 , AT & T spent over $ 16
. A BBC correspondent in Somalia says the Ethiop
cover slightly fewer areas of health and still be at a

MIN ACTIVATIONS
MIN = -10.892

explaining that " If you ve got
. It s either going to cost us now
This is also mentioned in Sunni Had ith collections :
points , modern , and anything that s legal
. It s either like you overlook everything and
just as cap ably as anything you d see
term . " If Barack Obama wins a The
as Le Fort de Br é gan ç on ser a
person . He would do anything for anybody .
can swing five days in either direction . If
us .' Scroll down for video Hillary
of 10 , saying " If you 're harbor ing even
big teeth and immensely powerful jaws ; it can cut down
to neighborhood kids . " If the tad pole had just
the prospect of voting for either Donald Trump or Hillary Clinton
kel said she was " anything but indifferent " about London
With Ghostbusters we learned that if you find a phantom ,
arm . Scroll down for video White
confirm a release date for either KH 3 of FF 14
the entire state . " If Matthew directly impacts Florida ,"

INTERVAL 6.907 - 12.840
CONTAINS 0.146%

Vector < Part icle > & particles ) { density Grid
Earth 's spin , of course , is not the only
who made sure Thomas safely navig ated urban for
( below ), the sk ipper and project manager of the
. Women 's rights groups warn the new interim

INTERVAL 0.974 - 6.907
CONTAINS 29.848%

'm praying that our school district will reconsider its recent decision
done on an elevated , fold - up table behind the
come back he may have gone back to Dragon
already know your way around Angular , these may be helpful
the noun is over there , and you still had to

INTERVAL -4.959 - 0.974
CONTAINS 68.888%

home , however basic , will act as a gateway for
This is all going to take a number of years .
ises via A q aba , Jordan , Port Sok h
TA 6 Jac op o Gu arn ieri ( Ast ana
between 10 % and 30 %. The cartel operated

INTERVAL -10.892 - -4.959
CONTAINS 1.117%

one extra submarine annually . If the GOP is willing to
the Prime Minister and , if necessary , dismiss one that
and non - in vasive insects . The desire for foreign
ready to go , but then why is nothing happening ?
exited his vehicle and observed another vehicle adjacent to his own
Token When
Token ID1649
Feature activation-4.21e+00

Pos logit contributions
wcs+0.175
Cra+0.171
yip+0.165
 ingred+0.158
hovah+0.158
Neg logit contributions
iless-0.140
igible-0.140
 checkpoints-0.134
idated-0.126
ulnerable-0.124
Token an
Token ID281
Feature activation-1.80e+00

Pos logit contributions
wcs+2.862
Cra+2.795
yip+2.656
 ingred+2.584
kinson+2.566
Neg logit contributions
iless-2.964
igible-2.959
 checkpoints-2.772
idated-2.720
ulnerable-2.678
Token O
Token ID440
Feature activation+3.31e+00

Pos logit contributions
wcs+1.384
Cra+1.363
yip+1.293
kinson+1.258
 ingred+1.252
Neg logit contributions
iless-1.137
igible-1.114
 checkpoints-1.077
idated-1.020
ulnerable-1.001
TokenCC
Token ID4093
Feature activation+3.02e+00

Pos logit contributions
iless+2.150
igible+2.141
 checkpoints+2.047
idated+1.942
ulnerable+1.924
Neg logit contributions
wcs-2.521
Cra-2.425
yip-2.362
 ingred-2.256
hovah-2.256
TokenRP
Token ID20031
Feature activation+1.65e+00

Pos logit contributions
iless+2.052
igible+2.040
 checkpoints+1.970
idated+1.862
ulnerable+1.827
Neg logit contributions
wcs-2.227
Cra-2.128
yip-2.058
 ingred-1.990
hovah-1.975
Token reporter
Token ID9095
Feature activation+1.28e+01

Pos logit contributions
iless+1.001
igible+0.994
 checkpoints+0.952
idated+0.897
ulnerable+0.877
Neg logit contributions
wcs-1.337
Cra-1.288
yip-1.251
 ingred-1.208
hovah-1.203
Token ph
Token ID872
Feature activation-9.50e-01

Pos logit contributions
 checkpoints+7.032
iless+6.994
igible+6.991
í+6.476
idated+6.250
Neg logit contributions
wcs-9.856
yip-9.810
Cra-9.753
 ingred-9.439
hovah-9.412
Tokenoned
Token ID12004
Feature activation+3.94e+00

Pos logit contributions
wcs+0.851
Cra+0.838
yip+0.814
atos+0.794
kinson+0.792
Neg logit contributions
iless-0.466
igible-0.457
 checkpoints-0.451
OAD-0.413
idated-0.400
Token And
Token ID843
Feature activation+3.29e-01

Pos logit contributions
iless+2.635
igible+2.605
 checkpoints+2.531
idated+2.376
itimate+2.346
Neg logit contributions
wcs-2.941
Cra-2.820
yip-2.743
hovah-2.609
 ingred-2.602
Tokenrey
Token ID4364
Feature activation+3.06e-01

Pos logit contributions
iless+0.251
igible+0.251
 checkpoints+0.244
idated+0.231
ulnerable+0.227
Neg logit contributions
wcs-0.212
Cra-0.203
yip-0.198
kinson-0.186
hovah-0.185
Tokenuk
Token ID2724
Feature activation-2.13e-01

Pos logit contributions
iless+0.292
igible+0.290
 checkpoints+0.283
idated+0.272
itimate+0.269
Neg logit contributions
wcs-0.141
Cra-0.133
yip-0.126
kinson-0.117
 ingred-0.116
Token Press
Token ID4332
Feature activation+3.72e+00

Pos logit contributions
iless+2.806
igible+2.803
 checkpoints+2.715
idated+2.529
í+2.499
Neg logit contributions
wcs-3.649
yip-3.490
Cra-3.460
 ingred-3.350
hovah-3.341
Token is
Token ID318
Feature activation+4.38e-01

Pos logit contributions
iless+2.623
igible+2.575
 checkpoints+2.524
idated+2.372
ulnerable+2.345
Neg logit contributions
wcs-2.650
Cra-2.533
yip-2.503
hovah-2.340
 ingred-2.335
Token reporting
Token ID6447
Feature activation+8.02e+00

Pos logit contributions
iless+0.277
igible+0.275
 checkpoints+0.263
idated+0.251
itimate+0.246
Neg logit contributions
wcs-0.342
Cra-0.331
yip-0.319
 ingred-0.309
kinson-0.307
Token that
Token ID326
Feature activation+2.37e+00

Pos logit contributions
iless+4.752
igible+4.736
 checkpoints+4.677
idated+4.242
í+4.190
Neg logit contributions
wcs-6.246
Cra-5.991
yip-5.963
hovah-5.653
atos-5.593
Token AT
Token ID5161
Feature activation+6.63e+00

Pos logit contributions
iless+1.575
igible+1.562
 checkpoints+1.515
idated+1.421
itimate+1.398
Neg logit contributions
wcs-1.778
Cra-1.711
yip-1.666
hovah-1.587
 ingred-1.582
Token&
Token ID5
Feature activation+1.24e+01

Pos logit contributions
iless+2.990
igible+2.943
 checkpoints+2.876
idated+2.548
ulnerable+2.539
Neg logit contributions
wcs-6.406
Cra-6.069
yip-5.933
hovah-5.783
 ingred-5.769
TokenT
Token ID51
Feature activation+5.08e+00

Pos logit contributions
OAD+5.011
í+4.940
 checkpoints+4.792
igible+4.643
iless+4.479
Neg logit contributions
wcs-12.201
 ingred-12.161
hovah-11.928
yip-11.737
kinson-10.743
Token,
Token ID11
Feature activation-1.70e+00

Pos logit contributions
iless+3.173
igible+3.148
 checkpoints+3.038
idated+2.843
í+2.810
Neg logit contributions
wcs-4.001
Cra-3.823
yip-3.743
hovah-3.611
 ingred-3.563
Token the
Token ID262
Feature activation+7.42e-02

Pos logit contributions
wcs+1.329
Cra+1.308
yip+1.254
kinson+1.207
 ingred+1.190
Neg logit contributions
iless-1.058
igible-1.049
 checkpoints-1.000
idated-0.951
ulnerable-0.944
Token defendant
Token ID11304
Feature activation-2.72e-01

Pos logit contributions
iless+0.049
igible+0.048
 checkpoints+0.046
idated+0.044
ulnerable+0.043
Neg logit contributions
wcs-0.056
Cra-0.054
yip-0.053
 ingred-0.050
kinson-0.050
Token in
Token ID287
Feature activation+1.05e+00

Pos logit contributions
wcs+0.190
Cra+0.184
yip+0.177
 ingred+0.169
hovah+0.168
Neg logit contributions
iless-0.194
igible-0.193
 checkpoints-0.186
idated-0.177
ulnerable-0.174
Token the
Token ID262
Feature activation-3.76e-01

Pos logit contributions
iless+2.508
igible+2.499
 checkpoints+2.436
idated+2.258
itimate+2.234
Neg logit contributions
wcs-3.186
Cra-3.114
yip-3.045
 ingred-2.904
hovah-2.900
Token river
Token ID7850
Feature activation-2.08e+00

Pos logit contributions
wcs+0.291
Cra+0.282
yip+0.272
 ingred+0.262
kinson+0.260
Neg logit contributions
iless-0.239
igible-0.237
 checkpoints-0.226
idated-0.215
ulnerable-0.211
Token to
Token ID284
Feature activation+1.08e+00

Pos logit contributions
wcs+1.488
Cra+1.433
yip+1.380
kinson+1.327
waters+1.319
Neg logit contributions
iless-1.438
igible-1.433
 checkpoints-1.366
idated-1.309
itimate-1.280
Token become
Token ID1716
Feature activation+2.57e+00

Pos logit contributions
iless+0.699
igible+0.694
 checkpoints+0.667
idated+0.631
itimate+0.619
Neg logit contributions
wcs-0.821
Cra-0.795
yip-0.770
 ingred-0.738
hovah-0.735
Token un
Token ID555
Feature activation+4.10e+00

Pos logit contributions
igible+1.609
iless+1.607
 checkpoints+1.542
idated+1.450
ulnerable+1.435
Neg logit contributions
wcs-2.017
Cra-1.955
yip-1.919
hovah-1.828
 ingred-1.822
Tokennav
Token ID28341
Feature activation+1.23e+01

Pos logit contributions
igible+2.719
iless+2.697
 checkpoints+2.534
idated+2.469
ulnerable+2.461
Neg logit contributions
wcs-3.064
Cra-2.929
yip-2.863
 ingred-2.805
hovah-2.800
Tokenig
Token ID328
Feature activation+4.16e+00

Pos logit contributions
igible+7.497
iless+7.453
ulnerable+6.873
idated+6.576
itimate+6.455
Neg logit contributions
Cra-9.870
wcs-9.790
yip-9.673
hovah-9.608
 ingred-9.424
Tokenable
Token ID540
Feature activation+1.78e+00

Pos logit contributions
iless+0.909
igible+0.900
 checkpoints+0.700
idated+0.664
itimate+0.620
Neg logit contributions
wcs-4.998
Cra-4.906
yip-4.837
 ingred-4.734
hovah-4.696
Token this
Token ID428
Feature activation+3.18e+00

Pos logit contributions
iless+1.277
igible+1.268
 checkpoints+1.228
idated+1.163
ulnerable+1.147
Neg logit contributions
wcs-1.231
Cra-1.193
yip-1.157
 ingred-1.101
hovah-1.100
Token summer
Token ID3931
Feature activation+2.44e+00

Pos logit contributions
iless+2.081
igible+2.066
 checkpoints+1.996
idated+1.888
itimate+1.859
Neg logit contributions
wcs-2.398
Cra-2.333
yip-2.256
hovah-2.166
 ingred-2.163
Token.
Token ID13
Feature activation-3.74e-01

Pos logit contributions
iless+1.710
igible+1.684
 checkpoints+1.626
idated+1.544
ulnerable+1.529
Neg logit contributions
wcs-1.733
Cra-1.686
yip-1.635
 ingred-1.571
hovah-1.553
Token this
Token ID428
Feature activation+1.62e+00

Pos logit contributions
wcs+2.739
Cra+2.671
yip+2.532
atos+2.489
 ingred+2.478
Neg logit contributions
iless-2.448
igible-2.404
 checkpoints-2.250
idated-2.232
ulnerable-2.185
Token into
Token ID656
Feature activation-4.68e+00

Pos logit contributions
iless+1.100
igible+1.095
 checkpoints+1.064
idated+0.993
itimate+0.985
Neg logit contributions
wcs-1.194
Cra-1.143
yip-1.119
hovah-1.069
kinson-1.056
Token perspective
Token ID6650
Feature activation+1.05e+00

Pos logit contributions
wcs+3.201
Cra+3.105
yip+2.899
kinson+2.856
 ingred+2.835
Neg logit contributions
iless-3.359
igible-3.307
 checkpoints-3.144
idated-3.087
ulnerable-3.013
Token,
Token ID11
Feature activation-2.69e-01

Pos logit contributions
iless+0.671
igible+0.665
 checkpoints+0.640
idated+0.601
ulnerable+0.592
Neg logit contributions
wcs-0.813
Cra-0.784
yip-0.760
 ingred-0.731
hovah-0.728
Token AT
Token ID5161
Feature activation+6.15e+00

Pos logit contributions
wcs+0.211
Cra+0.206
yip+0.199
 ingred+0.190
kinson+0.190
Neg logit contributions
iless-0.169
igible-0.167
 checkpoints-0.160
idated-0.152
ulnerable-0.149
Token&
Token ID5
Feature activation+1.17e+01

Pos logit contributions
igible+2.675
iless+2.673
 checkpoints+2.565
í+2.408
OAD+2.360
Neg logit contributions
wcs-5.991
yip-5.667
Cra-5.633
 ingred-5.610
hovah-5.609
TokenT
Token ID51
Feature activation+5.02e+00

Pos logit contributions
OAD+4.805
í+4.783
igible+4.593
 checkpoints+4.560
iless+4.435
Neg logit contributions
 ingred-11.248
wcs-11.114
hovah-11.055
yip-10.722
kinson-9.902
Token's
Token ID338
Feature activation+2.17e+00

Pos logit contributions
igible+2.900
iless+2.891
 checkpoints+2.796
idated+2.582
í+2.574
Neg logit contributions
wcs-4.156
Cra-3.977
yip-3.922
hovah-3.796
 ingred-3.740
Token spending
Token ID4581
Feature activation-3.17e+00

Pos logit contributions
igible+1.449
iless+1.443
 checkpoints+1.393
idated+1.306
itimate+1.290
Neg logit contributions
wcs-1.618
Cra-1.555
yip-1.510
 ingred-1.448
hovah-1.446
Token for
Token ID329
Feature activation+7.07e-01

Pos logit contributions
wcs+2.013
Cra+1.942
yip+1.863
kinson+1.773
 ingred+1.764
Neg logit contributions
iless-2.436
igible-2.407
 checkpoints-2.304
idated-2.235
ulnerable-2.210
Token three
Token ID1115
Feature activation+2.82e-01

Pos logit contributions
iless+0.451
igible+0.449
 checkpoints+0.431
idated+0.407
itimate+0.399
Neg logit contributions
wcs-0.548
Cra-0.531
yip-0.515
 ingred-0.493
hovah-0.492
Token All
Token ID1439
Feature activation+8.18e-02

Pos logit contributions
wcs+0.203
Cra+0.202
yip+0.189
atos+0.185
kinson+0.184
Neg logit contributions
iless-0.178
igible-0.175
 checkpoints-0.167
idated-0.158
itimate-0.157
Token these
Token ID777
Feature activation-2.57e-01

Pos logit contributions
iless+0.056
igible+0.056
 checkpoints+0.053
idated+0.051
ulnerable+0.050
Neg logit contributions
wcs-0.060
Cra-0.058
yip-0.055
 ingred-0.053
kinson-0.053
Token years
Token ID812
Feature activation-3.13e-01

Pos logit contributions
wcs+0.193
Cra+0.187
yip+0.179
 ingred+0.174
kinson+0.173
Neg logit contributions
iless-0.170
igible-0.169
 checkpoints-0.160
idated-0.153
ulnerable-0.151
Token we
Token ID356
Feature activation-1.15e+00

Pos logit contributions
wcs+0.232
Cra+0.225
yip+0.217
 ingred+0.208
hovah+0.207
Neg logit contributions
iless-0.210
igible-0.209
 checkpoints-0.199
idated-0.190
itimate-0.187
Token have
Token ID423
Feature activation-2.06e+00

Pos logit contributions
wcs+0.826
Cra+0.798
yip+0.765
kinson+0.734
 ingred+0.734
Neg logit contributions
iless-0.800
igible-0.795
 checkpoints-0.760
idated-0.724
itimate-0.715
Token navig
Token ID20436
Feature activation+1.16e+01

Pos logit contributions
wcs+1.432
Cra+1.381
yip+1.305
 ingred+1.266
kinson+1.263
Neg logit contributions
iless-1.467
igible-1.467
 checkpoints-1.384
ulnerable-1.327
idated-1.325
Tokenated
Token ID515
Feature activation+3.78e+00

Pos logit contributions
iless+4.268
igible+4.204
idated+3.773
 checkpoints+3.534
ulnerable+3.276
Neg logit contributions
wcs-11.776
yip-11.727
Cra-11.688
 ingred-11.393
hovah-11.234
Token the
Token ID262
Feature activation+2.79e-01

Pos logit contributions
iless+2.424
igible+2.390
 checkpoints+2.369
idated+2.197
ulnerable+2.135
Neg logit contributions
wcs-2.909
Cra-2.819
yip-2.751
hovah-2.625
 ingred-2.604
Token Bar
Token ID2409
Feature activation-5.73e+00

Pos logit contributions
iless+0.188
igible+0.187
 checkpoints+0.177
idated+0.169
ulnerable+0.167
Neg logit contributions
wcs-0.206
Cra-0.199
yip-0.192
 ingred-0.185
kinson-0.184
Tokenre
Token ID260
Feature activation-6.98e+00

Pos logit contributions
wcs+3.777
Cra+3.723
yip+3.540
atos+3.401
kinson+3.379
Neg logit contributions
iless-4.159
igible-4.150
 checkpoints-3.973
ulnerable-3.770
idated-3.750
Token and
Token ID290
Feature activation-3.87e-02

Pos logit contributions
wcs+4.869
Cra+4.825
yip+4.473
atos+4.441
kinson+4.357
Neg logit contributions
iless-4.680
igible-4.665
 checkpoints-4.428
idated-4.270
itimate-4.241
Token buy
Token ID2822
Feature activation+1.55e+00

Pos logit contributions
iless+1.574
igible+1.571
 checkpoints+1.511
idated+1.424
ulnerable+1.395
Neg logit contributions
wcs-1.875
Cra-1.810
yip-1.751
hovah-1.699
 ingred-1.679
Token you
Token ID345
Feature activation+1.92e+00

Pos logit contributions
iless+0.929
igible+0.921
 checkpoints+0.883
idated+0.827
itimate+0.809
Neg logit contributions
wcs-1.269
Cra-1.226
yip-1.192
hovah-1.150
 ingred-1.146
Token?
Token ID30
Feature activation+5.54e+00

Pos logit contributions
iless+1.101
igible+1.094
 checkpoints+1.047
idated+0.978
ulnerable+0.958
Neg logit contributions
wcs-1.608
Cra-1.558
yip-1.515
hovah-1.463
 ingred-1.461
Token While
Token ID2893
Feature activation-5.94e-01

Pos logit contributions
igible+3.177
iless+3.156
 checkpoints+3.080
í+2.851
idated+2.836
Neg logit contributions
wcs-4.647
yip-4.363
Cra-4.338
 ingred-4.226
hovah-4.192
Token AT
Token ID5161
Feature activation+7.35e+00

Pos logit contributions
wcs+0.479
Cra+0.467
yip+0.451
 ingred+0.433
kinson+0.433
Neg logit contributions
iless-0.360
igible-0.355
 checkpoints-0.337
idated-0.322
ulnerable-0.316
Token&
Token ID5
Feature activation+1.15e+01

Pos logit contributions
igible+3.024
iless+3.007
 checkpoints+2.921
í+2.775
OAD+2.740
Neg logit contributions
wcs-7.298
 ingred-6.905
yip-6.904
hovah-6.882
Cra-6.790
TokenT
Token ID51
Feature activation+5.19e+00

Pos logit contributions
í+4.716
OAD+4.696
igible+4.560
 checkpoints+4.532
iless+4.374
Neg logit contributions
 ingred-11.020
wcs-10.859
hovah-10.798
yip-10.454
kinson-9.661
Token's
Token ID338
Feature activation+2.59e+00

Pos logit contributions
igible+3.260
iless+3.244
 checkpoints+3.194
idated+2.939
í+2.927
Neg logit contributions
wcs-4.009
Cra-3.828
yip-3.766
hovah-3.644
 ingred-3.597
Token powerhouse
Token ID34886
Feature activation+2.22e+00

Pos logit contributions
igible+1.666
iless+1.658
 checkpoints+1.611
idated+1.495
itimate+1.482
Neg logit contributions
wcs-1.990
Cra-1.912
yip-1.864
hovah-1.793
 ingred-1.785
Token FISA
Token ID44073
Feature activation+1.62e+00

Pos logit contributions
igible+1.515
iless+1.514
 checkpoints+1.467
idated+1.370
itimate+1.359
Neg logit contributions
wcs-1.612
Cra-1.551
yip-1.512
hovah-1.443
 ingred-1.436
Token lobbyist
Token ID35196
Feature activation+3.55e+00

Pos logit contributions
iless+1.120
igible+1.113
 checkpoints+1.082
idated+1.016
ulnerable+1.004
Neg logit contributions
wcs-1.166
Cra-1.122
yip-1.085
 ingred-1.040
hovah-1.034
Token gain
Token ID4461
Feature activation-1.73e+00

Pos logit contributions
iless+0.721
igible+0.716
 checkpoints+0.682
idated+0.644
ulnerable+0.631
Neg logit contributions
wcs-1.021
Cra-0.992
yip-0.961
 ingred-0.927
kinson-0.922
Token,
Token ID11
Feature activation-3.51e-01

Pos logit contributions
wcs+1.175
Cra+1.122
yip+1.081
kinson+1.032
 ingred+1.030
Neg logit contributions
iless-1.274
igible-1.267
 checkpoints-1.220
idated-1.172
itimate-1.153
Token wildlife
Token ID15599
Feature activation+1.96e-01

Pos logit contributions
wcs+0.244
Cra+0.235
yip+0.226
 ingred+0.217
kinson+0.215
Neg logit contributions
iless-0.253
igible-0.251
 checkpoints-0.239
idated-0.231
ulnerable-0.228
Token sightings
Token ID36242
Feature activation-1.14e+00

Pos logit contributions
iless+0.127
igible+0.126
 checkpoints+0.119
idated+0.114
itimate+0.112
Neg logit contributions
wcs-0.151
Cra-0.146
yip-0.141
 ingred-0.136
kinson-0.135
Token,
Token ID11
Feature activation-5.15e-01

Pos logit contributions
wcs+0.830
Cra+0.798
yip+0.772
 ingred+0.740
hovah+0.735
Neg logit contributions
iless-0.779
igible-0.773
 checkpoints-0.741
idated-0.707
itimate-0.696
Token navig
Token ID20436
Feature activation+1.14e+01

Pos logit contributions
wcs+0.379
Cra+0.366
yip+0.355
 ingred+0.340
kinson+0.337
Neg logit contributions
iless-0.349
igible-0.346
 checkpoints-0.328
idated-0.316
ulnerable-0.311
Tokenational
Token ID864
Feature activation+3.32e+00

Pos logit contributions
igible+4.278
iless+4.129
 checkpoints+3.761
idated+3.460
itimate+3.426
Neg logit contributions
wcs-11.438
Cra-11.205
yip-11.084
 ingred-10.929
hovah-10.851
Token challenges
Token ID6459
Feature activation+5.97e-01

Pos logit contributions
iless+2.127
igible+2.126
 checkpoints+2.091
idated+1.930
itimate+1.896
Neg logit contributions
wcs-2.542
Cra-2.465
yip-2.404
hovah-2.302
kinson-2.278
Token,
Token ID11
Feature activation+3.01e-02

Pos logit contributions
iless+0.396
igible+0.393
 checkpoints+0.379
idated+0.358
ulnerable+0.352
Neg logit contributions
wcs-0.448
Cra-0.434
yip-0.420
 ingred-0.402
hovah-0.400
Token even
Token ID772
Feature activation-9.17e-01

Pos logit contributions
iless+0.020
igible+0.020
 checkpoints+0.019
idated+0.018
ulnerable+0.018
Neg logit contributions
wcs-0.022
Cra-0.021
yip-0.021
 ingred-0.020
kinson-0.020
Token solitude
Token ID49917
Feature activation+2.98e-01

Pos logit contributions
wcs+0.700
Cra+0.677
yip+0.656
 ingred+0.632
kinson+0.623
Neg logit contributions
iless-0.595
igible-0.590
 checkpoints-0.556
idated-0.538
itimate-0.529
Token who
Token ID508
Feature activation+1.58e+00

Pos logit contributions
wcs+1.463
Cra+1.414
yip+1.359
 ingred+1.299
kinson+1.296
Neg logit contributions
iless-1.388
igible-1.375
 checkpoints-1.316
idated-1.254
itimate-1.234
Token made
Token ID925
Feature activation-6.39e-01

Pos logit contributions
iless+1.120
igible+1.113
 checkpoints+1.074
idated+1.020
ulnerable+1.001
Neg logit contributions
wcs-1.113
Cra-1.076
yip-1.041
 ingred-0.992
hovah-0.987
Token sure
Token ID1654
Feature activation+3.25e+00

Pos logit contributions
wcs+0.510
Cra+0.497
yip+0.477
 ingred+0.463
atos+0.458
Neg logit contributions
iless-0.392
igible-0.388
 checkpoints-0.362
idated-0.351
ulnerable-0.346
Token Thomas
Token ID5658
Feature activation-7.68e-02

Pos logit contributions
iless+2.059
igible+2.036
 checkpoints+1.994
idated+1.859
itimate+1.820
Neg logit contributions
wcs-2.516
Cra-2.444
yip-2.385
hovah-2.279
 ingred-2.261
Token safely
Token ID11512
Feature activation+5.20e+00

Pos logit contributions
wcs+0.052
Cra+0.050
yip+0.048
 ingred+0.046
kinson+0.046
Neg logit contributions
iless-0.056
igible-0.056
 checkpoints-0.054
idated-0.051
ulnerable-0.051
Token navig
Token ID20436
Feature activation+1.12e+01

Pos logit contributions
iless+3.418
igible+3.411
 checkpoints+3.360
idated+3.110
í+3.100
Neg logit contributions
wcs-3.821
Cra-3.798
yip-3.734
 ingred-3.495
hovah-3.480
Tokenated
Token ID515
Feature activation+3.21e+00

Pos logit contributions
igible+4.002
iless+3.902
idated+3.546
 checkpoints+3.484
í+3.146
Neg logit contributions
yip-11.443
wcs-11.354
Cra-11.291
 ingred-11.106
hovah-10.881
Token
Token ID564
Feature activation+6.60e-01

Pos logit contributions
iless+2.184
igible+2.157
 checkpoints+2.136
idated+1.981
ulnerable+1.942
Neg logit contributions
wcs-2.335
Cra-2.269
yip-2.215
hovah-2.110
kinson-2.088
Token
Token ID250
Feature activation+3.39e-01

Pos logit contributions
iless+0.531
igible+0.526
 checkpoints+0.511
idated+0.489
ulnerable+0.481
Neg logit contributions
wcs-0.405
Cra-0.388
yip-0.375
kinson-0.351
hovah-0.350
Tokenurban
Token ID32679
Feature activation+2.25e-01

Pos logit contributions
iless+0.240
igible+0.238
 checkpoints+0.230
idated+0.218
ulnerable+0.215
Neg logit contributions
wcs-0.240
Cra-0.231
yip-0.224
 ingred-0.214
hovah-0.213
Token for
Token ID329
Feature activation-6.67e-01

Pos logit contributions
iless+0.146
igible+0.145
 checkpoints+0.139
idated+0.131
itimate+0.130
Neg logit contributions
wcs-0.171
Cra-0.166
yip-0.160
 ingred-0.154
kinson-0.153
Token in
Token ID287
Feature activation-8.82e-01

Pos logit contributions
wcs+0.013
Cra+0.013
yip+0.012
 ingred+0.012
kinson+0.012
Neg logit contributions
iless-0.012
igible-0.012
 checkpoints-0.012
idated-0.011
ulnerable-0.011
Token May
Token ID1737
Feature activation+4.89e+00

Pos logit contributions
wcs+0.652
Cra+0.633
yip+0.609
 ingred+0.583
kinson+0.583
Neg logit contributions
iless-0.590
igible-0.588
 checkpoints-0.561
idated-0.535
ulnerable-0.528
Token 1996
Token ID8235
Feature activation-7.25e-01

Pos logit contributions
iless+3.087
igible+3.034
 checkpoints+2.939
idated+2.756
í+2.733
Neg logit contributions
wcs-3.844
Cra-3.646
yip-3.577
 ingred-3.462
hovah-3.433
Token,
Token ID11
Feature activation-1.96e+00

Pos logit contributions
wcs+0.544
Cra+0.525
yip+0.508
 ingred+0.487
hovah+0.486
Neg logit contributions
iless-0.479
igible-0.477
 checkpoints-0.458
idated-0.435
itimate-0.427
Token CBS
Token ID11133
Feature activation+6.47e+00

Pos logit contributions
wcs+1.403
Cra+1.363
yip+1.310
 ingred+1.263
kinson+1.261
Neg logit contributions
igible-1.336
iless-1.331
 checkpoints-1.268
idated-1.224
ulnerable-1.204
Token correspondent
Token ID21076
Feature activation+1.11e+01

Pos logit contributions
iless+3.849
igible+3.797
 checkpoints+3.645
í+3.453
idated+3.408
Neg logit contributions
wcs-5.252
Cra-5.021
yip-5.018
hovah-4.705
 ingred-4.698
Token Leslie
Token ID26909
Feature activation+3.10e+00

Pos logit contributions
iless+6.325
igible+6.122
 checkpoints+6.084
í+5.851
abeth+5.663
Neg logit contributions
wcs-8.842
yip-8.684
Cra-8.412
hovah-8.092
 ingred-7.976
Token St
Token ID520
Feature activation-1.61e+00

Pos logit contributions
iless+1.868
igible+1.854
 checkpoints+1.784
idated+1.662
itimate+1.650
Neg logit contributions
wcs-2.492
Cra-2.399
yip-2.362
 ingred-2.277
hovah-2.244
Tokenahl
Token ID15668
Feature activation+8.99e-01

Pos logit contributions
wcs+1.224
Cra+1.214
yip+1.167
kinson+1.157
atos+1.134
Neg logit contributions
iless-0.981
igible-0.980
 checkpoints-0.968
idated-0.899
ulnerable-0.874
Token asked
Token ID1965
Feature activation+2.24e+00

Pos logit contributions
iless+0.574
igible+0.571
 checkpoints+0.548
idated+0.518
itimate+0.509
Neg logit contributions
wcs-0.696
Cra-0.673
yip-0.651
 ingred-0.624
kinson-0.623
Token Clinton
Token ID2605
Feature activation-2.20e-01

Pos logit contributions
iless+1.506
igible+1.490
 checkpoints+1.440
idated+1.357
itimate+1.336
Neg logit contributions
wcs-1.666
Cra-1.605
yip-1.558
hovah-1.487
 ingred-1.483
Token spring
Token ID6076
Feature activation+6.07e-01

Pos logit contributions
iless+1.450
igible+1.445
 checkpoints+1.386
idated+1.304
itimate+1.281
Neg logit contributions
wcs-1.870
Cra-1.816
yip-1.764
hovah-1.697
 ingred-1.696
Token.
Token ID13
Feature activation+1.03e+00

Pos logit contributions
iless+0.433
igible+0.429
 checkpoints+0.414
idated+0.394
ulnerable+0.387
Neg logit contributions
wcs-0.425
Cra-0.411
yip-0.399
 ingred-0.381
hovah-0.378
Token New
Token ID968
Feature activation+4.32e+00

Pos logit contributions
iless+0.646
igible+0.642
 checkpoints+0.616
idated+0.582
itimate+0.571
Neg logit contributions
wcs-0.806
Cra-0.780
yip-0.758
 ingred-0.727
hovah-0.723
Token York
Token ID1971
Feature activation+2.76e+00

Pos logit contributions
igible+2.483
iless+2.480
 checkpoints+2.364
idated+2.207
itimate+2.172
Neg logit contributions
wcs-3.559
Cra-3.452
yip-3.407
hovah-3.234
 ingred-3.234
Token Times
Token ID3782
Feature activation+4.27e+00

Pos logit contributions
iless+1.879
igible+1.854
 checkpoints+1.792
idated+1.693
itimate+1.672
Neg logit contributions
wcs-2.028
Cra-1.941
yip-1.907
hovah-1.806
 ingred-1.800
Token reporter
Token ID9095
Feature activation+1.11e+01

Pos logit contributions
iless+2.223
igible+2.220
 checkpoints+2.107
idated+1.951
í+1.935
Neg logit contributions
wcs-3.791
Cra-3.636
yip-3.610
hovah-3.430
 ingred-3.428
Token Jonathan
Token ID11232
Feature activation-3.18e-02

Pos logit contributions
iless+6.229
igible+6.227
 checkpoints+6.129
í+5.860
abeth+5.708
Neg logit contributions
wcs-8.752
yip-8.260
Cra-8.166
 ingred-7.901
hovah-7.817
Token We
Token ID775
Feature activation-2.26e+00

Pos logit contributions
wcs+0.022
Cra+0.022
yip+0.021
 ingred+0.020
hovah+0.020
Neg logit contributions
iless-0.023
igible-0.022
 checkpoints-0.022
idated-0.021
ulnerable-0.020
Tokenisman
Token ID23845
Feature activation+2.79e-01

Pos logit contributions
wcs+1.661
Cra+1.634
yip+1.563
hovah+1.503
kinson+1.499
Neg logit contributions
iless-1.498
igible-1.468
 checkpoints-1.431
idated-1.347
ulnerable-1.325
Token wrote
Token ID2630
Feature activation+1.97e+00

Pos logit contributions
iless+0.191
igible+0.189
 checkpoints+0.182
idated+0.173
itimate+0.170
Neg logit contributions
wcs-0.203
Cra-0.197
yip-0.190
kinson-0.181
 ingred-0.181
Token in
Token ID287
Feature activation-8.32e-01

Pos logit contributions
iless+1.275
igible+1.270
 checkpoints+1.219
idated+1.146
itimate+1.129
Neg logit contributions
wcs-1.506
Cra-1.448
yip-1.420
 ingred-1.352
hovah-1.345
Token locations
Token ID7064
Feature activation+2.45e+00

Pos logit contributions
wcs+1.718
Cra+1.672
yip+1.606
 ingred+1.548
atos+1.536
Neg logit contributions
iless-1.465
igible-1.463
 checkpoints-1.380
idated-1.322
ulnerable-1.308
Token which
Token ID543
Feature activation+2.67e+00

Pos logit contributions
iless+1.489
igible+1.480
 checkpoints+1.429
idated+1.340
ulnerable+1.307
Neg logit contributions
wcs-1.973
Cra-1.907
yip-1.856
hovah-1.776
 ingred-1.776
Token are
Token ID389
Feature activation+1.86e+00

Pos logit contributions
iless+1.685
igible+1.680
 checkpoints+1.627
idated+1.528
itimate+1.492
Neg logit contributions
wcs-2.085
Cra-2.023
yip-1.959
hovah-1.874
 ingred-1.873
Token empty
Token ID6565
Feature activation+9.98e-01

Pos logit contributions
iless+1.276
igible+1.271
 checkpoints+1.230
idated+1.162
ulnerable+1.141
Neg logit contributions
wcs-1.355
Cra-1.309
yip-1.271
 ingred-1.210
hovah-1.208
Token.
Token ID13
Feature activation+2.55e+00

Pos logit contributions
iless+0.652
igible+0.647
 checkpoints+0.623
idated+0.589
ulnerable+0.578
Neg logit contributions
wcs-0.759
Cra-0.735
yip-0.712
 ingred-0.682
hovah-0.679
Token Compl
Token ID20011
Feature activation+1.08e+01

Pos logit contributions
iless+1.485
igible+1.473
 checkpoints+1.419
idated+1.324
ulnerable+1.296
Neg logit contributions
wcs-2.121
Cra-2.057
yip-2.006
 ingred-1.923
hovah-1.921
Tokeniment
Token ID3681
Feature activation-6.82e-01

Pos logit contributions
iless+6.864
igible+6.796
idated+6.237
í+6.237
 checkpoints+6.138
Neg logit contributions
Cra-7.833
yip-7.741
wcs-7.727
hovah-7.270
 ingred-7.260
Token with
Token ID351
Feature activation-1.65e-01

Pos logit contributions
wcs+0.505
Cra+0.491
yip+0.473
 ingred+0.453
hovah+0.451
Neg logit contributions
iless-0.456
igible-0.454
 checkpoints-0.434
idated-0.413
ulnerable-0.406
Token previous
Token ID2180
Feature activation-3.39e-01

Pos logit contributions
wcs+0.125
Cra+0.121
yip+0.117
 ingred+0.113
kinson+0.112
Neg logit contributions
iless-0.108
igible-0.107
 checkpoints-0.102
idated-0.097
ulnerable-0.095
Token ser
Token ID1055
Feature activation-3.89e+00

Pos logit contributions
wcs+0.258
Cra+0.250
yip+0.242
 ingred+0.232
hovah+0.230
Neg logit contributions
iless-0.221
igible-0.220
 checkpoints-0.210
idated-0.200
itimate-0.196
Tokenach
Token ID620
Feature activation+5.45e-01

Pos logit contributions
wcs+2.938
Cra+2.835
yip+2.728
kinson+2.659
atos+2.656
Neg logit contributions
iless-2.500
igible-2.469
 checkpoints-2.396
idated-2.232
itimate-2.226
Token the
Token ID262
Feature activation+2.02e-01

Pos logit contributions
wcs+1.120
Cra+1.088
yip+1.046
hovah+1.002
 ingred+1.001
Neg logit contributions
iless-0.941
igible-0.928
 checkpoints-0.892
idated-0.845
ulnerable-0.829
Token
Token ID564
Feature activation-1.53e+00

Pos logit contributions
iless+0.130
igible+0.128
 checkpoints+0.123
idated+0.117
ulnerable+0.114
Neg logit contributions
wcs-0.157
Cra-0.152
yip-0.147
 ingred-0.141
hovah-0.140
Token
Token ID250
Feature activation-9.78e-01

Pos logit contributions
wcs+0.870
Cra+0.838
yip+0.791
atos+0.750
 ingred+0.749
Neg logit contributions
iless-1.289
igible-1.283
 checkpoints-1.243
idated-1.188
ulnerable-1.177
TokenF
Token ID37
Feature activation+3.20e+00

Pos logit contributions
wcs+0.711
Cra+0.691
yip+0.662
 ingred+0.631
hovah+0.630
Neg logit contributions
iless-0.671
igible-0.665
 checkpoints-0.644
idated-0.609
itimate-0.597
TokenTC
Token ID4825
Feature activation-3.09e-02

Pos logit contributions
igible+1.998
iless+1.995
 checkpoints+1.898
idated+1.813
ulnerable+1.782
Neg logit contributions
wcs-2.513
Cra-2.415
yip-2.352
 ingred-2.275
hovah-2.259
Token Compl
Token ID20011
Feature activation+1.07e+01

Pos logit contributions
wcs+0.024
Cra+0.023
yip+0.022
 ingred+0.022
hovah+0.021
Neg logit contributions
iless-0.020
igible-0.020
 checkpoints-0.019
idated-0.018
itimate-0.017
Tokenaint
Token ID2913
Feature activation+3.14e+00

Pos logit contributions
iless+5.027
igible+5.017
í+4.698
idated+4.385
ulnerable+4.383
Neg logit contributions
wcs-9.655
yip-9.532
Cra-9.362
 ingred-9.261
hovah-8.825
Token Assistant
Token ID15286
Feature activation-2.18e+00

Pos logit contributions
iless+2.121
igible+2.113
 checkpoints+2.020
idated+1.917
í+1.890
Neg logit contributions
wcs-2.311
Cra-2.221
yip-2.176
 ingred-2.076
hovah-2.068
Token
Token ID447
Feature activation-9.28e-01

Pos logit contributions
wcs+1.603
Cra+1.561
yip+1.499
 ingred+1.433
kinson+1.432
Neg logit contributions
iless-1.460
igible-1.436
 checkpoints-1.396
idated-1.328
itimate-1.294
Token
Token ID251
Feature activation-2.46e+00

Pos logit contributions
wcs+0.599
Cra+0.577
yip+0.555
 ingred+0.527
hovah+0.525
Neg logit contributions
iless-0.712
igible-0.707
 checkpoints-0.683
idated-0.653
itimate-0.643
Token to
Token ID284
Feature activation-1.21e+00

Pos logit contributions
wcs+1.537
Cra+1.483
yip+1.425
 ingred+1.342
hovah+1.338
Neg logit contributions
iless-1.933
igible-1.906
 checkpoints-1.858
idated-1.769
ulnerable-1.740
Token a
Token ID257
Feature activation+3.45e-01

Pos logit contributions
iless+0.031
igible+0.031
 checkpoints+0.030
idated+0.028
ulnerable+0.028
Neg logit contributions
wcs-0.034
Cra-0.033
yip-0.032
 ingred-0.031
kinson-0.031
Token licensing
Token ID15665
Feature activation+1.66e+00

Pos logit contributions
iless+0.224
igible+0.221
 checkpoints+0.212
idated+0.202
ulnerable+0.198
Neg logit contributions
wcs-0.265
Cra-0.257
yip-0.248
 ingred-0.238
kinson-0.237
Token division
Token ID7297
Feature activation+5.14e+00

Pos logit contributions
iless+1.005
igible+1.003
 checkpoints+0.962
idated+0.902
itimate+0.889
Neg logit contributions
wcs-1.342
Cra-1.296
yip-1.265
hovah-1.212
 ingred-1.212
Token of
Token ID286
Feature activation-9.86e-01

Pos logit contributions
igible+3.375
iless+3.373
 checkpoints+3.242
idated+3.047
í+3.038
Neg logit contributions
wcs-3.804
Cra-3.641
yip-3.601
hovah-3.451
 ingred-3.418
Token AT
Token ID5161
Feature activation+5.94e+00

Pos logit contributions
wcs+0.741
Cra+0.725
yip+0.695
kinson+0.668
 ingred+0.666
Neg logit contributions
iless-0.653
igible-0.640
 checkpoints-0.617
idated-0.584
ulnerable-0.579
Token&
Token ID5
Feature activation+1.06e+01

Pos logit contributions
igible+2.924
iless+2.898
 checkpoints+2.755
idated+2.554
OAD+2.506
Neg logit contributions
wcs-5.459
Cra-5.171
yip-5.068
hovah-4.957
 ingred-4.943
TokenT
Token ID51
Feature activation+3.83e+00

Pos logit contributions
OAD+4.526
 checkpoints+4.429
í+4.425
igible+4.365
iless+4.187
Neg logit contributions
wcs-10.171
 ingred-10.030
hovah-9.828
yip-9.751
kinson-8.949
Token/
Token ID14
Feature activation+2.86e+00

Pos logit contributions
iless+2.573
igible+2.571
 checkpoints+2.469
idated+2.343
ulnerable+2.295
Neg logit contributions
wcs-2.831
Cra-2.718
yip-2.645
 ingred-2.536
hovah-2.526
TokenWestern
Token ID24227
Feature activation+1.23e+00

Pos logit contributions
iless+2.050
igible+2.046
 checkpoints+1.961
idated+1.883
OAD+1.854
Neg logit contributions
wcs-1.975
Cra-1.867
yip-1.850
 ingred-1.775
hovah-1.761
Token Electric
Token ID13944
Feature activation+2.89e+00

Pos logit contributions
iless+0.739
igible+0.735
 checkpoints+0.703
idated+0.663
itimate+0.649
Neg logit contributions
wcs-0.996
Cra-0.964
yip-0.937
 ingred-0.900
hovah-0.897
Token,
Token ID11
Feature activation-1.15e-01

Pos logit contributions
igible+1.919
iless+1.915
 checkpoints+1.840
idated+1.748
itimate+1.705
Neg logit contributions
wcs-2.162
Cra-2.076
yip-2.033
 ingred-1.948
hovah-1.933
TokenTwo
Token ID7571
Feature activation+2.53e+00

Pos logit contributions
iless+1.019
igible+1.015
 checkpoints+0.977
idated+0.935
itimate+0.921
Neg logit contributions
wcs-0.893
Cra-0.849
yip-0.837
hovah-0.796
 ingred-0.796
Token years
Token ID812
Feature activation-1.48e+00

Pos logit contributions
iless+1.545
igible+1.530
 checkpoints+1.486
idated+1.373
itimate+1.360
Neg logit contributions
wcs-2.023
Cra-1.959
yip-1.910
hovah-1.831
 ingred-1.821
Token ago
Token ID2084
Feature activation+2.09e+00

Pos logit contributions
wcs+1.106
Cra+1.069
yip+1.033
 ingred+0.987
kinson+0.987
Neg logit contributions
iless-0.985
igible-0.982
 checkpoints-0.943
idated-0.897
itimate-0.880
Token Rolling
Token ID21567
Feature activation+4.55e+00

Pos logit contributions
iless+1.330
igible+1.319
 checkpoints+1.267
idated+1.193
ulnerable+1.171
Neg logit contributions
wcs-1.625
Cra-1.577
yip-1.537
 ingred-1.464
hovah-1.460
Token Stone
Token ID8026
Feature activation+5.58e+00

Pos logit contributions
iless+1.610
igible+1.598
 checkpoints+1.490
idated+1.322
ulnerable+1.305
Neg logit contributions
wcs-4.816
Cra-4.670
yip-4.634
 ingred-4.466
hovah-4.447
Token reporter
Token ID9095
Feature activation+1.05e+01

Pos logit contributions
iless+3.436
igible+3.425
 checkpoints+3.225
í+3.069
idated+3.054
Neg logit contributions
wcs-4.434
Cra-4.263
yip-4.171
 ingred-3.957
hovah-3.944
Token Michael
Token ID3899
Feature activation-6.19e-02

Pos logit contributions
iless+6.043
igible+5.994
 checkpoints+5.898
í+5.582
abeth+5.480
Neg logit contributions
wcs-8.307
yip-7.832
Cra-7.802
 ingred-7.535
hovah-7.465
Token Hastings
Token ID38330
Feature activation+3.66e+00

Pos logit contributions
wcs+0.046
Cra+0.044
yip+0.043
 ingred+0.041
hovah+0.041
Neg logit contributions
iless-0.042
igible-0.042
 checkpoints-0.040
idated-0.038
ulnerable-0.037
Token writing
Token ID3597
Feature activation+2.44e+00

Pos logit contributions
iless+2.468
igible+2.435
 checkpoints+2.351
idated+2.215
í+2.204
Neg logit contributions
wcs-2.697
Cra-2.610
yip-2.549
 ingred-2.429
hovah-2.423
Token in
Token ID287
Feature activation-1.25e+00

Pos logit contributions
iless+1.630
igible+1.623
 checkpoints+1.554
idated+1.467
ulnerable+1.445
Neg logit contributions
wcs-1.820
Cra-1.750
yip-1.711
 ingred-1.624
hovah-1.618
Token America
Token ID2253
Feature activation+3.03e+00

Pos logit contributions
wcs+0.942
Cra+0.914
yip+0.882
 ingred+0.847
kinson+0.844
Neg logit contributions
iless-0.818
igible-0.809
 checkpoints-0.782
idated-0.739
itimate-0.725
Token housing
Token ID5627
Feature activation-2.18e+00

Pos logit contributions
igible+1.477
iless+1.476
 checkpoints+1.426
idated+1.347
itimate+1.329
Neg logit contributions
wcs-1.511
Cra-1.439
yip-1.412
hovah-1.348
 ingred-1.345
Token market
Token ID1910
Feature activation-2.66e+00

Pos logit contributions
wcs+1.466
Cra+1.434
yip+1.356
kinson+1.301
 ingred+1.298
Neg logit contributions
iless-1.604
igible-1.589
 checkpoints-1.507
idated-1.463
ulnerable-1.436
Token from
Token ID422
Feature activation-5.56e-01

Pos logit contributions
wcs+1.810
Cra+1.729
yip+1.657
kinson+1.596
waters+1.578
Neg logit contributions
iless-1.927
igible-1.927
 checkpoints-1.830
idated-1.766
itimate-1.744
Token real
Token ID1103
Feature activation+3.59e-01

Pos logit contributions
wcs+0.414
Cra+0.404
yip+0.388
 ingred+0.372
kinson+0.372
Neg logit contributions
iless-0.369
igible-0.367
 checkpoints-0.351
idated-0.334
itimate-0.329
Token estate
Token ID7964
Feature activation-6.43e-01

Pos logit contributions
iless+0.231
igible+0.230
 checkpoints+0.221
idated+0.209
itimate+0.206
Neg logit contributions
wcs-0.276
Cra-0.267
yip-0.258
 ingred-0.248
hovah-0.247
Token reporter
Token ID9095
Feature activation+1.04e+01

Pos logit contributions
wcs+0.518
Cra+0.505
yip+0.487
 ingred+0.470
kinson+0.467
Neg logit contributions
iless-0.390
igible-0.387
 checkpoints-0.368
idated-0.349
ulnerable-0.342
Token,
Token ID11
Feature activation+8.17e-01

Pos logit contributions
iless+6.156
igible+6.146
 checkpoints+6.046
í+5.661
abeth+5.537
Neg logit contributions
wcs-7.870
Cra-7.421
yip-7.365
hovah-7.131
 ingred-7.101
Token Tara
Token ID37723
Feature activation-8.27e-01

Pos logit contributions
iless+0.538
igible+0.535
 checkpoints+0.514
idated+0.487
ulnerable+0.478
Neg logit contributions
wcs-0.616
Cra-0.597
yip-0.578
 ingred-0.553
hovah-0.551
Token Perkins
Token ID29618
Feature activation+4.06e+00

Pos logit contributions
wcs+0.610
Cra+0.595
yip+0.573
kinson+0.547
hovah+0.545
Neg logit contributions
iless-0.556
igible-0.551
 checkpoints-0.531
idated-0.503
ulnerable-0.495
Token,
Token ID11
Feature activation+3.42e-01

Pos logit contributions
iless+2.710
igible+2.675
 checkpoints+2.596
í+2.415
idated+2.412
Neg logit contributions
wcs-3.035
Cra-2.884
yip-2.855
hovah-2.717
 ingred-2.706
Token and
Token ID290
Feature activation+2.90e+00

Pos logit contributions
iless+0.240
igible+0.239
 checkpoints+0.229
idated+0.219
ulnerable+0.216
Neg logit contributions
wcs-0.242
Cra-0.234
yip-0.225
 ingred-0.216
kinson-0.216
Token BT
Token ID22205
Feature activation+4.75e+00

Pos logit contributions
iless+0.229
igible+0.227
 checkpoints+0.218
idated+0.207
ulnerable+0.203
Neg logit contributions
wcs-0.258
Cra-0.250
yip-0.242
 ingred-0.231
hovah-0.231
Token,
Token ID11
Feature activation-5.25e-01

Pos logit contributions
iless+3.139
igible+3.116
 checkpoints+3.000
í+2.845
idated+2.843
Neg logit contributions
wcs-3.501
Cra-3.354
yip-3.263
hovah-3.157
 ingred-3.142
Token O
Token ID440
Feature activation+2.90e+00

Pos logit contributions
wcs+0.394
Cra+0.383
yip+0.370
kinson+0.353
 ingred+0.352
Neg logit contributions
iless-0.347
igible-0.344
 checkpoints-0.330
idated-0.313
ulnerable-0.308
Token2
Token ID17
Feature activation+1.53e+00

Pos logit contributions
iless+1.702
igible+1.698
 checkpoints+1.618
idated+1.522
ulnerable+1.509
Neg logit contributions
wcs-2.372
Cra-2.291
yip-2.210
 ingred-2.150
hovah-2.146
Token and
Token ID290
Feature activation+2.09e+00

Pos logit contributions
iless+1.004
igible+1.004
 checkpoints+0.963
idated+0.909
ulnerable+0.894
Neg logit contributions
wcs-1.145
Cra-1.106
yip-1.068
 ingred-1.033
kinson-1.025
Token Virgin
Token ID5283
Feature activation+1.04e+01

Pos logit contributions
iless+1.359
igible+1.350
 checkpoints+1.301
idated+1.227
itimate+1.205
Neg logit contributions
wcs-1.600
Cra-1.544
yip-1.499
 ingred-1.442
hovah-1.433
Token having
Token ID1719
Feature activation+2.11e+00

Pos logit contributions
iless+5.989
igible+5.920
 checkpoints+5.677
í+5.533
OAD+5.240
Neg logit contributions
wcs-8.190
Cra-7.772
hovah-7.620
yip-7.531
 ingred-7.419
Token blocked
Token ID10226
Feature activation+1.72e+00

Pos logit contributions
iless+1.432
igible+1.426
 checkpoints+1.383
idated+1.303
itimate+1.284
Neg logit contributions
wcs-1.546
Cra-1.490
yip-1.445
 ingred-1.380
hovah-1.379
Token addresses
Token ID9405
Feature activation+3.05e+00

Pos logit contributions
iless+1.065
igible+1.061
 checkpoints+1.022
idated+0.954
ulnerable+0.944
Neg logit contributions
wcs-1.376
Cra-1.322
yip-1.283
 ingred-1.239
hovah-1.234
Token on
Token ID319
Feature activation+2.67e+00

Pos logit contributions
iless+2.090
igible+2.088
 checkpoints+2.020
idated+1.907
ulnerable+1.886
Neg logit contributions
wcs-2.197
Cra-2.128
yip-2.056
hovah-1.975
 ingred-1.973
Token it
Token ID340
Feature activation+2.05e+00

Pos logit contributions
igible+1.665
iless+1.663
 checkpoints+1.608
idated+1.495
ulnerable+1.485
Neg logit contributions
wcs-2.108
Cra-2.022
yip-1.965
 ingred-1.897
hovah-1.892
Token-
Token ID12
Feature activation+2.45e+00

Pos logit contributions
iless+0.224
igible+0.223
 checkpoints+0.214
idated+0.202
ulnerable+0.198
Neg logit contributions
wcs-0.278
Cra-0.269
yip-0.261
 ingred-0.250
hovah-0.249
TokenC
Token ID34
Feature activation-3.65e-01

Pos logit contributions
iless+1.855
igible+1.852
 checkpoints+1.778
idated+1.710
OAD+1.687
Neg logit contributions
wcs-1.593
yip-1.494
Cra-1.484
 ingred-1.428
hovah-1.422
Tokenrazy
Token ID5918
Feature activation+1.58e+00

Pos logit contributions
wcs+0.249
Cra+0.240
yip+0.232
 ingred+0.220
hovah+0.220
Neg logit contributions
iless-0.266
igible-0.265
 checkpoints-0.256
idated-0.243
ulnerable-0.239
Token Air
Token ID3701
Feature activation+3.20e+00

Pos logit contributions
iless+1.059
igible+1.055
 checkpoints+1.014
idated+0.960
ulnerable+0.945
Neg logit contributions
wcs-1.174
Cra-1.129
yip-1.100
 ingred-1.050
hovah-1.046
Tokenplane
Token ID14382
Feature activation+3.85e+00

Pos logit contributions
iless+2.203
igible+2.198
 checkpoints+2.109
idated+1.983
itimate+1.964
Neg logit contributions
wcs-2.312
Cra-2.216
yip-2.159
 ingred-2.065
hovah-2.058
Token Pilot
Token ID21697
Feature activation+1.03e+01

Pos logit contributions
iless+2.479
igible+2.475
 checkpoints+2.396
idated+2.222
í+2.209
Neg logit contributions
wcs-2.933
Cra-2.780
yip-2.771
hovah-2.653
 ingred-2.638
Token-
Token ID12
Feature activation+1.96e+00

Pos logit contributions
iless+5.929
igible+5.832
 checkpoints+5.701
í+5.275
ulnerable+5.198
Neg logit contributions
wcs-7.997
yip-7.805
Cra-7.424
hovah-7.296
 ingred-7.265
Token08
Token ID2919
Feature activation-3.04e+00

Pos logit contributions
iless+1.483
igible+1.479
 checkpoints+1.422
idated+1.365
itimate+1.345
Neg logit contributions
wcs-1.271
Cra-1.192
yip-1.189
 ingred-1.136
hovah-1.131
Token Election
Token ID14219
Feature activation-2.02e+00

Pos logit contributions
wcs+2.316
Cra+2.266
yip+2.187
kinson+2.090
atos+2.086
Neg logit contributions
iless-1.947
igible-1.914
 checkpoints-1.864
idated-1.758
itimate-1.717
Token-
Token ID12
Feature activation-9.50e-01

Pos logit contributions
wcs+1.539
Cra+1.498
yip+1.432
 ingred+1.382
hovah+1.375
Neg logit contributions
iless-1.315
igible-1.299
 checkpoints-1.247
idated-1.185
ulnerable-1.160
TokenJ
Token ID41
Feature activation-3.43e+00

Pos logit contributions
wcs+0.616
Cra+0.600
yip+0.569
 ingred+0.539
kinson+0.538
Neg logit contributions
iless-0.727
igible-0.722
 checkpoints-0.700
idated-0.667
ulnerable-0.656
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
iless+1.106
igible+1.099
 checkpoints+1.060
idated+0.999
itimate+0.983
Neg logit contributions
wcs-1.210
Cra-1.166
yip-1.132
 ingred-1.081
hovah-1.079
Token For
Token ID1114
Feature activation+1.03e+00

Pos logit contributions
wcs+0.083
Cra+0.081
yip+0.078
atos+0.075
kinson+0.075
Neg logit contributions
iless-0.067
igible-0.067
 checkpoints-0.064
idated-0.061
itimate-0.060
Token 2007
Token ID4343
Feature activation-3.58e+00

Pos logit contributions
iless+0.640
igible+0.636
 checkpoints+0.610
idated+0.575
itimate+0.564
Neg logit contributions
wcs-0.813
Cra-0.787
yip-0.764
 ingred-0.733
hovah-0.730
Token,
Token ID11
Feature activation+1.13e-01

Pos logit contributions
wcs+2.512
Cra+2.418
yip+2.359
kinson+2.251
atos+2.250
Neg logit contributions
iless-2.476
igible-2.458
 checkpoints-2.347
idated-2.267
itimate-2.233
Token AT
Token ID5161
Feature activation+5.84e+00

Pos logit contributions
iless+0.065
igible+0.064
 checkpoints+0.061
idated+0.058
itimate+0.056
Neg logit contributions
wcs-0.094
Cra-0.092
yip-0.089
 ingred-0.086
kinson-0.085
Token&
Token ID5
Feature activation+1.03e+01

Pos logit contributions
igible+2.547
iless+2.539
 checkpoints+2.432
í+2.288
OAD+2.249
Neg logit contributions
wcs-5.683
yip-5.394
Cra-5.354
 ingred-5.335
hovah-5.325
TokenT
Token ID51
Feature activation+3.85e+00

Pos logit contributions
í+4.418
OAD+4.402
igible+4.377
 checkpoints+4.288
iless+4.227
Neg logit contributions
 ingred-9.674
wcs-9.586
hovah-9.497
yip-9.281
kinson-8.564
Token spent
Token ID3377
Feature activation-1.59e+00

Pos logit contributions
igible+2.312
iless+2.301
 checkpoints+2.233
idated+2.072
í+2.058
Neg logit contributions
wcs-3.107
Cra-2.978
yip-2.937
hovah-2.827
 ingred-2.796
Token over
Token ID625
Feature activation+1.53e+00

Pos logit contributions
wcs+1.121
Cra+1.084
yip+1.046
 ingred+0.997
kinson+0.991
Neg logit contributions
iless-1.118
igible-1.110
 checkpoints-1.066
idated-1.019
itimate-1.003
Token $
Token ID720
Feature activation+5.67e-01

Pos logit contributions
iless+1.015
igible+1.014
 checkpoints+0.979
idated+0.923
itimate+0.905
Neg logit contributions
wcs-1.150
Cra-1.105
yip-1.074
 ingred-1.032
hovah-1.030
Token16
Token ID1433
Feature activation+2.20e-01

Pos logit contributions
iless+0.368
igible+0.366
 checkpoints+0.351
idated+0.333
ulnerable+0.326
Neg logit contributions
wcs-0.434
Cra-0.419
yip-0.407
 ingred-0.391
hovah-0.389
Token.
Token ID13
Feature activation-3.63e-03

Pos logit contributions
iless+0.953
igible+0.942
 checkpoints+0.918
idated+0.861
ulnerable+0.855
Neg logit contributions
wcs-0.940
Cra-0.910
yip-0.881
 ingred-0.841
hovah-0.838
Token
Token ID198
Feature activation+3.46e-01

Pos logit contributions
wcs+0.003
Cra+0.003
yip+0.003
 ingred+0.003
hovah+0.003
Neg logit contributions
iless-0.002
igible-0.002
 checkpoints-0.002
idated-0.002
itimate-0.002
Token
Token ID198
Feature activation+4.89e-01

Pos logit contributions
iless+0.218
igible+0.216
 checkpoints+0.206
idated+0.195
itimate+0.192
Neg logit contributions
wcs-0.271
Cra-0.266
yip-0.253
kinson-0.244
atos-0.244
TokenA
Token ID32
Feature activation-9.21e-01

Pos logit contributions
iless+0.369
igible+0.367
 checkpoints+0.354
idated+0.338
itimate+0.333
Neg logit contributions
wcs-0.323
Cra-0.310
yip-0.300
 ingred-0.285
hovah-0.284
Token BBC
Token ID7823
Feature activation+8.39e+00

Pos logit contributions
wcs+0.707
Cra+0.684
yip+0.665
 ingred+0.635
kinson+0.634
Neg logit contributions
iless-0.589
igible-0.587
 checkpoints-0.563
idated-0.535
itimate-0.522
Token correspondent
Token ID21076
Feature activation+1.03e+01

Pos logit contributions
iless+4.550
 checkpoints+4.491
igible+4.488
ulnerable+4.194
í+4.187
Neg logit contributions
wcs-6.960
Cra-6.670
yip-6.646
 ingred-6.367
hovah-6.291
Token in
Token ID287
Feature activation-6.05e-01

Pos logit contributions
iless+6.077
 checkpoints+5.936
igible+5.782
í+5.481
ulnerable+5.406
Neg logit contributions
wcs-7.805
Cra-7.765
yip-7.597
 ingred-7.461
hovah-7.336
Token Somalia
Token ID23918
Feature activation+1.95e-01

Pos logit contributions
wcs+0.514
Cra+0.502
yip+0.489
 ingred+0.469
kinson+0.468
Neg logit contributions
iless-0.337
igible-0.333
 checkpoints-0.313
idated-0.298
ulnerable-0.291
Token says
Token ID1139
Feature activation+4.28e+00

Pos logit contributions
iless+0.142
igible+0.142
 checkpoints+0.136
idated+0.131
itimate+0.128
Neg logit contributions
wcs-0.133
Cra-0.128
yip-0.124
 ingred-0.118
kinson-0.117
Token the
Token ID262
Feature activation-1.31e+00

Pos logit contributions
iless+2.744
 checkpoints+2.711
igible+2.702
idated+2.450
itimate+2.450
Neg logit contributions
wcs-3.278
Cra-3.177
yip-3.074
hovah-2.986
kinson-2.934
Token Ethiop
Token ID23230
Feature activation-1.34e+00

Pos logit contributions
wcs+0.954
Cra+0.918
yip+0.892
 ingred+0.853
kinson+0.847
Neg logit contributions
igible-0.896
iless-0.893
 checkpoints-0.839
idated-0.817
ulnerable-0.796
Token cover
Token ID3002
Feature activation+5.78e+00

Pos logit contributions
iless+1.252
igible+1.248
 checkpoints+1.202
idated+1.125
ulnerable+1.108
Neg logit contributions
wcs-1.589
Cra-1.537
yip-1.491
hovah-1.435
 ingred-1.427
Token slightly
Token ID4622
Feature activation-1.28e+00

Pos logit contributions
iless+3.665
igible+3.639
 checkpoints+3.614
idated+3.270
itimate+3.256
Neg logit contributions
wcs-4.417
Cra-4.242
yip-4.186
hovah-4.065
 ingred-3.946
Token fewer
Token ID7380
Feature activation+3.66e+00

Pos logit contributions
wcs+0.937
Cra+0.903
yip+0.872
 ingred+0.835
kinson+0.831
Neg logit contributions
iless-0.867
igible-0.860
 checkpoints-0.825
idated-0.787
ulnerable-0.773
Token areas
Token ID3006
Feature activation+3.96e+00

Pos logit contributions
iless+2.531
igible+2.530
 checkpoints+2.468
idated+2.288
itimate+2.274
Neg logit contributions
wcs-2.635
Cra-2.538
yip-2.477
hovah-2.384
kinson-2.340
Token of
Token ID286
Feature activation+3.85e+00

Pos logit contributions
iless+2.613
igible+2.599
 checkpoints+2.508
idated+2.335
ulnerable+2.323
Neg logit contributions
wcs-2.975
Cra-2.895
yip-2.821
hovah-2.735
 ingred-2.722
Token health
Token ID1535
Feature activation+1.02e+01

Pos logit contributions
igible+2.139
iless+2.128
 checkpoints+2.047
idated+1.890
ulnerable+1.857
Neg logit contributions
wcs-3.302
Cra-3.204
yip-3.139
hovah-3.026
 ingred-2.993
Token and
Token ID290
Feature activation+5.32e-01

Pos logit contributions
igible+5.359
 checkpoints+5.280
iless+5.278
ulnerable+4.695
idated+4.667
Neg logit contributions
yip-8.546
wcs-8.453
Cra-8.428
hovah-8.212
 ingred-7.932
Token still
Token ID991
Feature activation-3.21e+00

Pos logit contributions
iless+0.345
igible+0.343
 checkpoints+0.329
idated+0.312
itimate+0.306
Neg logit contributions
wcs-0.407
Cra-0.394
yip-0.381
 ingred-0.365
hovah-0.364
Token be
Token ID307
Feature activation-1.89e+00

Pos logit contributions
wcs+2.368
Cra+2.289
yip+2.233
kinson+2.153
 ingred+2.136
Neg logit contributions
iless-2.112
igible-2.066
 checkpoints-1.976
idated-1.908
ulnerable-1.868
Token at
Token ID379
Feature activation+3.28e+00

Pos logit contributions
wcs+1.473
Cra+1.435
yip+1.363
 ingred+1.321
kinson+1.320
Neg logit contributions
iless-1.190
igible-1.170
 checkpoints-1.111
idated-1.063
itimate-1.048
Token a
Token ID257
Feature activation+5.00e-01

Pos logit contributions
igible+1.977
iless+1.975
 checkpoints+1.905
idated+1.780
itimate+1.743
Neg logit contributions
wcs-2.656
Cra-2.568
yip-2.501
 ingred-2.403
hovah-2.390
Token explaining
Token ID11170
Feature activation-3.59e+00

Pos logit contributions
wcs+2.000
Cra+1.945
yip+1.833
kinson+1.786
 ingred+1.765
Neg logit contributions
iless-2.270
igible-2.242
 checkpoints-2.101
idated-2.054
ulnerable-2.034
Token that
Token ID326
Feature activation-1.68e+00

Pos logit contributions
wcs+2.464
Cra+2.366
yip+2.252
kinson+2.200
 ingred+2.181
Neg logit contributions
igible-2.554
iless-2.552
 checkpoints-2.387
idated-2.334
ulnerable-2.311
Token
Token ID198
Feature activation-2.91e+00

Pos logit contributions
wcs+1.253
Cra+1.214
yip+1.167
kinson+1.128
 ingred+1.124
Neg logit contributions
iless-1.112
igible-1.110
 checkpoints-1.043
idated-1.008
ulnerable-0.991
Token
Token ID198
Feature activation-1.94e+00

Pos logit contributions
Cra+2.059
wcs+2.035
atos+1.853
waters+1.851
shock+1.837
Neg logit contributions
iless-2.028
igible-1.991
 checkpoints-1.898
idated-1.804
itimate-1.794
Token"
Token ID1
Feature activation-3.75e+00

Pos logit contributions
wcs+1.207
Cra+1.170
yip+1.109
kinson+1.055
 ingred+1.052
Neg logit contributions
iless-1.531
igible-1.528
 checkpoints-1.477
idated-1.410
ulnerable-1.387
TokenIf
Token ID1532
Feature activation-1.09e+01

Pos logit contributions
wcs+2.504
Cra+2.454
yip+2.307
kinson+2.228
atos+2.203
Neg logit contributions
igible-2.748
iless-2.735
 checkpoints-2.623
idated-2.509
ulnerable-2.469
Token you
Token ID345
Feature activation-1.87e+00

Pos logit contributions
wcs+6.859
Cra+6.583
yip+6.297
 ante+6.273
kinson+6.269
Neg logit contributions
igible-7.506
iless-7.466
abeth-6.765
idated-6.748
ulnerable-6.689
Token
Token ID447
Feature activation-2.36e+00

Pos logit contributions
wcs+1.381
Cra+1.328
yip+1.283
kinson+1.239
atos+1.234
Neg logit contributions
iless-1.253
igible-1.239
 checkpoints-1.176
idated-1.128
ulnerable-1.107
Token
Token ID247
Feature activation+1.91e+00

Pos logit contributions
wcs+1.592
Cra+1.537
yip+1.477
 ingred+1.417
kinson+1.404
Neg logit contributions
iless-1.738
igible-1.730
 checkpoints-1.667
idated-1.588
ulnerable-1.564
Tokenve
Token ID303
Feature activation+1.65e+00

Pos logit contributions
iless+1.323
igible+1.318
 checkpoints+1.265
idated+1.207
itimate+1.190
Neg logit contributions
wcs-1.380
Cra-1.329
yip-1.293
 ingred-1.239
hovah-1.235
Token got
Token ID1392
Feature activation+8.10e-01

Pos logit contributions
iless+1.103
igible+1.097
 checkpoints+1.059
idated+1.002
itimate+0.983
Neg logit contributions
wcs-1.235
Cra-1.193
yip-1.158
 ingred-1.106
hovah-1.102
Token.
Token ID13
Feature activation-1.76e+00

Pos logit contributions
wcs+1.748
Cra+1.676
yip+1.619
 ingred+1.544
kinson+1.529
Neg logit contributions
igible-1.782
iless-1.779
 checkpoints-1.706
idated-1.645
itimate-1.602
Token It
Token ID632
Feature activation+1.66e+00

Pos logit contributions
wcs+1.283
Cra+1.262
yip+1.202
atos+1.155
hovah+1.146
Neg logit contributions
iless-1.186
igible-1.167
 checkpoints-1.123
idated-1.069
itimate-1.046
Token
Token ID447
Feature activation-1.76e+00

Pos logit contributions
iless+1.090
igible+1.086
 checkpoints+1.042
idated+0.986
ulnerable+0.972
Neg logit contributions
wcs-1.258
Cra-1.220
yip-1.184
 ingred-1.132
hovah-1.126
Token
Token ID247
Feature activation+1.38e+00

Pos logit contributions
wcs+1.210
Cra+1.167
yip+1.126
 ingred+1.076
kinson+1.070
Neg logit contributions
iless-1.273
igible-1.266
 checkpoints-1.221
idated-1.161
ulnerable-1.143
Tokens
Token ID82
Feature activation-2.50e+00

Pos logit contributions
igible+0.999
iless+0.998
 checkpoints+0.959
idated+0.915
itimate+0.904
Neg logit contributions
wcs-0.945
Cra-0.913
yip-0.885
 ingred-0.842
hovah-0.836
Token either
Token ID2035
Feature activation-1.08e+01

Pos logit contributions
wcs+1.620
Cra+1.562
yip+1.493
 ingred+1.433
kinson+1.421
Neg logit contributions
iless-1.889
igible-1.866
 checkpoints-1.793
idated-1.732
itimate-1.691
Token going
Token ID1016
Feature activation-2.21e+00

Pos logit contributions
wcs+7.177
Cra+6.708
yip+6.499
 ingred+6.454
 ante+6.342
Neg logit contributions
iless-7.233
igible-7.049
 checkpoints-6.649
OAD-6.589
idated-6.525
Token to
Token ID284
Feature activation+4.16e-01

Pos logit contributions
wcs+1.597
Cra+1.524
yip+1.477
 ingred+1.414
hovah+1.412
Neg logit contributions
iless-1.526
igible-1.520
 checkpoints-1.463
idated-1.394
itimate-1.368
Token cost
Token ID1575
Feature activation-6.48e-01

Pos logit contributions
iless+0.274
igible+0.273
 checkpoints+0.261
idated+0.248
itimate+0.244
Neg logit contributions
wcs-0.314
Cra-0.303
yip-0.294
 ingred-0.282
hovah-0.280
Token us
Token ID514
Feature activation+1.39e+00

Pos logit contributions
wcs+0.454
Cra+0.438
yip+0.424
 ingred+0.404
kinson+0.401
Neg logit contributions
iless-0.461
igible-0.459
 checkpoints-0.441
idated-0.421
ulnerable-0.413
Token now
Token ID783
Feature activation+4.69e-01

Pos logit contributions
iless+0.897
igible+0.892
 checkpoints+0.859
idated+0.811
ulnerable+0.796
Neg logit contributions
wcs-1.061
Cra-1.027
yip-0.995
 ingred-0.953
hovah-0.951
Token This
Token ID770
Feature activation+1.29e+00

Pos logit contributions
iless+0.021
igible+0.021
 checkpoints+0.020
idated+0.019
ulnerable+0.019
Neg logit contributions
wcs-0.025
Cra-0.025
yip-0.024
hovah-0.023
kinson-0.023
Token is
Token ID318
Feature activation-3.69e-01

Pos logit contributions
iless+0.879
igible+0.874
 checkpoints+0.843
idated+0.797
itimate+0.784
Neg logit contributions
wcs-0.943
Cra-0.911
yip-0.883
 ingred-0.842
hovah-0.841
Token also
Token ID635
Feature activation+3.93e-02

Pos logit contributions
wcs+0.274
Cra+0.266
yip+0.257
 ingred+0.247
hovah+0.245
Neg logit contributions
iless-0.247
igible-0.244
 checkpoints-0.234
idated-0.223
ulnerable-0.219
Token mentioned
Token ID4750
Feature activation-9.60e-01

Pos logit contributions
iless+0.025
igible+0.025
 checkpoints+0.024
idated+0.023
ulnerable+0.022
Neg logit contributions
wcs-0.030
Cra-0.029
yip-0.028
 ingred-0.027
hovah-0.027
Token in
Token ID287
Feature activation-3.94e+00

Pos logit contributions
wcs+0.661
Cra+0.637
yip+0.614
 ingred+0.587
hovah+0.584
Neg logit contributions
iless-0.695
igible-0.692
 checkpoints-0.666
idated-0.635
itimate-0.625
Token Sunni
Token ID18592
Feature activation-1.07e+01

Pos logit contributions
wcs+2.834
Cra+2.807
yip+2.690
 ingred+2.605
hovah+2.602
Neg logit contributions
iless-2.601
igible-2.590
 checkpoints-2.424
idated-2.332
ulnerable-2.330
Token Had
Token ID11161
Feature activation-1.54e+00

Pos logit contributions
Cra+6.086
wcs+5.934
 ante+5.695
 ingred+5.687
hovah+5.432
Neg logit contributions
igible-8.051
iless-7.988
OAD-7.357
idated-7.325
itimate-7.324
Tokenith
Token ID342
Feature activation-3.52e+00

Pos logit contributions
wcs+0.877
Cra+0.842
yip+0.803
hovah+0.762
atos+0.761
Neg logit contributions
igible-1.284
iless-1.283
 checkpoints-1.242
idated-1.187
ulnerable-1.176
Token collections
Token ID17268
Feature activation-1.92e+00

Pos logit contributions
wcs+2.545
Cra+2.497
yip+2.369
hovah+2.295
 ingred+2.289
Neg logit contributions
iless-2.382
igible-2.359
 checkpoints-2.224
idated-2.147
ulnerable-2.125
Token:
Token ID25
Feature activation-2.13e-01

Pos logit contributions
wcs+1.351
Cra+1.307
yip+1.254
hovah+1.205
 ingred+1.202
Neg logit contributions
iless-1.358
igible-1.352
 checkpoints-1.290
idated-1.236
itimate-1.220
Token
Token ID198
Feature activation-2.72e-01

Pos logit contributions
wcs+0.169
Cra+0.164
yip+0.159
 ingred+0.153
hovah+0.152
Neg logit contributions
iless-0.132
igible-0.131
 checkpoints-0.125
idated-0.119
ulnerable-0.116
Token points
Token ID2173
Feature activation-2.89e+00

Pos logit contributions
wcs+1.705
Cra+1.630
yip+1.559
 ingred+1.512
kinson+1.511
Neg logit contributions
iless-1.425
igible-1.414
 checkpoints-1.348
idated-1.295
itimate-1.274
Token,
Token ID11
Feature activation-1.98e+00

Pos logit contributions
wcs+2.003
Cra+1.929
yip+1.844
kinson+1.762
 ingred+1.761
Neg logit contributions
iless-2.066
igible-2.042
 checkpoints-1.962
idated-1.896
ulnerable-1.870
Token modern
Token ID3660
Feature activation-2.64e+00

Pos logit contributions
wcs+1.424
Cra+1.363
yip+1.316
kinson+1.255
 ingred+1.248
Neg logit contributions
iless-1.372
igible-1.350
 checkpoints-1.290
idated-1.247
ulnerable-1.224
Token,
Token ID11
Feature activation-3.15e+00

Pos logit contributions
wcs+1.990
Cra+1.906
yip+1.808
kinson+1.766
 ingred+1.753
Neg logit contributions
iless-1.750
igible-1.732
 checkpoints-1.648
idated-1.578
ulnerable-1.559
Token and
Token ID290
Feature activation-3.13e-01

Pos logit contributions
wcs+2.297
Cra+2.210
yip+2.109
 ingred+2.037
kinson+2.036
Neg logit contributions
iless-2.145
igible-2.127
 checkpoints-2.029
idated-1.969
ulnerable-1.920
Token anything
Token ID1997
Feature activation-1.07e+01

Pos logit contributions
wcs+0.233
Cra+0.225
yip+0.217
 ingred+0.208
kinson+0.207
Neg logit contributions
iless-0.210
igible-0.209
 checkpoints-0.200
idated-0.191
ulnerable-0.188
Token that
Token ID326
Feature activation-3.35e+00

Pos logit contributions
wcs+7.001
Cra+6.415
kinson+5.962
 ante+5.958
atos+5.919
Neg logit contributions
iless-7.607
igible-7.506
 checkpoints-7.218
idated-7.131
itimate-6.821
Token
Token ID447
Feature activation-1.70e+00

Pos logit contributions
wcs+2.431
Cra+2.331
yip+2.237
kinson+2.164
 ingred+2.162
Neg logit contributions
iless-2.297
igible-2.259
 checkpoints-2.155
idated-2.092
itimate-2.031
Token
Token ID247
Feature activation+6.93e-01

Pos logit contributions
wcs+1.150
Cra+1.109
yip+1.067
 ingred+1.021
hovah+1.014
Neg logit contributions
iless-1.254
igible-1.249
 checkpoints-1.204
idated-1.146
ulnerable-1.129
Tokens
Token ID82
Feature activation-7.85e-01

Pos logit contributions
iless+0.493
igible+0.492
 checkpoints+0.473
idated+0.450
itimate+0.444
Neg logit contributions
wcs-0.486
Cra-0.469
yip-0.454
 ingred-0.433
hovah-0.431
Token legal
Token ID2742
Feature activation+3.17e+00

Pos logit contributions
wcs+0.584
Cra+0.562
yip+0.540
 ingred+0.519
kinson+0.519
Neg logit contributions
iless-0.529
igible-0.523
 checkpoints-0.503
idated-0.479
itimate-0.470
Token.
Token ID13
Feature activation-5.37e-01

Pos logit contributions
wcs+0.698
Cra+0.671
yip+0.648
 ingred+0.619
kinson+0.617
Neg logit contributions
iless-0.673
igible-0.669
 checkpoints-0.643
idated-0.614
itimate-0.602
Token It
Token ID632
Feature activation+1.60e+00

Pos logit contributions
wcs+0.403
Cra+0.395
yip+0.376
kinson+0.362
atos+0.362
Neg logit contributions
iless-0.355
igible-0.350
 checkpoints-0.336
idated-0.319
itimate-0.314
Token
Token ID447
Feature activation-2.49e+00

Pos logit contributions
iless+1.077
igible+1.072
 checkpoints+1.030
idated+0.976
í+0.963
Neg logit contributions
wcs-1.172
Cra-1.146
yip-1.111
 ingred-1.064
hovah-1.055
Token
Token ID247
Feature activation-7.57e-03

Pos logit contributions
wcs+1.665
Cra+1.608
yip+1.541
 ingred+1.477
kinson+1.473
Neg logit contributions
iless-1.831
igible-1.825
 checkpoints-1.760
idated-1.675
ulnerable-1.651
Tokens
Token ID82
Feature activation-2.14e+00

Pos logit contributions
wcs+0.005
Cra+0.005
yip+0.005
 ingred+0.004
hovah+0.004
Neg logit contributions
iless-0.006
igible-0.006
 checkpoints-0.005
idated-0.005
itimate-0.005
Token either
Token ID2035
Feature activation-1.04e+01

Pos logit contributions
wcs+1.622
Cra+1.555
yip+1.496
 ingred+1.445
kinson+1.442
Neg logit contributions
iless-1.413
igible-1.391
 checkpoints-1.326
idated-1.272
ulnerable-1.243
Token like
Token ID588
Feature activation-1.42e+00

Pos logit contributions
wcs+7.167
Cra+6.466
yip+6.224
 ingred+6.130
 ante+6.057
Neg logit contributions
iless-7.250
igible-7.077
 checkpoints-6.616
idated-6.518
itimate-6.378
Token you
Token ID345
Feature activation+4.92e-01

Pos logit contributions
wcs+1.031
Cra+0.991
yip+0.959
 ingred+0.916
kinson+0.911
Neg logit contributions
iless-0.980
igible-0.975
 checkpoints-0.929
idated-0.890
itimate-0.875
Token overlook
Token ID15677
Feature activation+6.85e-01

Pos logit contributions
iless+0.316
igible+0.314
 checkpoints+0.302
idated+0.285
ulnerable+0.280
Neg logit contributions
wcs-0.378
Cra-0.367
yip-0.355
 ingred-0.340
hovah-0.339
Token everything
Token ID2279
Feature activation-1.20e+00

Pos logit contributions
iless+0.445
igible+0.442
 checkpoints+0.424
idated+0.402
ulnerable+0.394
Neg logit contributions
wcs-0.524
Cra-0.507
yip-0.491
 ingred-0.471
kinson-0.469
Token and
Token ID290
Feature activation+1.04e+00

Pos logit contributions
wcs+0.982
Cra+0.946
yip+0.918
 ingred+0.883
kinson+0.880
Neg logit contributions
iless-0.722
igible-0.716
 checkpoints-0.677
idated-0.648
ulnerable-0.629
Token just
Token ID655
Feature activation-1.98e+00

Pos logit contributions
iless+0.123
igible+0.122
 checkpoints+0.118
idated+0.112
ulnerable+0.110
Neg logit contributions
wcs-0.117
Cra-0.113
yip-0.109
 ingred-0.104
hovah-0.104
Token as
Token ID355
Feature activation+1.79e+00

Pos logit contributions
wcs+1.372
Cra+1.318
yip+1.271
kinson+1.213
 ingred+1.213
Neg logit contributions
iless-1.418
igible-1.417
 checkpoints-1.356
idated-1.308
itimate-1.282
Token cap
Token ID1451
Feature activation+5.75e-01

Pos logit contributions
iless+1.098
igible+1.088
 checkpoints+1.048
idated+0.983
itimate+0.964
Neg logit contributions
wcs-1.429
Cra-1.383
yip-1.345
 ingred-1.287
hovah-1.287
Tokenably
Token ID1346
Feature activation+1.26e+00

Pos logit contributions
iless+0.184
igible+0.182
 checkpoints+0.168
idated+0.148
ulnerable+0.142
Neg logit contributions
wcs-0.628
Cra-0.614
yip-0.600
 ingred-0.583
hovah-0.582
Token as
Token ID355
Feature activation-1.90e+00

Pos logit contributions
iless+0.937
igible+0.931
 checkpoints+0.900
idated+0.855
ulnerable+0.842
Neg logit contributions
wcs-0.850
Cra-0.821
yip-0.791
 ingred-0.753
hovah-0.750
Token anything
Token ID1997
Feature activation-1.04e+01

Pos logit contributions
wcs+1.377
Cra+1.343
yip+1.292
 ingred+1.239
kinson+1.236
Neg logit contributions
iless-1.287
igible-1.279
 checkpoints-1.213
idated-1.170
ulnerable-1.151
Token you
Token ID345
Feature activation-1.84e+00

Pos logit contributions
wcs+5.961
Cra+5.774
atos+5.433
yip+5.423
 ante+5.412
Neg logit contributions
iless-7.840
igible-7.802
 checkpoints-7.277
idated-7.177
abeth-7.086
Token
Token ID447
Feature activation+2.78e-01

Pos logit contributions
wcs+1.287
Cra+1.237
yip+1.198
atos+1.141
kinson+1.141
Neg logit contributions
iless-1.297
igible-1.290
 checkpoints-1.253
idated-1.186
itimate-1.167
Token
Token ID247
Feature activation+9.07e-01

Pos logit contributions
iless+0.195
igible+0.194
 checkpoints+0.187
idated+0.178
itimate+0.175
Neg logit contributions
wcs-0.198
Cra-0.192
yip-0.186
 ingred-0.177
hovah-0.176
Tokend
Token ID67
Feature activation-1.12e+00

Pos logit contributions
iless+0.576
igible+0.572
 checkpoints+0.548
idated+0.519
itimate+0.509
Neg logit contributions
wcs-0.707
Cra-0.684
yip-0.663
 ingred-0.637
hovah-0.634
Token see
Token ID766
Feature activation-1.57e+00

Pos logit contributions
wcs+0.813
Cra+0.788
yip+0.766
kinson+0.730
 ingred+0.727
Neg logit contributions
iless-0.759
igible-0.752
 checkpoints-0.731
idated-0.689
ulnerable-0.679
Token term
Token ID3381
Feature activation-3.23e+00

Pos logit contributions
wcs+0.167
Cra+0.161
yip+0.155
 ingred+0.148
kinson+0.147
Neg logit contributions
iless-0.178
igible-0.177
 checkpoints-0.171
idated-0.163
ulnerable-0.160
Token.
Token ID13
Feature activation-1.44e+00

Pos logit contributions
wcs+2.032
Cra+1.923
yip+1.856
kinson+1.751
atos+1.751
Neg logit contributions
iless-2.497
igible-2.492
 checkpoints-2.414
idated-2.320
itimate-2.271
Token
Token ID198
Feature activation-2.03e+00

Pos logit contributions
wcs+1.069
Cra+1.061
yip+0.999
atos+0.969
kinson+0.966
Neg logit contributions
iless-0.951
igible-0.937
 checkpoints-0.895
idated-0.852
itimate-0.839
Token
Token ID198
Feature activation-9.75e-01

Pos logit contributions
Cra+1.472
wcs+1.463
yip+1.332
atos+1.332
waters+1.322
Neg logit contributions
iless-1.382
igible-1.363
 checkpoints-1.303
idated-1.233
itimate-1.226
Token"
Token ID1
Feature activation-1.80e+00

Pos logit contributions
wcs+0.597
Cra+0.582
yip+0.547
atos+0.519
kinson+0.519
Neg logit contributions
iless-0.779
igible-0.772
 checkpoints-0.751
idated-0.716
ulnerable-0.706
TokenIf
Token ID1532
Feature activation-1.03e+01

Pos logit contributions
wcs+1.135
Cra+1.129
yip+1.041
atos+1.001
kinson+0.995
Neg logit contributions
iless-1.405
igible-1.389
 checkpoints-1.345
idated-1.282
ulnerable-1.266
Token Barack
Token ID8732
Feature activation+3.12e+00

Pos logit contributions
wcs+6.069
Cra+5.893
kinson+5.535
yip+5.530
shock+5.449
Neg logit contributions
iless-7.614
igible-7.569
idated-6.915
 checkpoints-6.902
ulnerable-6.856
Token Obama
Token ID2486
Feature activation+1.52e+00

Pos logit contributions
iless+2.083
igible+2.075
 checkpoints+2.000
idated+1.880
itimate+1.867
Neg logit contributions
wcs-2.305
Cra-2.239
yip-2.190
hovah-2.086
 ingred-2.079
Token wins
Token ID7864
Feature activation-2.02e-01

Pos logit contributions
iless+1.011
igible+1.005
 checkpoints+0.972
idated+0.915
itimate+0.899
Neg logit contributions
wcs-1.131
Cra-1.100
yip-1.070
 ingred-1.017
hovah-1.015
Token a
Token ID257
Feature activation-5.40e-01

Pos logit contributions
wcs+0.151
Cra+0.146
yip+0.141
 ingred+0.135
kinson+0.135
Neg logit contributions
iless-0.135
igible-0.134
 checkpoints-0.129
idated-0.122
ulnerable-0.120
Token The
Token ID383
Feature activation-4.12e-01

Pos logit contributions
wcs+0.435
Cra+0.422
yip+0.412
kinson+0.393
 ingred+0.392
Neg logit contributions
iless-0.327
igible-0.324
 checkpoints-0.310
idated-0.291
ulnerable-0.287
Tokenas
Token ID292
Feature activation+1.20e+00

Pos logit contributions
wcs+0.755
Cra+0.732
yip+0.706
 ingred+0.678
kinson+0.673
Neg logit contributions
iless-0.691
igible-0.688
 checkpoints-0.660
idated-0.630
itimate-0.618
Token Le
Token ID1004
Feature activation+1.76e+00

Pos logit contributions
iless+0.801
igible+0.796
 checkpoints+0.767
idated+0.723
ulnerable+0.713
Neg logit contributions
wcs-0.895
Cra-0.864
yip-0.839
hovah-0.802
 ingred-0.799
Token Fort
Token ID6401
Feature activation+1.54e+00

Pos logit contributions
iless+1.181
igible+1.176
 checkpoints+1.137
idated+1.057
itimate+1.055
Neg logit contributions
wcs-1.312
Cra-1.253
yip-1.232
kinson-1.168
 ingred-1.162
Token de
Token ID390
Feature activation-3.21e+00

Pos logit contributions
iless+0.590
igible+0.582
 checkpoints+0.544
idated+0.490
itimate+0.476
Neg logit contributions
wcs-1.582
Cra-1.543
yip-1.512
hovah-1.462
 ingred-1.460
Token Br
Token ID1709
Feature activation+5.29e+00

Pos logit contributions
wcs+2.082
Cra+2.028
yip+1.920
 ingred+1.846
hovah+1.836
Neg logit contributions
iless-2.443
igible-2.407
 checkpoints-2.326
idated-2.238
ulnerable-2.193
Tokené
Token ID2634
Feature activation-1.03e+01

Pos logit contributions
iless+3.432
igible+3.380
 checkpoints+3.159
í+3.062
idated+3.059
Neg logit contributions
wcs-4.084
Cra-3.921
yip-3.775
 ingred-3.716
hovah-3.616
Tokengan
Token ID1030
Feature activation-1.17e+00

Pos logit contributions
wcs+7.436
yip+7.297
Cra+7.183
atos+7.048
shock+6.876
Neg logit contributions
igible-6.038
 checkpoints-5.827
iless-5.794
OAD-5.576
idated-5.399
Tokenç
Token ID16175
Feature activation-4.30e+00

Pos logit contributions
wcs+0.907
Cra+0.881
yip+0.849
 ingred+0.814
atos+0.812
Neg logit contributions
iless-0.744
igible-0.741
 checkpoints-0.710
idated-0.671
itimate-0.657
Tokenon
Token ID261
Feature activation-1.46e+00

Pos logit contributions
wcs+2.694
Cra+2.616
yip+2.525
atos+2.426
 ingred+2.373
Neg logit contributions
igible-3.294
iless-3.279
 checkpoints-3.192
idated-3.045
ulnerable-2.976
Token ser
Token ID1055
Feature activation-4.22e+00

Pos logit contributions
wcs+1.116
Cra+1.082
yip+1.043
 ingred+1.007
atos+0.999
Neg logit contributions
iless-0.945
igible-0.939
 checkpoints-0.899
idated-0.859
itimate-0.839
Tokena
Token ID64
Feature activation-1.50e+00

Pos logit contributions
wcs+2.967
Cra+2.878
yip+2.749
atos+2.721
 ingred+2.685
Neg logit contributions
iless-2.902
igible-2.884
 checkpoints-2.767
idated-2.686
itimate-2.608
Token person
Token ID1048
Feature activation-2.74e+00

Pos logit contributions
wcs+1.599
Cra+1.547
yip+1.484
 ingred+1.422
hovah+1.415
Neg logit contributions
iless-1.778
igible-1.759
 checkpoints-1.709
idated-1.622
itimate-1.610
Token.
Token ID13
Feature activation-1.86e+00

Pos logit contributions
wcs+1.849
Cra+1.780
yip+1.713
kinson+1.632
 ingred+1.631
Neg logit contributions
iless-2.007
igible-1.997
 checkpoints-1.936
idated-1.843
itimate-1.813
Token He
Token ID679
Feature activation-1.98e+00

Pos logit contributions
wcs+1.369
Cra+1.334
yip+1.280
 ingred+1.223
hovah+1.222
Neg logit contributions
iless-1.250
igible-1.237
 checkpoints-1.193
idated-1.130
itimate-1.114
Token would
Token ID561
Feature activation-1.16e+00

Pos logit contributions
wcs+1.358
Cra+1.305
yip+1.248
atos+1.196
kinson+1.196
Neg logit contributions
iless-1.433
igible-1.427
 checkpoints-1.379
idated-1.312
itimate-1.295
Token do
Token ID466
Feature activation-1.38e+00

Pos logit contributions
wcs+0.874
Cra+0.843
yip+0.813
 ingred+0.783
atos+0.781
Neg logit contributions
iless-0.761
igible-0.756
 checkpoints-0.723
idated-0.692
itimate-0.679
Token anything
Token ID1997
Feature activation-1.03e+01

Pos logit contributions
wcs+0.933
Cra+0.905
yip+0.863
 ingred+0.830
kinson+0.826
Neg logit contributions
iless-1.016
igible-1.012
 checkpoints-0.964
idated-0.934
itimate-0.918
Token for
Token ID329
Feature activation-1.44e+00

Pos logit contributions
wcs+5.841
Cra+5.592
yip+5.339
 ingred+5.142
kinson+5.126
Neg logit contributions
igible-7.876
iless-7.737
 checkpoints-7.551
idated-7.508
icist-7.219
Token anybody
Token ID9599
Feature activation-7.28e+00

Pos logit contributions
wcs+1.050
Cra+1.017
yip+0.982
 ingred+0.942
kinson+0.935
Neg logit contributions
iless-0.981
igible-0.975
 checkpoints-0.934
idated-0.892
itimate-0.873
Token.
Token ID13
Feature activation-2.37e+00

Pos logit contributions
wcs+4.566
Cra+4.370
yip+4.237
 ingred+4.025
atos+4.010
Neg logit contributions
iless-5.407
igible-5.370
 checkpoints-5.200
idated-5.021
itimate-4.905
Token
Token ID447
Feature activation+8.39e-01

Pos logit contributions
wcs+1.711
Cra+1.675
yip+1.598
atos+1.527
kinson+1.525
Neg logit contributions
iless-1.622
igible-1.604
 checkpoints-1.550
idated-1.468
itimate-1.450
Token
Token ID251
Feature activation-1.59e+00

Pos logit contributions
iless+0.668
igible+0.664
 checkpoints+0.645
idated+0.614
ulnerable+0.606
Neg logit contributions
wcs-0.520
Cra-0.499
yip-0.483
kinson-0.451
 ingred-0.450
Token can
Token ID460
Feature activation-3.45e+00

Pos logit contributions
iless+0.006
igible+0.006
 checkpoints+0.005
idated+0.005
itimate+0.005
Neg logit contributions
wcs-0.006
Cra-0.006
yip-0.006
 ingred-0.006
hovah-0.005
Token swing
Token ID9628
Feature activation-3.17e+00

Pos logit contributions
wcs+2.513
Cra+2.386
yip+2.357
kinson+2.238
atos+2.232
Neg logit contributions
iless-2.320
igible-2.287
 checkpoints-2.220
idated-2.103
itimate-2.065
Token five
Token ID1936
Feature activation+2.73e+00

Pos logit contributions
wcs+2.095
Cra+2.008
yip+1.943
 ingred+1.846
atos+1.823
Neg logit contributions
iless-2.361
igible-2.360
 checkpoints-2.247
idated-2.186
itimate-2.139
Token days
Token ID1528
Feature activation-1.87e-01

Pos logit contributions
iless+1.692
igible+1.669
 checkpoints+1.625
idated+1.501
itimate+1.486
Neg logit contributions
wcs-2.150
Cra-2.099
yip-2.030
hovah-1.958
 ingred-1.950
Token in
Token ID287
Feature activation-6.79e-02

Pos logit contributions
wcs+0.130
Cra+0.126
yip+0.122
 ingred+0.116
hovah+0.115
Neg logit contributions
iless-0.134
igible-0.133
 checkpoints-0.128
idated-0.122
ulnerable-0.120
Token either
Token ID2035
Feature activation-1.03e+01

Pos logit contributions
wcs+0.053
Cra+0.052
yip+0.050
 ingred+0.048
hovah+0.048
Neg logit contributions
iless-0.043
igible-0.042
 checkpoints-0.041
idated-0.038
itimate-0.038
Token direction
Token ID4571
Feature activation-6.43e-01

Pos logit contributions
wcs+6.986
Cra+6.550
yip+6.084
 ante+6.066
waters+6.019
Neg logit contributions
iless-7.106
igible-6.980
 checkpoints-6.705
idated-6.529
ulnerable-6.449
Token.
Token ID13
Feature activation-1.59e-01

Pos logit contributions
wcs+0.430
Cra+0.412
yip+0.398
 ingred+0.377
hovah+0.375
Neg logit contributions
iless-0.478
igible-0.476
 checkpoints-0.460
idated-0.440
itimate-0.433
Token
Token ID564
Feature activation+3.92e-01

Pos logit contributions
wcs+0.123
Cra+0.120
yip+0.115
hovah+0.110
atos+0.110
Neg logit contributions
iless-0.101
igible-0.100
 checkpoints-0.096
idated-0.091
ulnerable-0.089
Token
Token ID250
Feature activation+8.78e-01

Pos logit contributions
iless+0.322
igible+0.320
 checkpoints+0.311
idated+0.298
itimate+0.293
Neg logit contributions
wcs-0.233
Cra-0.223
yip-0.214
 ingred-0.202
hovah-0.201
TokenIf
Token ID1532
Feature activation-7.06e+00

Pos logit contributions
iless+0.665
igible+0.661
 checkpoints+0.639
idated+0.609
itimate+0.600
Neg logit contributions
wcs-0.577
Cra-0.553
yip-0.536
 ingred-0.510
hovah-0.507
Token us
Token ID514
Feature activation-8.89e-01

Pos logit contributions
wcs+0.703
Cra+0.677
yip+0.653
 ingred+0.621
kinson+0.619
Neg logit contributions
iless-0.768
igible-0.766
 checkpoints-0.736
idated-0.706
ulnerable-0.694
Token.'
Token ID2637
Feature activation-1.17e-01

Pos logit contributions
wcs+0.608
Cra+0.584
yip+0.566
 ingred+0.538
kinson+0.538
Neg logit contributions
iless-0.647
igible-0.642
 checkpoints-0.618
idated-0.593
itimate-0.581
Token
Token ID198
Feature activation-2.86e-01

Pos logit contributions
wcs+0.093
Cra+0.090
yip+0.087
 ingred+0.084
hovah+0.083
Neg logit contributions
iless-0.073
igible-0.072
 checkpoints-0.069
idated-0.065
ulnerable-0.064
Token
Token ID198
Feature activation-9.51e-02

Pos logit contributions
wcs+0.220
Cra+0.217
yip+0.204
kinson+0.198
atos+0.198
Neg logit contributions
iless-0.183
igible-0.181
 checkpoints-0.174
idated-0.164
itimate-0.162
TokenScroll
Token ID29261
Feature activation-4.44e+00

Pos logit contributions
wcs+0.059
Cra+0.058
yip+0.054
kinson+0.051
 ingred+0.051
Neg logit contributions
iless-0.076
igible-0.075
 checkpoints-0.073
idated-0.069
ulnerable-0.068
Token down
Token ID866
Feature activation-1.02e+01

Pos logit contributions
wcs+2.875
Cra+2.822
yip+2.599
kinson+2.582
 ingred+2.577
Neg logit contributions
igible-3.297
iless-3.236
 checkpoints-3.131
idated-3.061
itimate-2.971
Token for
Token ID329
Feature activation-2.80e+00

Pos logit contributions
wcs+4.691
Cra+4.574
 ingred+4.253
 ante+4.237
yip+4.232
Neg logit contributions
igible-8.633
iless-8.385
idated-8.312
 checkpoints-8.281
abeth-8.017
Token video
Token ID2008
Feature activation-2.99e-02

Pos logit contributions
wcs+2.132
Cra+2.072
yip+1.972
 ingred+1.930
kinson+1.911
Neg logit contributions
iless-1.813
igible-1.788
 checkpoints-1.693
idated-1.641
ulnerable-1.595
Token
Token ID198
Feature activation-8.48e-01

Pos logit contributions
wcs+0.024
Cra+0.023
yip+0.022
 ingred+0.022
hovah+0.021
Neg logit contributions
iless-0.018
igible-0.018
 checkpoints-0.018
idated-0.017
itimate-0.016
Token
Token ID198
Feature activation-8.64e-01

Pos logit contributions
wcs+0.632
Cra+0.632
yip+0.583
atos+0.572
kinson+0.571
Neg logit contributions
iless-0.559
igible-0.550
 checkpoints-0.528
idated-0.499
itimate-0.496
TokenHillary
Token ID20397
Feature activation+1.23e+00

Pos logit contributions
wcs+0.496
Cra+0.487
yip+0.451
kinson+0.425
atos+0.423
Neg logit contributions
iless-0.724
igible-0.719
 checkpoints-0.701
idated-0.668
ulnerable-0.660
Token of
Token ID286
Feature activation+2.49e-01

Pos logit contributions
wcs+1.516
Cra+1.493
yip+1.382
kinson+1.326
atos+1.320
Neg logit contributions
iless-1.862
igible-1.852
 checkpoints-1.777
idated-1.717
ulnerable-1.693
Token 10
Token ID838
Feature activation+7.14e-01

Pos logit contributions
iless+0.200
igible+0.199
 checkpoints+0.192
idated+0.185
itimate+0.183
Neg logit contributions
wcs-0.151
Cra-0.146
yip-0.136
 ingred-0.132
kinson-0.130
Token,
Token ID11
Feature activation+1.52e-01

Pos logit contributions
iless+0.494
igible+0.491
 checkpoints+0.474
idated+0.449
ulnerable+0.441
Neg logit contributions
wcs-0.516
Cra-0.497
yip-0.484
 ingred-0.460
kinson-0.458
Token saying
Token ID2282
Feature activation+7.60e-01

Pos logit contributions
iless+0.112
igible+0.112
 checkpoints+0.108
idated+0.103
itimate+0.101
Neg logit contributions
wcs-0.103
Cra-0.099
yip-0.096
 ingred-0.091
hovah-0.091
Token "
Token ID366
Feature activation-3.79e+00

Pos logit contributions
iless+0.491
igible+0.488
 checkpoints+0.469
idated+0.443
ulnerable+0.435
Neg logit contributions
wcs-0.583
Cra-0.564
yip-0.547
 ingred-0.524
hovah-0.522
TokenIf
Token ID1532
Feature activation-1.02e+01

Pos logit contributions
wcs+2.555
Cra+2.504
yip+2.293
atos+2.218
shock+2.204
Neg logit contributions
iless-2.784
igible-2.772
 checkpoints-2.677
idated-2.555
ulnerable-2.507
Token you
Token ID345
Feature activation-1.25e+00

Pos logit contributions
wcs+6.498
Cra+6.224
yip+5.705
shock+5.696
 ingred+5.635
Neg logit contributions
iless-7.203
igible-7.102
 checkpoints-6.647
idated-6.479
OAD-6.388
Token're
Token ID821
Feature activation+2.93e-01

Pos logit contributions
wcs+0.886
Cra+0.855
yip+0.820
 ingred+0.786
atos+0.785
Neg logit contributions
iless-0.881
igible-0.875
 checkpoints-0.837
idated-0.799
ulnerable-0.787
Token harbor
Token ID25451
Feature activation-1.96e+00

Pos logit contributions
iless+0.205
igible+0.204
 checkpoints+0.196
idated+0.186
itimate+0.183
Neg logit contributions
wcs-0.210
Cra-0.203
yip-0.195
 ingred-0.187
hovah-0.186
Tokening
Token ID278
Feature activation-3.42e-01

Pos logit contributions
wcs+1.273
Cra+1.229
yip+1.179
 ingred+1.122
hovah+1.120
Neg logit contributions
iless-1.483
igible-1.475
 checkpoints-1.429
idated-1.364
itimate-1.343
Token even
Token ID772
Feature activation+4.15e-01

Pos logit contributions
wcs+0.269
Cra+0.261
yip+0.252
 ingred+0.243
kinson+0.241
Neg logit contributions
iless-0.215
igible-0.213
 checkpoints-0.204
idated-0.193
ulnerable-0.190
Token big
Token ID1263
Feature activation+1.78e+00

Pos logit contributions
iless+0.038
igible+0.038
 checkpoints+0.036
idated+0.035
ulnerable+0.034
Neg logit contributions
wcs-0.045
Cra-0.043
yip-0.042
 ingred-0.040
kinson-0.040
Token teeth
Token ID9941
Feature activation-5.89e+00

Pos logit contributions
iless+1.163
igible+1.153
 checkpoints+1.112
idated+1.048
itimate+1.031
Neg logit contributions
wcs-1.355
Cra-1.311
yip-1.270
 ingred-1.215
hovah-1.213
Token and
Token ID290
Feature activation+1.31e+00

Pos logit contributions
wcs+3.645
Cra+3.392
yip+3.340
atos+3.172
kinson+3.153
Neg logit contributions
igible-4.559
iless-4.499
idated-4.283
 checkpoints-4.267
OAD-4.116
Token immensely
Token ID29731
Feature activation-1.06e+00

Pos logit contributions
iless+0.836
igible+0.829
 checkpoints+0.800
idated+0.752
itimate+0.740
Neg logit contributions
wcs-1.017
Cra-0.985
yip-0.954
 ingred-0.915
hovah-0.914
Token powerful
Token ID3665
Feature activation-2.61e+00

Pos logit contributions
wcs+0.818
Cra+0.790
yip+0.764
 ingred+0.734
kinson+0.731
Neg logit contributions
iless-0.685
igible-0.683
 checkpoints-0.648
idated-0.624
itimate-0.606
Token jaws
Token ID39940
Feature activation-1.01e+01

Pos logit contributions
wcs+1.726
Cra+1.656
yip+1.583
 ingred+1.529
atos+1.514
Neg logit contributions
iless-1.951
igible-1.949
 checkpoints-1.843
idated-1.801
ulnerable-1.761
Token;
Token ID26
Feature activation+3.35e-01

Pos logit contributions
wcs+5.527
Cra+5.021
yip+4.933
atos+4.778
waters+4.749
Neg logit contributions
igible-8.182
iless-8.094
idated-7.881
 checkpoints-7.675
itimate-7.461
Token it
Token ID340
Feature activation+5.96e-01

Pos logit contributions
iless+0.217
igible+0.216
 checkpoints+0.207
idated+0.196
ulnerable+0.193
Neg logit contributions
wcs-0.257
Cra-0.249
yip-0.241
 ingred-0.231
hovah-0.230
Token can
Token ID460
Feature activation-4.47e+00

Pos logit contributions
iless+0.406
igible+0.402
 checkpoints+0.389
idated+0.367
itimate+0.362
Neg logit contributions
wcs-0.437
Cra-0.423
yip-0.409
 ingred-0.391
hovah-0.390
Token cut
Token ID2005
Feature activation-2.47e+00

Pos logit contributions
wcs+3.170
Cra+3.014
yip+2.982
atos+2.863
 ante+2.839
Neg logit contributions
igible-3.055
iless-3.020
 checkpoints-2.882
idated-2.806
abeth-2.701
Token down
Token ID866
Feature activation+5.87e-01

Pos logit contributions
wcs+1.616
Cra+1.548
yip+1.493
 ingred+1.428
atos+1.413
Neg logit contributions
iless-1.865
igible-1.865
 checkpoints-1.761
idated-1.730
itimate-1.676
Token to
Token ID284
Feature activation-2.87e-01

Pos logit contributions
wcs+0.807
Cra+0.778
yip+0.747
 ingred+0.718
atos+0.710
Neg logit contributions
iless-0.862
igible-0.858
 checkpoints-0.824
idated-0.789
ulnerable-0.776
Token neighborhood
Token ID6232
Feature activation+9.87e-02

Pos logit contributions
wcs+0.219
Cra+0.212
yip+0.204
 ingred+0.197
kinson+0.196
Neg logit contributions
iless-0.187
igible-0.186
 checkpoints-0.178
idated-0.169
ulnerable-0.166
Token kids
Token ID3988
Feature activation+5.99e-01

Pos logit contributions
iless+0.065
igible+0.065
 checkpoints+0.062
idated+0.059
ulnerable+0.058
Neg logit contributions
wcs-0.074
Cra-0.072
yip-0.070
 ingred-0.067
hovah-0.066
Token.
Token ID13
Feature activation+7.93e-01

Pos logit contributions
iless+0.433
igible+0.428
 checkpoints+0.416
idated+0.394
ulnerable+0.388
Neg logit contributions
wcs-0.414
Cra-0.400
yip-0.388
 ingred-0.369
hovah-0.369
Token "
Token ID366
Feature activation-3.12e+00

Pos logit contributions
iless+0.528
igible+0.524
 checkpoints+0.504
idated+0.478
itimate+0.469
Neg logit contributions
wcs-0.593
Cra-0.574
yip-0.555
 ingred-0.531
hovah-0.529
TokenIf
Token ID1532
Feature activation-1.01e+01

Pos logit contributions
Cra+1.954
wcs+1.884
yip+1.707
atos+1.692
waters+1.664
Neg logit contributions
iless-2.468
igible-2.451
 checkpoints-2.376
idated-2.246
ulnerable-2.229
Token the
Token ID262
Feature activation-5.22e-01

Pos logit contributions
wcs+5.815
Cra+5.633
yip+5.364
 ante+5.201
atos+5.147
Neg logit contributions
iless-7.659
igible-7.656
 checkpoints-7.013
idated-6.968
ulnerable-6.915
Token tad
Token ID36264
Feature activation-7.29e-01

Pos logit contributions
wcs+0.389
Cra+0.377
yip+0.363
 ingred+0.350
kinson+0.347
Neg logit contributions
iless-0.349
igible-0.346
 checkpoints-0.330
idated-0.315
ulnerable-0.310
Tokenpole
Token ID36869
Feature activation-1.37e+00

Pos logit contributions
wcs+0.594
Cra+0.576
yip+0.558
 ingred+0.537
hovah+0.535
Neg logit contributions
iless-0.437
igible-0.434
 checkpoints-0.415
idated-0.391
itimate-0.383
Token had
Token ID550
Feature activation+1.76e+00

Pos logit contributions
wcs+0.954
Cra+0.922
yip+0.889
 ingred+0.845
kinson+0.843
Neg logit contributions
iless-0.986
igible-0.976
 checkpoints-0.934
idated-0.896
ulnerable-0.885
Token just
Token ID655
Feature activation-4.27e-02

Pos logit contributions
iless+1.223
igible+1.213
 checkpoints+1.181
idated+1.113
itimate+1.096
Neg logit contributions
wcs-1.255
Cra-1.216
yip-1.178
hovah-1.122
 ingred-1.122
Token the
Token ID262
Feature activation+5.76e-01

Pos logit contributions
iless+0.021
igible+0.021
 checkpoints+0.020
idated+0.019
ulnerable+0.018
Neg logit contributions
wcs-0.025
Cra-0.024
yip-0.023
 ingred-0.022
kinson-0.022
Token prospect
Token ID6034
Feature activation+2.68e+00

Pos logit contributions
iless+0.363
igible+0.360
 checkpoints+0.346
idated+0.326
itimate+0.320
Neg logit contributions
wcs-0.452
Cra-0.438
yip-0.425
 ingred-0.407
hovah-0.406
Token of
Token ID286
Feature activation-1.17e+00

Pos logit contributions
iless+1.853
igible+1.841
 checkpoints+1.763
idated+1.677
itimate+1.657
Neg logit contributions
wcs-1.931
Cra-1.872
yip-1.809
 ingred-1.733
hovah-1.730
Token voting
Token ID6709
Feature activation-2.36e+00

Pos logit contributions
wcs+0.846
Cra+0.815
yip+0.790
 ingred+0.754
kinson+0.750
Neg logit contributions
iless-0.797
igible-0.795
 checkpoints-0.760
idated-0.730
ulnerable-0.716
Token for
Token ID329
Feature activation+4.16e-02

Pos logit contributions
wcs+1.512
Cra+1.458
yip+1.399
 ingred+1.337
kinson+1.335
Neg logit contributions
iless-1.795
igible-1.795
 checkpoints-1.730
idated-1.661
ulnerable-1.631
Token either
Token ID2035
Feature activation-1.01e+01

Pos logit contributions
iless+0.028
igible+0.028
 checkpoints+0.027
idated+0.025
itimate+0.025
Neg logit contributions
wcs-0.031
Cra-0.030
yip-0.029
 ingred-0.028
hovah-0.028
Token Donald
Token ID3759
Feature activation+4.37e-01

Pos logit contributions
wcs+6.165
Cra+5.903
 ante+5.539
 ingred+5.513
yip+5.448
Neg logit contributions
igible-7.328
iless-7.310
 checkpoints-7.092
idated-6.873
ulnerable-6.751
Token Trump
Token ID1301
Feature activation-2.55e-01

Pos logit contributions
iless+0.305
igible+0.304
 checkpoints+0.292
idated+0.278
itimate+0.273
Neg logit contributions
wcs-0.313
Cra-0.302
yip-0.292
 ingred-0.279
hovah-0.277
Token or
Token ID393
Feature activation-2.21e+00

Pos logit contributions
wcs+0.234
Cra+0.228
yip+0.222
 ingred+0.214
hovah+0.213
Neg logit contributions
iless-0.127
igible-0.126
 checkpoints-0.119
idated-0.111
itimate-0.108
Token Hillary
Token ID5073
Feature activation+3.43e+00

Pos logit contributions
wcs+1.326
Cra+1.274
yip+1.215
kinson+1.153
 ingred+1.151
Neg logit contributions
iless-1.784
igible-1.775
 checkpoints-1.724
idated-1.654
ulnerable-1.624
Token Clinton
Token ID2605
Feature activation+7.10e-01

Pos logit contributions
iless+2.636
igible+2.619
 checkpoints+2.558
idated+2.424
itimate+2.409
Neg logit contributions
wcs-2.193
Cra-2.089
yip-2.052
hovah-1.980
 ingred-1.967
Tokenkel
Token ID7750
Feature activation+1.71e-01

Pos logit contributions
iless+0.793
igible+0.788
 checkpoints+0.761
idated+0.725
ulnerable+0.714
Neg logit contributions
wcs-0.721
Cra-0.695
yip-0.671
 ingred-0.639
hovah-0.636
Token said
Token ID531
Feature activation+2.79e+00

Pos logit contributions
iless+0.122
igible+0.122
 checkpoints+0.117
idated+0.112
itimate+0.110
Neg logit contributions
wcs-0.119
Cra-0.115
yip-0.111
 ingred-0.106
kinson-0.105
Token she
Token ID673
Feature activation-1.10e+00

Pos logit contributions
iless+1.878
igible+1.863
 checkpoints+1.819
idated+1.703
itimate+1.675
Neg logit contributions
wcs-2.052
Cra-1.981
yip-1.927
hovah-1.854
kinson-1.823
Token was
Token ID373
Feature activation+1.30e+00

Pos logit contributions
wcs+0.688
Cra+0.655
yip+0.631
 ingred+0.598
kinson+0.598
Neg logit contributions
iless-0.858
igible-0.851
 checkpoints-0.822
idated-0.791
ulnerable-0.778
Token "
Token ID366
Feature activation-2.34e+00

Pos logit contributions
iless+0.824
igible+0.818
 checkpoints+0.787
idated+0.742
ulnerable+0.729
Neg logit contributions
wcs-1.008
Cra-0.977
yip-0.948
 ingred-0.908
hovah-0.905
Tokenanything
Token ID49459
Feature activation-1.01e+01

Pos logit contributions
wcs+1.680
Cra+1.623
yip+1.557
kinson+1.481
atos+1.477
Neg logit contributions
iless-1.622
igible-1.622
 checkpoints-1.578
idated-1.483
itimate-1.454
Token but
Token ID475
Feature activation-3.72e+00

Pos logit contributions
wcs+5.280
yip+4.777
Cra+4.731
kinson+4.464
atos+4.336
Neg logit contributions
igible-8.466
iless-8.224
 checkpoints-8.081
idated-7.911
itimate-7.720
Token indifferent
Token ID31655
Feature activation-3.40e+00

Pos logit contributions
wcs+3.006
Cra+2.906
yip+2.786
atos+2.724
 ingred+2.703
Neg logit contributions
iless-2.216
igible-2.197
 checkpoints-2.097
idated-1.977
OAD-1.917
Token"
Token ID1
Feature activation-1.87e+00

Pos logit contributions
wcs+2.005
Cra+1.910
yip+1.853
kinson+1.753
atos+1.726
Neg logit contributions
iless-2.745
igible-2.745
 checkpoints-2.667
idated-2.567
ulnerable-2.510
Token about
Token ID546
Feature activation-9.86e-01

Pos logit contributions
wcs+1.329
Cra+1.272
yip+1.235
kinson+1.176
 ingred+1.172
Neg logit contributions
iless-1.310
igible-1.305
 checkpoints-1.259
idated-1.201
ulnerable-1.177
Token London
Token ID3576
Feature activation+1.95e-01

Pos logit contributions
wcs+0.717
Cra+0.692
yip+0.671
 ingred+0.641
kinson+0.637
Neg logit contributions
iless-0.673
igible-0.670
 checkpoints-0.641
idated-0.613
ulnerable-0.604
Token With
Token ID2080
Feature activation-3.97e+00

Pos logit contributions
iless+1.084
igible+1.078
 checkpoints+1.036
idated+0.979
ulnerable+0.962
Neg logit contributions
wcs-1.281
Cra-1.235
yip-1.207
 ingred-1.152
hovah-1.145
Token Ghostbusters
Token ID50037
Feature activation+3.05e+00

Pos logit contributions
wcs+2.711
Cra+2.586
yip+2.513
 ingred+2.411
kinson+2.410
Neg logit contributions
iless-2.855
igible-2.808
 checkpoints-2.731
idated-2.580
itimate-2.558
Token we
Token ID356
Feature activation+5.96e-01

Pos logit contributions
iless+1.914
igible+1.904
 checkpoints+1.840
idated+1.734
ulnerable+1.693
Neg logit contributions
wcs-2.378
Cra-2.314
yip-2.250
 ingred-2.145
hovah-2.137
Token learned
Token ID4499
Feature activation-9.35e-01

Pos logit contributions
iless+0.369
igible+0.368
 checkpoints+0.353
idated+0.331
itimate+0.328
Neg logit contributions
wcs-0.473
Cra-0.457
yip-0.442
kinson-0.424
 ingred-0.424
Token that
Token ID326
Feature activation-1.09e+00

Pos logit contributions
wcs+0.663
Cra+0.640
yip+0.612
kinson+0.589
 ingred+0.583
Neg logit contributions
iless-0.659
igible-0.654
 checkpoints-0.626
idated-0.599
itimate-0.592
Token if
Token ID611
Feature activation-1.00e+01

Pos logit contributions
wcs+0.831
Cra+0.806
yip+0.776
kinson+0.745
 ingred+0.743
Neg logit contributions
iless-0.705
igible-0.701
 checkpoints-0.667
idated-0.639
itimate-0.629
Token you
Token ID345
Feature activation-6.22e-01

Pos logit contributions
wcs+4.345
Cra+3.939
craft+3.504
shock+3.495
 Atk+3.447
Neg logit contributions
igible-9.321
iless-9.320
itimate-8.818
 checkpoints-8.683
ulnerable-8.600
Token find
Token ID1064
Feature activation-1.86e-01

Pos logit contributions
wcs+0.428
Cra+0.414
yip+0.394
atos+0.378
kinson+0.377
Neg logit contributions
iless-0.450
igible-0.448
 checkpoints-0.428
idated-0.411
itimate-0.405
Token a
Token ID257
Feature activation+3.94e-01

Pos logit contributions
wcs+0.144
Cra+0.141
yip+0.134
kinson+0.129
atos+0.128
Neg logit contributions
iless-0.119
igible-0.118
 checkpoints-0.112
idated-0.107
itimate-0.105
Token phantom
Token ID36381
Feature activation+4.65e+00

Pos logit contributions
iless+0.182
igible+0.180
 checkpoints+0.170
idated+0.157
ulnerable+0.152
Neg logit contributions
wcs-0.375
Cra-0.366
yip-0.357
 ingred-0.345
kinson-0.343
Token,
Token ID11
Feature activation-1.98e-01

Pos logit contributions
iless+2.686
igible+2.655
 checkpoints+2.577
í+2.396
idated+2.383
Neg logit contributions
wcs-3.873
yip-3.701
Cra-3.701
hovah-3.678
 ingred-3.668
Token arm
Token ID3211
Feature activation+3.24e+00

Pos logit contributions
wcs+0.283
Cra+0.274
yip+0.265
 ingred+0.254
kinson+0.254
Neg logit contributions
iless-0.235
igible-0.232
 checkpoints-0.223
idated-0.211
ulnerable-0.207
Token.
Token ID13
Feature activation+3.54e-01

Pos logit contributions
iless+2.191
igible+2.188
 checkpoints+2.108
idated+1.969
í+1.960
Neg logit contributions
wcs-2.351
Cra-2.292
yip-2.227
hovah-2.131
 ingred-2.115
Token
Token ID198
Feature activation-1.62e+00

Pos logit contributions
iless+0.230
igible+0.229
 checkpoints+0.220
idated+0.209
itimate+0.205
Neg logit contributions
wcs-0.268
Cra-0.263
yip-0.251
 ingred-0.241
kinson-0.241
Token
Token ID198
Feature activation-7.04e-01

Pos logit contributions
Cra+1.181
wcs+1.176
yip+1.075
atos+1.067
kinson+1.064
Neg logit contributions
iless-1.091
igible-1.075
 checkpoints-1.032
idated-0.976
itimate-0.972
TokenScroll
Token ID29261
Feature activation-3.77e+00

Pos logit contributions
wcs+0.489
Cra+0.483
yip+0.451
 ingred+0.433
kinson+0.433
Neg logit contributions
iless-0.502
igible-0.500
 checkpoints-0.486
idated-0.459
itimate-0.450
Token down
Token ID866
Feature activation-1.00e+01

Pos logit contributions
wcs+2.501
Cra+2.462
yip+2.281
kinson+2.247
 ingred+2.239
Neg logit contributions
igible-2.752
iless-2.715
 checkpoints-2.627
idated-2.530
itimate-2.489
Token for
Token ID329
Feature activation-2.33e+00

Pos logit contributions
wcs+4.542
Cra+4.480
 ante+4.183
yip+4.167
 ingred+4.126
Neg logit contributions
igible-8.454
idated-8.198
iless-8.177
 checkpoints-8.158
itimate-7.877
Token video
Token ID2008
Feature activation-4.01e-01

Pos logit contributions
wcs+1.793
Cra+1.747
yip+1.672
 ingred+1.630
hovah+1.616
Neg logit contributions
iless-1.483
igible-1.466
 checkpoints-1.391
idated-1.341
ulnerable-1.303
Token
Token ID198
Feature activation-6.92e-01

Pos logit contributions
wcs+0.311
Cra+0.303
yip+0.293
 ingred+0.281
hovah+0.280
Neg logit contributions
iless-0.254
igible-0.252
 checkpoints-0.242
idated-0.229
itimate-0.225
Token
Token ID198
Feature activation-4.20e-01

Pos logit contributions
wcs+0.516
Cra+0.516
yip+0.476
atos+0.467
kinson+0.466
Neg logit contributions
iless-0.456
igible-0.449
 checkpoints-0.430
idated-0.407
itimate-0.405
TokenWhite
Token ID12256
Feature activation-1.65e+00

Pos logit contributions
wcs+0.268
Cra+0.263
yip+0.248
kinson+0.235
 ingred+0.235
Neg logit contributions
iless-0.324
igible-0.322
 checkpoints-0.312
idated-0.297
itimate-0.293
Token confirm
Token ID6216
Feature activation+1.69e+00

Pos logit contributions
iless+0.956
igible+0.948
 checkpoints+0.911
idated+0.865
itimate+0.847
Neg logit contributions
wcs-1.087
Cra-1.047
yip-1.016
 ingred-0.975
kinson-0.970
Token a
Token ID257
Feature activation-3.09e-01

Pos logit contributions
iless+1.100
igible+1.095
 checkpoints+1.055
idated+0.994
itimate+0.978
Neg logit contributions
wcs-1.284
Cra-1.241
yip-1.207
 ingred-1.156
hovah-1.155
Token release
Token ID2650
Feature activation-5.31e-01

Pos logit contributions
wcs+0.230
Cra+0.222
yip+0.213
 ingred+0.205
kinson+0.205
Neg logit contributions
iless-0.207
igible-0.205
 checkpoints-0.197
idated-0.188
ulnerable-0.184
Token date
Token ID3128
Feature activation+1.88e+00

Pos logit contributions
wcs+0.399
Cra+0.384
yip+0.369
kinson+0.356
 ingred+0.355
Neg logit contributions
iless-0.352
igible-0.349
 checkpoints-0.334
idated-0.319
ulnerable-0.313
Token for
Token ID329
Feature activation+7.37e-01

Pos logit contributions
iless+1.323
igible+1.318
 checkpoints+1.273
idated+1.208
itimate+1.186
Neg logit contributions
wcs-1.323
Cra-1.282
yip-1.246
 ingred-1.188
hovah-1.185
Token either
Token ID2035
Feature activation-9.98e+00

Pos logit contributions
iless+0.471
igible+0.467
 checkpoints+0.448
idated+0.424
ulnerable+0.416
Neg logit contributions
wcs-0.571
Cra-0.554
yip-0.536
 ingred-0.514
hovah-0.512
Token KH
Token ID40249
Feature activation+3.21e+00

Pos logit contributions
Cra+6.304
wcs+6.239
 ante+5.761
shock+5.757
craft+5.689
Neg logit contributions
iless-7.183
igible-6.928
 checkpoints-6.589
ulnerable-6.408
idated-6.296
Token3
Token ID18
Feature activation+1.90e+00

Pos logit contributions
iless+1.999
igible+1.985
 checkpoints+1.904
idated+1.805
itimate+1.762
Neg logit contributions
wcs-2.560
Cra-2.454
yip-2.383
 ingred-2.312
hovah-2.279
Token of
Token ID286
Feature activation+4.88e-01

Pos logit contributions
iless+1.021
igible+1.018
 checkpoints+0.973
idated+0.912
itimate+0.889
Neg logit contributions
wcs-1.661
Cra-1.607
yip-1.574
 ingred-1.522
hovah-1.511
Token FF
Token ID18402
Feature activation+3.35e+00

Pos logit contributions
iless+0.316
igible+0.314
 checkpoints+0.302
idated+0.285
itimate+0.280
Neg logit contributions
wcs-0.374
Cra-0.362
yip-0.351
 ingred-0.336
hovah-0.335
Token14
Token ID1415
Feature activation-7.17e-01

Pos logit contributions
igible+2.242
iless+2.222
 checkpoints+2.151
idated+2.039
itimate+2.002
Neg logit contributions
wcs-2.502
Cra-2.386
yip-2.315
 ingred-2.245
hovah-2.204
Token the
Token ID262
Feature activation-1.39e+00

Pos logit contributions
iless+0.239
igible+0.238
 checkpoints+0.228
idated+0.217
itimate+0.213
Neg logit contributions
wcs-0.265
Cra-0.257
yip-0.248
 ingred-0.238
kinson-0.237
Token entire
Token ID2104
Feature activation-4.24e-01

Pos logit contributions
wcs+0.989
Cra+0.963
yip+0.926
 ingred+0.889
atos+0.883
Neg logit contributions
iless-0.946
igible-0.940
 checkpoints-0.895
idated-0.859
itimate-0.844
Token state
Token ID1181
Feature activation-2.13e+00

Pos logit contributions
wcs+0.311
Cra+0.301
yip+0.291
 ingred+0.278
kinson+0.276
Neg logit contributions
iless-0.286
igible-0.282
 checkpoints-0.272
idated-0.260
itimate-0.254
Token.
Token ID13
Feature activation-1.98e+00

Pos logit contributions
wcs+1.479
Cra+1.421
yip+1.372
 ingred+1.307
kinson+1.304
Neg logit contributions
iless-1.533
igible-1.524
 checkpoints-1.468
idated-1.402
itimate-1.378
Token "
Token ID366
Feature activation-3.13e+00

Pos logit contributions
wcs+1.455
Cra+1.425
yip+1.354
atos+1.301
kinson+1.300
Neg logit contributions
iless-1.324
igible-1.307
 checkpoints-1.259
idated-1.196
itimate-1.180
TokenIf
Token ID1532
Feature activation-9.98e+00

Pos logit contributions
Cra+1.902
wcs+1.894
yip+1.720
waters+1.671
atos+1.668
Neg logit contributions
iless-2.489
igible-2.456
 checkpoints-2.397
idated-2.275
itimate-2.232
Token Matthew
Token ID9308
Feature activation-1.14e+00

Pos logit contributions
wcs+6.330
Cra+5.809
waters+5.761
yip+5.656
 ante+5.501
Neg logit contributions
iless-7.086
igible-6.874
 checkpoints-6.558
idated-6.489
icist-6.428
Token directly
Token ID3264
Feature activation-4.08e-01

Pos logit contributions
wcs+0.837
Cra+0.808
yip+0.778
 ingred+0.747
kinson+0.745
Neg logit contributions
iless-0.766
igible-0.763
 checkpoints-0.731
idated-0.698
itimate-0.684
Token impacts
Token ID12751
Feature activation-2.36e+00

Pos logit contributions
wcs+0.338
Cra+0.326
yip+0.317
kinson+0.305
 ingred+0.305
Neg logit contributions
iless-0.238
igible-0.236
 checkpoints-0.225
idated-0.213
itimate-0.208
Token Florida
Token ID4744
Feature activation+3.68e-01

Pos logit contributions
wcs+1.696
Cra+1.639
yip+1.567
 ingred+1.512
waters+1.507
Neg logit contributions
iless-1.606
igible-1.599
 checkpoints-1.523
idated-1.462
itimate-1.429
Token,"
Token ID553
Feature activation+2.16e+00

Pos logit contributions
iless+0.246
igible+0.244
 checkpoints+0.235
idated+0.222
ulnerable+0.219
Neg logit contributions
wcs-0.275
Cra-0.266
yip-0.258
 ingred-0.247
hovah-0.246
Token Vector
Token ID20650
Feature activation+2.20e+00

Pos logit contributions
iless+2.363
igible+2.326
 checkpoints+2.274
idated+2.114
itimate+2.087
Neg logit contributions
wcs-2.803
Cra-2.717
yip-2.674
 ingred-2.520
hovah-2.513
Token<
Token ID27
Feature activation+3.02e+00

Pos logit contributions
iless+1.298
igible+1.287
 checkpoints+1.241
idated+1.172
itimate+1.139
Neg logit contributions
wcs-1.802
Cra-1.727
yip-1.718
hovah-1.634
 ingred-1.617
Token Part
Token ID2142
Feature activation+4.34e+00

Pos logit contributions
iless+2.208
igible+2.182
 checkpoints+2.136
idated+1.999
itimate+1.982
Neg logit contributions
wcs-2.035
Cra-1.968
yip-1.915
hovah-1.810
 ingred-1.809
Tokenicle
Token ID1548
Feature activation+8.29e-01

Pos logit contributions
iless+3.306
igible+3.276
 checkpoints+3.097
idated+2.997
í+2.992
Neg logit contributions
wcs-2.824
Cra-2.672
yip-2.643
hovah-2.525
 ingred-2.516
Token >
Token ID1875
Feature activation+3.11e+00

Pos logit contributions
iless+0.538
igible+0.534
 checkpoints+0.513
idated+0.486
ulnerable+0.476
Neg logit contributions
wcs-0.634
Cra-0.613
yip-0.595
 ingred-0.570
hovah-0.568
Token &
Token ID1222
Feature activation+7.76e+00

Pos logit contributions
iless+2.219
igible+2.211
 checkpoints+2.158
idated+2.032
itimate+1.989
Neg logit contributions
wcs-2.173
Cra-2.092
yip-2.042
hovah-1.921
kinson-1.909
Token particles
Token ID13166
Feature activation+4.90e-01

Pos logit contributions
iless+4.960
 checkpoints+4.959
igible+4.935
idated+4.502
 rover+4.473
Neg logit contributions
wcs-5.719
Cra-5.583
yip-5.525
hovah-5.162
atos-5.107
Token )
Token ID1267
Feature activation+2.24e+00

Pos logit contributions
iless+0.353
igible+0.351
 checkpoints+0.339
idated+0.322
itimate+0.317
Neg logit contributions
wcs-0.339
Cra-0.327
yip-0.316
 ingred-0.301
hovah-0.300
Token {
Token ID1391
Feature activation+3.77e+00

Pos logit contributions
iless+1.758
igible+1.741
 checkpoints+1.721
idated+1.618
itimate+1.600
Neg logit contributions
wcs-1.400
Cra-1.341
yip-1.315
hovah-1.228
 ingred-1.228
Token density
Token ID12109
Feature activation-1.57e+00

Pos logit contributions
iless+2.465
igible+2.442
 checkpoints+2.392
idated+2.219
itimate+2.185
Neg logit contributions
wcs-2.852
Cra-2.768
yip-2.699
hovah-2.569
 ingred-2.544
TokenGrid
Token ID41339
Feature activation+1.85e+00

Pos logit contributions
wcs+0.825
Cra+0.788
yip+0.747
 ingred+0.701
kinson+0.695
Neg logit contributions
iless-1.395
igible-1.388
 checkpoints-1.348
idated-1.293
ulnerable-1.281
TokenEarth
Token ID22840
Feature activation-5.54e-01

Pos logit contributions
igible+2.620
iless+2.616
 checkpoints+2.492
idated+2.409
í+2.376
Neg logit contributions
wcs-2.525
yip-2.398
Cra-2.375
hovah-2.304
 ingred-2.300
Token's
Token ID338
Feature activation+1.24e+00

Pos logit contributions
wcs+0.432
Cra+0.419
yip+0.404
kinson+0.388
 ingred+0.387
Neg logit contributions
iless-0.350
igible-0.348
 checkpoints-0.333
idated-0.317
ulnerable-0.309
Token spin
Token ID7906
Feature activation+2.34e+00

Pos logit contributions
iless+0.728
igible+0.723
 checkpoints+0.694
idated+0.651
itimate+0.638
Neg logit contributions
wcs-1.019
Cra-0.988
yip-0.961
 ingred-0.923
hovah-0.920
Token,
Token ID11
Feature activation+5.81e-01

Pos logit contributions
iless+1.510
igible+1.495
 checkpoints+1.441
idated+1.357
ulnerable+1.333
Neg logit contributions
wcs-1.792
Cra-1.735
yip-1.683
 ingred-1.613
hovah-1.608
Token of
Token ID286
Feature activation+2.80e-02

Pos logit contributions
iless+0.381
igible+0.377
 checkpoints+0.359
idated+0.343
ulnerable+0.339
Neg logit contributions
wcs-0.441
Cra-0.426
yip-0.413
 ingred-0.395
kinson-0.394
Token course
Token ID1781
Feature activation+7.04e+00

Pos logit contributions
iless+0.017
igible+0.017
 checkpoints+0.016
idated+0.015
ulnerable+0.015
Neg logit contributions
wcs-0.023
Cra-0.022
yip-0.022
kinson-0.021
 ingred-0.021
Token,
Token ID11
Feature activation+1.46e+00

Pos logit contributions
iless+3.986
igible+3.930
 checkpoints+3.798
 rover+3.493
idated+3.483
Neg logit contributions
wcs-5.736
Cra-5.654
yip-5.570
 ingred-5.305
hovah-5.286
Token is
Token ID318
Feature activation+9.29e-01

Pos logit contributions
iless+0.976
igible+0.969
 checkpoints+0.936
idated+0.882
itimate+0.868
Neg logit contributions
wcs-1.086
Cra-1.052
yip-1.018
 ingred-0.973
hovah-0.970
Token not
Token ID407
Feature activation+1.95e+00

Pos logit contributions
iless+0.607
igible+0.603
 checkpoints+0.581
idated+0.549
ulnerable+0.539
Neg logit contributions
wcs-0.706
Cra-0.683
yip-0.661
 ingred-0.633
hovah-0.631
Token the
Token ID262
Feature activation+2.71e+00

Pos logit contributions
iless+1.255
igible+1.252
 checkpoints+1.210
idated+1.137
ulnerable+1.117
Neg logit contributions
wcs-1.486
Cra-1.443
yip-1.403
hovah-1.338
 ingred-1.337
Token only
Token ID691
Feature activation+1.13e+00

Pos logit contributions
iless+1.789
igible+1.777
 checkpoints+1.719
idated+1.618
ulnerable+1.587
Neg logit contributions
wcs-2.046
Cra-1.981
yip-1.916
 ingred-1.830
hovah-1.830
Token who
Token ID508
Feature activation+1.58e+00

Pos logit contributions
wcs+1.463
Cra+1.414
yip+1.359
 ingred+1.299
kinson+1.296
Neg logit contributions
iless-1.388
igible-1.375
 checkpoints-1.316
idated-1.254
itimate-1.234
Token made
Token ID925
Feature activation-6.39e-01

Pos logit contributions
iless+1.120
igible+1.113
 checkpoints+1.074
idated+1.020
ulnerable+1.001
Neg logit contributions
wcs-1.113
Cra-1.076
yip-1.041
 ingred-0.992
hovah-0.987
Token sure
Token ID1654
Feature activation+3.25e+00

Pos logit contributions
wcs+0.510
Cra+0.497
yip+0.477
 ingred+0.463
atos+0.458
Neg logit contributions
iless-0.392
igible-0.388
 checkpoints-0.362
idated-0.351
ulnerable-0.346
Token Thomas
Token ID5658
Feature activation-7.68e-02

Pos logit contributions
iless+2.059
igible+2.036
 checkpoints+1.994
idated+1.859
itimate+1.820
Neg logit contributions
wcs-2.516
Cra-2.444
yip-2.385
hovah-2.279
 ingred-2.261
Token safely
Token ID11512
Feature activation+5.20e+00

Pos logit contributions
wcs+0.052
Cra+0.050
yip+0.048
 ingred+0.046
kinson+0.046
Neg logit contributions
iless-0.056
igible-0.056
 checkpoints-0.054
idated-0.051
ulnerable-0.051
Token navig
Token ID20436
Feature activation+1.12e+01

Pos logit contributions
iless+3.418
igible+3.411
 checkpoints+3.360
idated+3.110
í+3.100
Neg logit contributions
wcs-3.821
Cra-3.798
yip-3.734
 ingred-3.495
hovah-3.480
Tokenated
Token ID515
Feature activation+3.21e+00

Pos logit contributions
igible+4.002
iless+3.902
idated+3.546
 checkpoints+3.484
í+3.146
Neg logit contributions
yip-11.443
wcs-11.354
Cra-11.291
 ingred-11.106
hovah-10.881
Token
Token ID564
Feature activation+6.60e-01

Pos logit contributions
iless+2.184
igible+2.157
 checkpoints+2.136
idated+1.981
ulnerable+1.942
Neg logit contributions
wcs-2.335
Cra-2.269
yip-2.215
hovah-2.110
kinson-2.088
Token
Token ID250
Feature activation+3.39e-01

Pos logit contributions
iless+0.531
igible+0.526
 checkpoints+0.511
idated+0.489
ulnerable+0.481
Neg logit contributions
wcs-0.405
Cra-0.388
yip-0.375
kinson-0.351
hovah-0.350
Tokenurban
Token ID32679
Feature activation+2.25e-01

Pos logit contributions
iless+0.240
igible+0.238
 checkpoints+0.230
idated+0.218
ulnerable+0.215
Neg logit contributions
wcs-0.240
Cra-0.231
yip-0.224
 ingred-0.214
hovah-0.213
Token for
Token ID329
Feature activation-6.67e-01

Pos logit contributions
iless+0.146
igible+0.145
 checkpoints+0.139
idated+0.131
itimate+0.130
Neg logit contributions
wcs-0.171
Cra-0.166
yip-0.160
 ingred-0.154
kinson-0.153
Token (
Token ID357
Feature activation-1.84e+00

Pos logit contributions
wcs+0.205
Cra+0.199
yip+0.192
 ingred+0.183
hovah+0.182
Neg logit contributions
iless-0.198
igible-0.197
 checkpoints-0.190
idated-0.181
itimate-0.177
Tokenbelow
Token ID35993
Feature activation-3.59e+00

Pos logit contributions
wcs+1.252
Cra+1.218
yip+1.163
kinson+1.105
 ingred+1.099
Neg logit contributions
iless-1.345
igible-1.341
 checkpoints-1.296
idated-1.228
ulnerable-1.211
Token),
Token ID828
Feature activation+1.52e+00

Pos logit contributions
wcs+2.407
Cra+2.354
yip+2.292
kinson+2.183
 ingred+2.179
Neg logit contributions
iless-2.576
igible-2.547
 checkpoints-2.462
idated-2.353
itimate-2.336
Token the
Token ID262
Feature activation+1.43e+00

Pos logit contributions
iless+1.006
igible+0.999
 checkpoints+0.961
idated+0.910
itimate+0.894
Neg logit contributions
wcs-1.142
Cra-1.105
yip-1.070
 ingred-1.024
hovah-1.020
Token sk
Token ID1341
Feature activation+1.18e-02

Pos logit contributions
iless+0.906
igible+0.899
 checkpoints+0.864
idated+0.816
ulnerable+0.800
Neg logit contributions
wcs-1.115
Cra-1.080
yip-1.047
 ingred-1.003
hovah-1.000
Tokenipper
Token ID14710
Feature activation+7.57e+00

Pos logit contributions
iless+0.011
igible+0.011
 checkpoints+0.011
idated+0.010
itimate+0.010
Neg logit contributions
wcs-0.006
Cra-0.005
yip-0.005
 ingred-0.005
hovah-0.005
Token and
Token ID290
Feature activation+1.94e+00

Pos logit contributions
iless+4.773
igible+4.645
 checkpoints+4.625
í+4.368
 rover+4.283
Neg logit contributions
wcs-5.569
Cra-5.425
yip-5.377
hovah-5.198
 ingred-5.092
Token project
Token ID1628
Feature activation+2.32e+00

Pos logit contributions
iless+1.175
igible+1.166
 checkpoints+1.118
idated+1.053
itimate+1.032
Neg logit contributions
wcs-1.567
Cra-1.518
yip-1.475
 ingred-1.415
hovah-1.411
Token manager
Token ID4706
Feature activation+5.38e+00

Pos logit contributions
iless+1.378
igible+1.368
 checkpoints+1.308
idated+1.228
itimate+1.207
Neg logit contributions
wcs-1.909
Cra-1.844
yip-1.802
hovah-1.721
 ingred-1.718
Token of
Token ID286
Feature activation+4.85e-02

Pos logit contributions
iless+3.633
igible+3.542
 checkpoints+3.482
í+3.294
 rover+3.248
Neg logit contributions
wcs-3.878
Cra-3.738
yip-3.688
hovah-3.511
 ingred-3.499
Token the
Token ID262
Feature activation-4.56e-01

Pos logit contributions
iless+0.031
igible+0.031
 checkpoints+0.029
idated+0.028
ulnerable+0.027
Neg logit contributions
wcs-0.038
Cra-0.036
yip-0.035
 ingred-0.034
kinson-0.034
Token.
Token ID13
Feature activation-5.15e-01

Pos logit contributions
wcs+0.195
Cra+0.188
yip+0.182
 ingred+0.173
hovah+0.173
Neg logit contributions
iless-0.202
igible-0.201
 checkpoints-0.193
idated-0.184
ulnerable-0.181
Token
Token ID198
Feature activation-9.63e-01

Pos logit contributions
wcs+0.404
Cra+0.392
yip+0.378
 ingred+0.363
hovah+0.362
Neg logit contributions
iless-0.323
igible-0.321
 checkpoints-0.308
idated-0.290
itimate-0.285
Token
Token ID198
Feature activation-8.18e-01

Pos logit contributions
wcs+0.726
Cra+0.718
yip+0.668
atos+0.654
kinson+0.652
Neg logit contributions
iless-0.629
igible-0.623
 checkpoints-0.595
idated-0.563
itimate-0.558
TokenWomen
Token ID18495
Feature activation+3.13e+00

Pos logit contributions
wcs+0.525
Cra+0.508
yip+0.483
 ingred+0.459
kinson+0.457
Neg logit contributions
iless-0.632
igible-0.629
 checkpoints-0.610
idated-0.581
ulnerable-0.572
Token's
Token ID338
Feature activation+2.23e+00

Pos logit contributions
iless+2.133
igible+2.120
 checkpoints+2.044
idated+1.921
ulnerable+1.906
Neg logit contributions
wcs-2.296
Cra-2.227
yip-2.160
hovah-2.062
 ingred-2.055
Token rights
Token ID2489
Feature activation+7.15e+00

Pos logit contributions
iless+1.406
igible+1.395
 checkpoints+1.338
idated+1.267
ulnerable+1.239
Neg logit contributions
wcs-1.754
Cra-1.698
yip-1.646
 ingred-1.579
hovah-1.572
Token groups
Token ID2628
Feature activation+5.87e+00

Pos logit contributions
igible+3.665
 checkpoints+3.662
iless+3.657
í+3.238
ulnerable+3.235
Neg logit contributions
wcs-6.143
Cra-6.075
yip-5.952
hovah-5.693
atos-5.648
Token warn
Token ID9828
Feature activation+3.25e+00

Pos logit contributions
igible+3.871
iless+3.836
 checkpoints+3.804
í+3.516
itimate+3.480
Neg logit contributions
wcs-4.286
Cra-4.211
yip-4.115
hovah-3.952
 ingred-3.875
Token the
Token ID262
Feature activation-1.46e+00

Pos logit contributions
iless+2.111
igible+2.085
 checkpoints+2.025
idated+1.891
itimate+1.875
Neg logit contributions
wcs-2.460
Cra-2.403
yip-2.361
hovah-2.252
 ingred-2.230
Token new
Token ID649
Feature activation+1.50e+00

Pos logit contributions
wcs+1.038
Cra+0.997
yip+0.955
 ingred+0.922
kinson+0.917
Neg logit contributions
igible-1.017
iless-1.016
 checkpoints-0.966
idated-0.929
ulnerable-0.910
Token interim
Token ID19303
Feature activation-3.53e+00

Pos logit contributions
iless+1.031
igible+1.022
 checkpoints+0.996
idated+0.935
ulnerable+0.921
Neg logit contributions
wcs-1.087
Cra-1.052
yip-1.028
hovah-0.973
 ingred-0.971
Token'm
Token ID1101
Feature activation-8.12e-01

Pos logit contributions
iless+1.330
igible+1.323
 checkpoints+1.278
idated+1.217
itimate+1.197
Neg logit contributions
wcs-1.223
Cra-1.179
yip-1.139
 ingred-1.085
hovah-1.081
Token praying
Token ID26002
Feature activation+1.47e+00

Pos logit contributions
wcs+0.617
Cra+0.600
yip+0.572
kinson+0.553
 ingred+0.552
Neg logit contributions
iless-0.530
igible-0.525
 checkpoints-0.500
idated-0.477
itimate-0.470
Token that
Token ID326
Feature activation+4.41e-01

Pos logit contributions
iless+0.992
igible+0.981
 checkpoints+0.950
idated+0.895
ulnerable+0.883
Neg logit contributions
wcs-1.086
Cra-1.048
yip-1.020
 ingred-0.969
hovah-0.969
Token our
Token ID674
Feature activation+1.06e+00

Pos logit contributions
iless+0.290
igible+0.288
 checkpoints+0.276
idated+0.262
ulnerable+0.257
Neg logit contributions
wcs-0.334
Cra-0.323
yip-0.312
 ingred-0.300
kinson-0.298
Token school
Token ID1524
Feature activation-9.33e-01

Pos logit contributions
iless+0.695
igible+0.691
 checkpoints+0.663
idated+0.628
itimate+0.617
Neg logit contributions
wcs-0.804
Cra-0.778
yip-0.753
 ingred-0.721
hovah-0.718
Token district
Token ID4783
Feature activation+1.21e+00

Pos logit contributions
wcs+0.677
Cra+0.655
yip+0.630
 ingred+0.606
kinson+0.604
Neg logit contributions
iless-0.640
igible-0.638
 checkpoints-0.608
idated-0.579
ulnerable-0.571
Token will
Token ID481
Feature activation+4.12e-02

Pos logit contributions
iless+0.794
igible+0.788
 checkpoints+0.765
idated+0.719
itimate+0.707
Neg logit contributions
wcs-0.917
Cra-0.886
yip-0.864
hovah-0.824
 ingred-0.820
Token reconsider
Token ID26540
Feature activation-1.25e+00

Pos logit contributions
iless+0.027
igible+0.026
 checkpoints+0.025
idated+0.024
itimate+0.023
Neg logit contributions
wcs-0.032
Cra-0.031
yip-0.030
 ingred-0.028
kinson-0.028
Token its
Token ID663
Feature activation-1.76e-01

Pos logit contributions
wcs+0.911
Cra+0.878
yip+0.841
 ingred+0.810
atos+0.805
Neg logit contributions
iless-0.863
igible-0.855
 checkpoints-0.814
idated-0.783
ulnerable-0.771
Token recent
Token ID2274
Feature activation-8.66e-01

Pos logit contributions
wcs+0.131
Cra+0.127
yip+0.122
 ingred+0.117
hovah+0.116
Neg logit contributions
iless-0.118
igible-0.117
 checkpoints-0.112
idated-0.106
ulnerable-0.104
Token decision
Token ID2551
Feature activation-1.91e+00

Pos logit contributions
wcs+0.643
Cra+0.623
yip+0.598
 ingred+0.576
kinson+0.571
Neg logit contributions
iless-0.583
igible-0.577
 checkpoints-0.550
idated-0.526
ulnerable-0.516
Token done
Token ID1760
Feature activation+5.28e-01

Pos logit contributions
iless+0.808
igible+0.804
 checkpoints+0.777
idated+0.742
itimate+0.731
Neg logit contributions
wcs-0.647
Cra-0.623
yip-0.599
 ingred-0.568
hovah-0.566
Token on
Token ID319
Feature activation+1.74e+00

Pos logit contributions
iless+0.374
igible+0.371
 checkpoints+0.359
idated+0.340
ulnerable+0.335
Neg logit contributions
wcs-0.372
Cra-0.360
yip-0.348
 ingred-0.332
hovah-0.331
Token an
Token ID281
Feature activation-3.02e+00

Pos logit contributions
iless+1.116
igible+1.111
 checkpoints+1.071
idated+1.008
itimate+0.990
Neg logit contributions
wcs-1.337
Cra-1.292
yip-1.254
hovah-1.204
 ingred-1.199
Token elevated
Token ID15321
Feature activation-7.69e-01

Pos logit contributions
wcs+2.087
Cra+2.018
yip+1.916
 ingred+1.875
kinson+1.851
Neg logit contributions
iless-2.177
igible-2.125
 checkpoints-2.043
idated-1.958
ulnerable-1.949
Token,
Token ID11
Feature activation-2.78e+00

Pos logit contributions
wcs+0.586
Cra+0.568
yip+0.549
 ingred+0.528
kinson+0.524
Neg logit contributions
iless-0.500
igible-0.495
 checkpoints-0.475
idated-0.450
ulnerable-0.444
Token fold
Token ID5591
Feature activation+3.59e+00

Pos logit contributions
wcs+2.012
Cra+1.945
yip+1.874
 ingred+1.802
kinson+1.787
Neg logit contributions
iless-1.903
igible-1.885
 checkpoints-1.802
idated-1.727
ulnerable-1.705
Token-
Token ID12
Feature activation+3.72e+00

Pos logit contributions
igible+2.013
iless+1.998
 checkpoints+1.875
idated+1.774
itimate+1.739
Neg logit contributions
wcs-3.080
Cra-2.966
yip-2.870
 ingred-2.806
hovah-2.803
Tokenup
Token ID929
Feature activation+1.19e+00

Pos logit contributions
iless+2.352
igible+2.334
 checkpoints+2.205
idated+2.115
itimate+2.082
Neg logit contributions
wcs-2.880
Cra-2.788
yip-2.666
 ingred-2.642
hovah-2.603
Token table
Token ID3084
Feature activation-3.86e+00

Pos logit contributions
iless+0.764
igible+0.763
 checkpoints+0.732
idated+0.693
itimate+0.678
Neg logit contributions
wcs-0.913
Cra-0.881
yip-0.857
hovah-0.822
 ingred-0.818
Token behind
Token ID2157
Feature activation-2.45e+00

Pos logit contributions
wcs+2.637
Cra+2.523
yip+2.428
kinson+2.331
atos+2.313
Neg logit contributions
iless-2.783
igible-2.757
 checkpoints-2.691
idated-2.556
itimate-2.523
Token the
Token ID262
Feature activation-2.08e+00

Pos logit contributions
wcs+1.804
Cra+1.753
yip+1.684
 ingred+1.630
kinson+1.613
Neg logit contributions
iless-1.624
igible-1.616
 checkpoints-1.537
idated-1.472
ulnerable-1.453
Token come
Token ID1282
Feature activation-1.84e-01

Pos logit contributions
iless+0.947
igible+0.942
 checkpoints+0.905
idated+0.860
ulnerable+0.847
Neg logit contributions
wcs-0.975
Cra-0.939
yip-0.907
 ingred-0.867
hovah-0.864
Token back
Token ID736
Feature activation-2.31e+00

Pos logit contributions
wcs+0.130
Cra+0.125
yip+0.121
 ingred+0.116
kinson+0.115
Neg logit contributions
iless-0.130
igible-0.129
 checkpoints-0.124
idated-0.118
itimate-0.116
Token
Token ID198
Feature activation+2.98e+00

Pos logit contributions
wcs+1.709
Cra+1.645
yip+1.577
 ingred+1.524
atos+1.513
Neg logit contributions
igible-1.542
iless-1.530
 checkpoints-1.455
idated-1.398
itimate-1.373
Token
Token ID198
Feature activation+2.33e+00

Pos logit contributions
iless+1.685
igible+1.675
 checkpoints+1.611
idated+1.508
í+1.489
Neg logit contributions
wcs-2.529
Cra-2.426
yip-2.412
 ingred-2.355
hovah-2.348
Tokenhe
Token ID258
Feature activation-1.84e+00

Pos logit contributions
iless+1.646
igible+1.627
 checkpoints+1.569
idated+1.495
itimate+1.475
Neg logit contributions
wcs-1.641
Cra-1.569
yip-1.532
hovah-1.475
 ingred-1.471
Token may
Token ID743
Feature activation+1.29e+00

Pos logit contributions
wcs+1.301
Cra+1.240
yip+1.200
atos+1.156
kinson+1.151
Neg logit contributions
iless-1.285
igible-1.281
 checkpoints-1.222
idated-1.176
ulnerable-1.154
Token have
Token ID423
Feature activation+2.12e-02

Pos logit contributions
iless+0.861
igible+0.855
 checkpoints+0.822
idated+0.779
itimate+0.765
Neg logit contributions
wcs-0.968
Cra-0.936
yip-0.907
 ingred-0.868
hovah-0.864
Token gone
Token ID3750
Feature activation-9.68e-01

Pos logit contributions
iless+0.015
igible+0.015
 checkpoints+0.015
idated+0.014
ulnerable+0.014
Neg logit contributions
wcs-0.015
Cra-0.014
yip-0.013
 ingred-0.013
kinson-0.013
Token back
Token ID736
Feature activation-2.33e+00

Pos logit contributions
wcs+0.661
Cra+0.635
yip+0.613
 ingred+0.584
kinson+0.582
Neg logit contributions
iless-0.705
igible-0.703
 checkpoints-0.675
idated-0.648
itimate-0.637
Token to
Token ID284
Feature activation-3.77e+00

Pos logit contributions
wcs+1.632
Cra+1.573
yip+1.523
 ingred+1.453
kinson+1.447
Neg logit contributions
igible-1.645
iless-1.639
 checkpoints-1.570
idated-1.508
itimate-1.485
Token Dragon
Token ID2851
Feature activation-2.65e+00

Pos logit contributions
wcs+2.662
Cra+2.649
yip+2.510
 ingred+2.449
atos+2.398
Neg logit contributions
igible-2.560
iless-2.553
 checkpoints-2.384
idated-2.291
ulnerable-2.283
Token already
Token ID1541
Feature activation-1.26e-01

Pos logit contributions
iless+0.844
igible+0.838
 checkpoints+0.806
idated+0.762
ulnerable+0.747
Neg logit contributions
wcs-1.017
Cra-0.984
yip-0.955
 ingred-0.917
hovah-0.914
Token know
Token ID760
Feature activation-3.19e+00

Pos logit contributions
wcs+0.105
Cra+0.102
yip+0.098
kinson+0.095
atos+0.094
Neg logit contributions
iless-0.073
igible-0.073
 checkpoints-0.069
idated-0.066
itimate-0.064
Token your
Token ID534
Feature activation-1.06e+00

Pos logit contributions
wcs+1.953
Cra+1.876
yip+1.796
kinson+1.706
atos+1.687
Neg logit contributions
iless-2.538
igible-2.522
 checkpoints-2.429
idated-2.339
itimate-2.311
Token way
Token ID835
Feature activation+8.95e-01

Pos logit contributions
wcs+0.706
Cra+0.675
yip+0.641
kinson+0.615
atos+0.610
Neg logit contributions
iless-0.793
igible-0.790
 checkpoints-0.760
idated-0.737
itimate-0.719
Token around
Token ID1088
Feature activation+2.21e+00

Pos logit contributions
iless+0.595
igible+0.591
 checkpoints+0.573
idated+0.535
ulnerable+0.531
Neg logit contributions
wcs-0.666
Cra-0.646
yip-0.632
hovah-0.611
 ingred-0.610
Token Angular
Token ID28147
Feature activation+1.85e+00

Pos logit contributions
igible+1.513
iless+1.512
 checkpoints+1.453
idated+1.376
ulnerable+1.357
Neg logit contributions
wcs-1.618
Cra-1.547
yip-1.509
 ingred-1.463
hovah-1.459
Token,
Token ID11
Feature activation+1.67e+00

Pos logit contributions
iless+1.152
igible+1.144
 checkpoints+1.100
idated+1.037
í+1.019
Neg logit contributions
wcs-1.458
Cra-1.401
yip-1.373
 ingred-1.337
hovah-1.329
Token these
Token ID777
Feature activation+2.76e+00

Pos logit contributions
iless+1.154
igible+1.147
 checkpoints+1.104
idated+1.049
itimate+1.031
Neg logit contributions
wcs-1.204
Cra-1.163
yip-1.125
 ingred-1.074
hovah-1.069
Token may
Token ID743
Feature activation+1.41e-01

Pos logit contributions
iless+1.560
igible+1.552
 checkpoints+1.502
idated+1.383
ulnerable+1.368
Neg logit contributions
wcs-2.333
Cra-2.266
yip-2.206
hovah-2.148
 ingred-2.135
Token be
Token ID307
Feature activation+1.25e+00

Pos logit contributions
iless+0.098
igible+0.098
 checkpoints+0.094
idated+0.089
itimate+0.088
Neg logit contributions
wcs-0.101
Cra-0.098
yip-0.094
kinson-0.090
 ingred-0.089
Token helpful
Token ID7613
Feature activation+1.87e+00

Pos logit contributions
iless+0.788
igible+0.783
 checkpoints+0.753
idated+0.710
ulnerable+0.696
Neg logit contributions
wcs-0.981
Cra-0.950
yip-0.924
hovah-0.885
 ingred-0.885
Token the
Token ID262
Feature activation+1.84e-01

Pos logit contributions
wcs+0.765
Cra+0.740
yip+0.719
 ingred+0.690
hovah+0.683
Neg logit contributions
iless-0.652
igible-0.648
 checkpoints-0.619
idated-0.589
ulnerable-0.578
Token noun
Token ID23227
Feature activation-1.99e+00

Pos logit contributions
iless+0.121
igible+0.120
 checkpoints+0.115
idated+0.109
itimate+0.107
Neg logit contributions
wcs-0.139
Cra-0.134
yip-0.130
 ingred-0.125
hovah-0.124
Token is
Token ID318
Feature activation-7.42e-01

Pos logit contributions
wcs+1.519
Cra+1.465
yip+1.423
 ingred+1.371
atos+1.361
Neg logit contributions
iless-1.277
igible-1.264
 checkpoints-1.219
idated-1.158
ulnerable-1.136
Token over
Token ID625
Feature activation+2.49e+00

Pos logit contributions
wcs+0.602
Cra+0.583
yip+0.565
 ingred+0.545
hovah+0.540
Neg logit contributions
iless-0.446
igible-0.443
 checkpoints-0.422
idated-0.399
itimate-0.391
Token there
Token ID612
Feature activation+2.20e+00

Pos logit contributions
iless+1.465
igible+1.458
 checkpoints+1.399
idated+1.314
ulnerable+1.285
Neg logit contributions
wcs-2.045
Cra-1.985
yip-1.926
kinson-1.853
 ingred-1.852
Token,
Token ID11
Feature activation+1.43e+00

Pos logit contributions
iless+1.480
igible+1.464
 checkpoints+1.413
idated+1.330
ulnerable+1.315
Neg logit contributions
wcs-1.631
Cra-1.587
yip-1.526
 ingred-1.464
hovah-1.459
Token and
Token ID290
Feature activation+2.55e+00

Pos logit contributions
iless+0.915
igible+0.909
 checkpoints+0.876
idated+0.823
itimate+0.810
Neg logit contributions
wcs-1.110
Cra-1.076
yip-1.042
 ingred-0.999
hovah-0.996
Token you
Token ID345
Feature activation+7.36e-01

Pos logit contributions
iless+1.588
igible+1.571
 checkpoints+1.529
idated+1.421
itimate+1.404
Neg logit contributions
wcs-2.012
Cra-1.950
yip-1.892
hovah-1.814
kinson-1.806
Token still
Token ID991
Feature activation-2.07e+00

Pos logit contributions
iless+0.479
igible+0.476
 checkpoints+0.458
idated+0.432
itimate+0.425
Neg logit contributions
wcs-0.562
Cra-0.545
yip-0.528
 ingred-0.505
hovah-0.505
Token had
Token ID550
Feature activation+1.32e+00

Pos logit contributions
wcs+1.530
Cra+1.471
yip+1.426
 ingred+1.366
kinson+1.358
Neg logit contributions
iless-1.393
igible-1.384
 checkpoints-1.328
idated-1.264
ulnerable-1.241
Token to
Token ID284
Feature activation+1.49e+00

Pos logit contributions
iless+0.862
igible+0.857
 checkpoints+0.830
idated+0.779
itimate+0.767
Neg logit contributions
wcs-1.000
Cra-0.972
yip-0.939
 ingred-0.899
hovah-0.898
Token home
Token ID1363
Feature activation-2.12e-01

Pos logit contributions
iless+1.934
igible+1.917
 checkpoints+1.866
idated+1.736
itimate+1.696
Neg logit contributions
wcs-2.890
Cra-2.782
yip-2.748
hovah-2.630
kinson-2.608
Token,
Token ID11
Feature activation+1.15e+00

Pos logit contributions
wcs+0.162
Cra+0.157
yip+0.150
 ingred+0.145
kinson+0.145
Neg logit contributions
iless-0.137
igible-0.136
 checkpoints-0.130
idated-0.124
ulnerable-0.122
Token however
Token ID2158
Feature activation+7.06e-01

Pos logit contributions
iless+0.781
igible+0.776
 checkpoints+0.745
idated+0.708
ulnerable+0.697
Neg logit contributions
wcs-0.843
Cra-0.816
yip-0.788
 ingred-0.754
kinson-0.750
Token basic
Token ID4096
Feature activation+1.19e+00

Pos logit contributions
iless+0.429
igible+0.427
 checkpoints+0.408
idated+0.385
ulnerable+0.377
Neg logit contributions
wcs-0.568
Cra-0.553
yip-0.534
 ingred-0.515
kinson-0.511
Token,
Token ID11
Feature activation-8.16e-01

Pos logit contributions
iless+0.774
igible+0.768
 checkpoints+0.738
idated+0.698
ulnerable+0.686
Neg logit contributions
wcs-0.912
Cra-0.883
yip-0.856
 ingred-0.820
hovah-0.816
Token will
Token ID481
Feature activation+6.13e-01

Pos logit contributions
wcs+0.653
Cra+0.632
yip+0.611
 ingred+0.589
kinson+0.586
Neg logit contributions
iless-0.499
igible-0.495
 checkpoints-0.474
idated-0.449
itimate-0.441
Token act
Token ID719
Feature activation+7.63e-01

Pos logit contributions
iless+0.408
igible+0.405
 checkpoints+0.390
idated+0.370
itimate+0.363
Neg logit contributions
wcs-0.459
Cra-0.444
yip-0.430
 ingred-0.411
hovah-0.409
Token as
Token ID355
Feature activation+2.59e+00

Pos logit contributions
iless+0.569
igible+0.565
 checkpoints+0.546
idated+0.520
ulnerable+0.512
Neg logit contributions
wcs-0.510
Cra-0.491
yip-0.475
 ingred-0.451
kinson-0.449
Token a
Token ID257
Feature activation-4.87e-01

Pos logit contributions
iless+1.541
igible+1.532
 checkpoints+1.490
idated+1.393
itimate+1.350
Neg logit contributions
wcs-2.103
Cra-2.038
yip-1.980
kinson-1.907
hovah-1.907
Token gateway
Token ID24308
Feature activation-1.36e+00

Pos logit contributions
wcs+0.382
Cra+0.371
yip+0.359
 ingred+0.345
kinson+0.342
Neg logit contributions
iless-0.307
igible-0.305
 checkpoints-0.291
idated-0.276
ulnerable-0.271
Token for
Token ID329
Feature activation-5.31e-01

Pos logit contributions
wcs+0.973
Cra+0.940
yip+0.902
 ingred+0.869
kinson+0.861
Neg logit contributions
iless-0.945
igible-0.938
 checkpoints-0.899
idated-0.861
ulnerable-0.846
TokenThis
Token ID1212
Feature activation+1.11e+00

Pos logit contributions
iless+0.245
igible+0.244
 checkpoints+0.236
idated+0.225
ulnerable+0.221
Neg logit contributions
wcs-0.222
Cra-0.214
yip-0.206
 ingred-0.196
kinson-0.195
Token is
Token ID318
Feature activation-6.06e-01

Pos logit contributions
iless+0.698
igible+0.693
 checkpoints+0.666
idated+0.627
itimate+0.616
Neg logit contributions
wcs-0.875
Cra-0.848
yip-0.823
 ingred-0.789
hovah-0.787
Token all
Token ID477
Feature activation-7.15e-01

Pos logit contributions
wcs+0.454
Cra+0.439
yip+0.424
 ingred+0.407
kinson+0.404
Neg logit contributions
iless-0.403
igible-0.399
 checkpoints-0.382
idated-0.365
ulnerable-0.358
Token going
Token ID1016
Feature activation-2.49e+00

Pos logit contributions
wcs+0.548
Cra+0.530
yip+0.513
 ingred+0.492
kinson+0.489
Neg logit contributions
iless-0.462
igible-0.457
 checkpoints-0.438
idated-0.419
ulnerable-0.409
Token to
Token ID284
Feature activation+1.64e-01

Pos logit contributions
wcs+1.787
Cra+1.715
yip+1.652
 ingred+1.586
kinson+1.576
Neg logit contributions
iless-1.727
igible-1.722
 checkpoints-1.659
idated-1.589
itimate-1.551
Token take
Token ID1011
Feature activation-6.52e-01

Pos logit contributions
iless+0.111
igible+0.110
 checkpoints+0.106
idated+0.101
itimate+0.099
Neg logit contributions
wcs-0.121
Cra-0.117
yip-0.114
 ingred-0.109
kinson-0.108
Token a
Token ID257
Feature activation+5.62e-01

Pos logit contributions
wcs+0.496
Cra+0.480
yip+0.465
 ingred+0.446
hovah+0.444
Neg logit contributions
iless-0.425
igible-0.423
 checkpoints-0.406
idated-0.385
ulnerable-0.377
Token number
Token ID1271
Feature activation+3.08e+00

Pos logit contributions
iless+0.382
igible+0.379
 checkpoints+0.365
idated+0.346
itimate+0.340
Neg logit contributions
wcs-0.413
Cra-0.400
yip-0.387
 ingred-0.370
hovah-0.368
Token of
Token ID286
Feature activation+2.53e+00

Pos logit contributions
iless+2.105
igible+2.080
 checkpoints+2.046
idated+1.891
í+1.876
Neg logit contributions
wcs-2.253
Cra-2.155
yip-2.113
hovah-2.065
 ingred-2.032
Token years
Token ID812
Feature activation-1.73e+00

Pos logit contributions
iless+1.566
igible+1.539
 checkpoints+1.528
itimate+1.365
idated+1.361
Neg logit contributions
wcs-2.026
Cra-1.959
yip-1.890
hovah-1.829
atos-1.822
Token.
Token ID13
Feature activation+1.30e+00

Pos logit contributions
wcs+1.201
Cra+1.153
yip+1.118
kinson+1.059
 ingred+1.059
Neg logit contributions
iless-1.237
igible-1.235
 checkpoints-1.187
idated-1.138
ulnerable-1.118
Tokenises
Token ID2696
Feature activation+5.16e-01

Pos logit contributions
iless+1.589
igible+1.583
 checkpoints+1.450
idated+1.339
ulnerable+1.296
Neg logit contributions
wcs-4.164
Cra-4.069
yip-3.985
 ingred-3.889
hovah-3.885
Token via
Token ID2884
Feature activation+2.22e+00

Pos logit contributions
iless+0.370
igible+0.367
 checkpoints+0.353
idated+0.338
itimate+0.332
Neg logit contributions
wcs-0.359
Cra-0.347
yip-0.334
 ingred-0.319
kinson-0.317
Token A
Token ID317
Feature activation-1.77e-01

Pos logit contributions
iless+1.451
igible+1.444
 checkpoints+1.393
idated+1.313
itimate+1.288
Neg logit contributions
wcs-1.688
Cra-1.628
yip-1.580
 ingred-1.513
hovah-1.509
Tokenq
Token ID80
Feature activation+4.67e-01

Pos logit contributions
wcs+0.131
Cra+0.127
yip+0.123
 ingred+0.117
hovah+0.117
Neg logit contributions
iless-0.119
igible-0.119
 checkpoints-0.114
idated-0.108
ulnerable-0.106
Tokenaba
Token ID15498
Feature activation+4.95e-01

Pos logit contributions
iless+0.388
igible+0.386
 checkpoints+0.374
idated+0.357
itimate+0.354
Neg logit contributions
wcs-0.273
Cra-0.260
yip-0.248
 ingred-0.239
hovah-0.237
Token,
Token ID11
Feature activation-6.56e-01

Pos logit contributions
iless+0.343
igible+0.341
 checkpoints+0.328
idated+0.311
ulnerable+0.306
Neg logit contributions
wcs-0.358
Cra-0.345
yip-0.334
 ingred-0.319
hovah-0.318
Token Jordan
Token ID8078
Feature activation+2.82e+00

Pos logit contributions
wcs+0.474
Cra+0.462
yip+0.445
 ingred+0.425
kinson+0.422
Neg logit contributions
iless-0.450
igible-0.445
 checkpoints-0.425
idated-0.408
ulnerable-0.401
Token,
Token ID11
Feature activation-1.10e+00

Pos logit contributions
iless+1.859
igible+1.834
 checkpoints+1.779
idated+1.660
ulnerable+1.641
Neg logit contributions
wcs-2.114
Cra-2.055
yip-1.989
 ingred-1.921
hovah-1.910
Token Port
Token ID4347
Feature activation-2.47e+00

Pos logit contributions
wcs+0.788
Cra+0.766
yip+0.737
 ingred+0.704
kinson+0.701
Neg logit contributions
iless-0.760
igible-0.753
 checkpoints-0.717
idated-0.690
ulnerable-0.678
Token Sok
Token ID37641
Feature activation+8.49e-01

Pos logit contributions
wcs+1.728
Cra+1.709
yip+1.623
atos+1.561
kinson+1.549
Neg logit contributions
iless-1.739
igible-1.713
 checkpoints-1.658
idated-1.568
itimate-1.555
Tokenh
Token ID71
Feature activation-2.14e+00

Pos logit contributions
iless+0.669
igible+0.663
 checkpoints+0.643
idated+0.615
itimate+0.605
Neg logit contributions
wcs-0.532
Cra-0.509
yip-0.490
 ingred-0.470
kinson-0.462
TokenTA
Token ID5603
Feature activation+1.31e+00

Pos logit contributions
wcs+1.289
Cra+1.252
yip+1.193
 ingred+1.149
atos+1.147
Neg logit contributions
iless-1.070
igible-1.059
 checkpoints-1.017
idated-0.967
itimate-0.953
Token 6
Token ID718
Feature activation+6.91e-01

Pos logit contributions
iless+0.984
igible+0.981
 checkpoints+0.947
idated+0.899
ulnerable+0.892
Neg logit contributions
wcs-0.866
Cra-0.833
yip-0.812
 ingred-0.773
kinson-0.768
Token Jac
Token ID8445
Feature activation+1.91e+00

Pos logit contributions
iless+0.445
igible+0.442
 checkpoints+0.423
idated+0.402
itimate+0.394
Neg logit contributions
wcs-0.530
Cra-0.517
yip-0.496
 ingred-0.476
kinson-0.476
Tokenop
Token ID404
Feature activation+1.32e+00

Pos logit contributions
iless+1.566
igible+1.559
 checkpoints+1.509
idated+1.444
itimate+1.422
Neg logit contributions
wcs-1.142
Cra-1.096
yip-1.047
kinson-0.989
hovah-0.988
Tokeno
Token ID78
Feature activation-4.92e-01

Pos logit contributions
iless+1.174
igible+1.160
 checkpoints+1.140
idated+1.112
í+1.105
Neg logit contributions
wcs-0.687
yip-0.670
Cra-0.646
hovah-0.589
 ingred-0.586
Token Gu
Token ID1962
Feature activation-7.73e-01

Pos logit contributions
wcs+0.380
Cra+0.372
yip+0.357
kinson+0.344
atos+0.342
Neg logit contributions
iless-0.312
igible-0.310
 checkpoints-0.296
idated-0.280
ulnerable-0.275
Tokenarn
Token ID1501
Feature activation-4.16e+00

Pos logit contributions
wcs+0.490
Cra+0.467
yip+0.461
atos+0.433
kinson+0.432
Neg logit contributions
iless-0.596
igible-0.592
 checkpoints-0.585
idated-0.549
itimate-0.540
Tokenieri
Token ID29864
Feature activation-1.94e+00

Pos logit contributions
wcs+2.017
Cra+1.926
yip+1.837
atos+1.831
kinson+1.750
Neg logit contributions
igible-3.803
iless-3.722
 checkpoints-3.632
idated-3.483
abeth-3.463
Token (
Token ID357
Feature activation-5.08e-01

Pos logit contributions
wcs+1.456
Cra+1.411
yip+1.353
 ingred+1.305
atos+1.299
Neg logit contributions
iless-1.286
igible-1.273
 checkpoints-1.226
idated-1.168
itimate-1.144
TokenAst
Token ID33751
Feature activation+4.94e+00

Pos logit contributions
wcs+0.313
Cra+0.311
yip+0.283
atos+0.275
kinson+0.272
Neg logit contributions
iless-0.405
igible-0.402
 checkpoints-0.389
idated-0.370
ulnerable-0.367
Tokenana
Token ID2271
Feature activation+1.88e+00

Pos logit contributions
iless+3.427
igible+3.337
 checkpoints+3.229
í+3.074
idated+3.020
Neg logit contributions
wcs-3.612
yip-3.426
Cra-3.386
hovah-3.338
 ingred-3.240
Token between
Token ID1022
Feature activation-8.01e-01

Pos logit contributions
iless+0.403
igible+0.400
 checkpoints+0.388
idated+0.366
ulnerable+0.361
Neg logit contributions
wcs-0.406
Cra-0.390
yip-0.378
 ingred-0.361
hovah-0.360
Token 10
Token ID838
Feature activation+3.83e+00

Pos logit contributions
wcs+0.583
Cra+0.566
yip+0.546
 ingred+0.522
kinson+0.520
Neg logit contributions
iless-0.546
igible-0.543
 checkpoints-0.520
idated-0.497
ulnerable-0.488
Token%
Token ID4
Feature activation-1.81e+00

Pos logit contributions
iless+2.374
igible+2.327
 checkpoints+2.264
idated+2.104
ulnerable+2.086
Neg logit contributions
wcs-3.037
Cra-2.917
yip-2.825
 ingred-2.735
hovah-2.716
Token and
Token ID290
Feature activation+8.57e-01

Pos logit contributions
wcs+1.259
Cra+1.218
yip+1.185
 ingred+1.118
hovah+1.116
Neg logit contributions
iless-1.292
igible-1.285
 checkpoints-1.239
idated-1.183
ulnerable-1.160
Token 30
Token ID1542
Feature activation+3.06e+00

Pos logit contributions
iless+0.654
igible+0.650
 checkpoints+0.628
idated+0.600
itimate+0.590
Neg logit contributions
wcs-0.558
Cra-0.537
yip-0.518
 ingred-0.491
hovah-0.489
Token%.
Token ID7225
Feature activation+3.26e-01

Pos logit contributions
iless+1.728
igible+1.702
 checkpoints+1.640
idated+1.520
ulnerable+1.497
Neg logit contributions
wcs-2.601
Cra-2.515
yip-2.447
 ingred-2.366
hovah-2.347
Token
Token ID198
Feature activation+1.01e+00

Pos logit contributions
iless+0.206
igible+0.204
 checkpoints+0.195
idated+0.185
itimate+0.181
Neg logit contributions
wcs-0.254
Cra-0.248
yip-0.239
 ingred-0.229
hovah-0.228
Token
Token ID198
Feature activation+1.02e+00

Pos logit contributions
iless+0.621
igible+0.616
 checkpoints+0.590
idated+0.556
itimate+0.546
Neg logit contributions
wcs-0.812
Cra-0.791
yip-0.761
kinson-0.731
atos-0.728
TokenThe
Token ID464
Feature activation-4.11e-01

Pos logit contributions
iless+0.776
igible+0.771
 checkpoints+0.745
idated+0.713
itimate+0.702
Neg logit contributions
wcs-0.659
Cra-0.630
yip-0.613
 ingred-0.583
hovah-0.581
Token cartel
Token ID34430
Feature activation-3.82e+00

Pos logit contributions
wcs+0.316
Cra+0.307
yip+0.296
 ingred+0.285
hovah+0.283
Neg logit contributions
iless-0.265
igible-0.263
 checkpoints-0.252
idated-0.239
itimate-0.234
Token operated
Token ID12228
Feature activation+1.04e+00

Pos logit contributions
wcs+2.648
Cra+2.611
yip+2.492
 ingred+2.406
atos+2.389
Neg logit contributions
igible-2.667
iless-2.639
 checkpoints-2.483
idated-2.420
ulnerable-2.389
Token one
Token ID530
Feature activation-7.75e-01

Pos logit contributions
wcs+0.841
Cra+0.818
yip+0.779
 ingred+0.753
kinson+0.743
Neg logit contributions
iless-0.860
igible-0.854
 checkpoints-0.811
idated-0.784
ulnerable-0.770
Token extra
Token ID3131
Feature activation-3.57e-02

Pos logit contributions
wcs+0.576
Cra+0.560
yip+0.535
 ingred+0.518
kinson+0.510
Neg logit contributions
iless-0.521
igible-0.513
 checkpoints-0.494
idated-0.469
ulnerable-0.461
Token submarine
Token ID24927
Feature activation+5.70e-01

Pos logit contributions
wcs+0.027
Cra+0.026
yip+0.025
 ingred+0.025
kinson+0.024
Neg logit contributions
iless-0.023
igible-0.023
 checkpoints-0.022
idated-0.021
ulnerable-0.021
Token annually
Token ID13844
Feature activation+1.43e+00

Pos logit contributions
iless+0.406
igible+0.402
 checkpoints+0.389
idated+0.369
itimate+0.364
Neg logit contributions
wcs-0.400
Cra-0.386
yip-0.373
 ingred-0.356
kinson-0.354
Token.
Token ID13
Feature activation-3.25e-01

Pos logit contributions
iless+1.012
igible+1.007
 checkpoints+0.970
idated+0.921
itimate+0.905
Neg logit contributions
wcs-1.011
Cra-0.979
yip-0.949
hovah-0.904
 ingred-0.904
Token If
Token ID1002
Feature activation-7.69e+00

Pos logit contributions
wcs+0.245
Cra+0.241
yip+0.229
atos+0.220
kinson+0.220
Neg logit contributions
iless-0.214
igible-0.211
 checkpoints-0.202
idated-0.191
itimate-0.189
Token the
Token ID262
Feature activation+2.02e-01

Pos logit contributions
wcs+5.023
Cra+4.861
yip+4.586
 ingred+4.461
kinson+4.443
Neg logit contributions
iless-5.551
igible-5.450
 checkpoints-5.036
ulnerable-4.956
idated-4.917
Token GOP
Token ID6796
Feature activation-1.44e-01

Pos logit contributions
iless+0.136
igible+0.135
 checkpoints+0.129
idated+0.123
ulnerable+0.121
Neg logit contributions
wcs-0.150
Cra-0.145
yip-0.140
 ingred-0.134
kinson-0.134
Token is
Token ID318
Feature activation-5.09e-01

Pos logit contributions
wcs+0.104
Cra+0.101
yip+0.097
 ingred+0.093
kinson+0.093
Neg logit contributions
iless-0.099
igible-0.098
 checkpoints-0.094
idated-0.090
ulnerable-0.088
Token willing
Token ID4684
Feature activation-1.69e+00

Pos logit contributions
wcs+0.407
Cra+0.394
yip+0.380
 ingred+0.367
kinson+0.365
Neg logit contributions
iless-0.313
igible-0.311
 checkpoints-0.297
idated-0.280
itimate-0.275
Token to
Token ID284
Feature activation-7.43e-01

Pos logit contributions
wcs+1.211
Cra+1.171
yip+1.131
 ingred+1.081
hovah+1.079
Neg logit contributions
iless-1.168
igible-1.162
 checkpoints-1.117
idated-1.065
ulnerable-1.043
Token the
Token ID262
Feature activation-9.36e-01

Pos logit contributions
wcs+2.203
Cra+2.128
yip+2.060
 ingred+1.978
kinson+1.973
Neg logit contributions
iless-1.930
igible-1.900
 checkpoints-1.800
idated-1.751
ulnerable-1.704
Token Prime
Token ID5537
Feature activation-9.19e-01

Pos logit contributions
wcs+0.675
Cra+0.652
yip+0.630
 ingred+0.602
hovah+0.599
Neg logit contributions
iless-0.648
igible-0.644
 checkpoints-0.620
idated-0.589
itimate-0.579
Token Minister
Token ID4139
Feature activation-2.32e-01

Pos logit contributions
wcs+0.798
Cra+0.775
yip+0.754
 ingred+0.728
hovah+0.726
Neg logit contributions
iless-0.501
igible-0.498
 checkpoints-0.475
idated-0.443
ulnerable-0.434
Token and
Token ID290
Feature activation+2.12e-01

Pos logit contributions
wcs+0.161
Cra+0.156
yip+0.151
 ingred+0.144
hovah+0.143
Neg logit contributions
iless-0.167
igible-0.166
 checkpoints-0.160
idated-0.152
itimate-0.150
Token,
Token ID11
Feature activation-2.79e+00

Pos logit contributions
iless+0.140
igible+0.139
 checkpoints+0.134
idated+0.127
ulnerable+0.124
Neg logit contributions
wcs-0.160
Cra-0.154
yip-0.150
 ingred-0.143
kinson-0.142
Token if
Token ID611
Feature activation-7.61e+00

Pos logit contributions
wcs+1.909
Cra+1.825
yip+1.773
kinson+1.676
 ingred+1.672
Neg logit contributions
iless-2.016
igible-2.000
 checkpoints-1.918
idated-1.848
itimate-1.814
Token necessary
Token ID3306
Feature activation+2.98e+00

Pos logit contributions
wcs+5.103
Cra+4.756
yip+4.721
 ante+4.530
 ingred+4.448
Neg logit contributions
iless-5.419
igible-5.209
 checkpoints-4.969
idated-4.883
ulnerable-4.816
Token,
Token ID11
Feature activation-2.85e-01

Pos logit contributions
iless+1.803
igible+1.799
 checkpoints+1.716
idated+1.612
itimate+1.591
Neg logit contributions
wcs-2.383
Cra-2.347
yip-2.263
hovah-2.176
kinson-2.171
Token dismiss
Token ID6735
Feature activation+1.14e+00

Pos logit contributions
wcs+0.211
Cra+0.204
yip+0.198
 ingred+0.190
kinson+0.189
Neg logit contributions
iless-0.192
igible-0.190
 checkpoints-0.182
idated-0.174
ulnerable-0.170
Token one
Token ID530
Feature activation+5.46e-01

Pos logit contributions
iless+0.715
igible+0.714
 checkpoints+0.684
idated+0.644
itimate+0.635
Neg logit contributions
wcs-0.891
Cra-0.864
yip-0.835
 ingred-0.805
hovah-0.801
Token that
Token ID326
Feature activation+1.28e+00

Pos logit contributions
iless+0.349
igible+0.349
 checkpoints+0.334
idated+0.315
itimate+0.311
Neg logit contributions
wcs-0.422
Cra-0.410
yip-0.397
 ingred-0.381
hovah-0.380
Token and
Token ID290
Feature activation-2.08e+00

Pos logit contributions
wcs+3.696
Cra+3.590
yip+3.447
 ingred+3.343
waters+3.299
Neg logit contributions
iless-3.566
igible-3.536
 checkpoints-3.289
idated-3.244
abeth-3.142
Token non
Token ID1729
Feature activation-6.28e-02

Pos logit contributions
wcs+1.547
Cra+1.484
yip+1.444
 ingred+1.391
kinson+1.375
Neg logit contributions
igible-1.387
iless-1.386
 checkpoints-1.326
idated-1.265
itimate-1.233
Token-
Token ID12
Feature activation+3.72e+00

Pos logit contributions
wcs+0.046
Cra+0.044
yip+0.043
 ingred+0.041
hovah+0.041
Neg logit contributions
iless-0.043
igible-0.043
 checkpoints-0.041
idated-0.039
itimate-0.038
Tokenin
Token ID259
Feature activation+5.32e-01

Pos logit contributions
iless+3.115
igible+3.105
 checkpoints+2.962
í+2.893
ulnerable+2.890
Neg logit contributions
wcs-2.075
Cra-1.982
yip-1.879
 ingred-1.847
hovah-1.831
Tokenvasive
Token ID23747
Feature activation+1.47e+00

Pos logit contributions
iless+0.335
igible+0.333
 checkpoints+0.317
idated+0.301
ulnerable+0.297
Neg logit contributions
wcs-0.417
Cra-0.406
yip-0.393
 ingred-0.378
hovah-0.377
Token insects
Token ID19435
Feature activation-7.36e+00

Pos logit contributions
iless+1.040
igible+1.032
 checkpoints+1.008
idated+0.946
ulnerable+0.937
Neg logit contributions
wcs-1.036
Cra-1.000
yip-0.970
hovah-0.928
 ingred-0.919
Token.
Token ID13
Feature activation-1.55e-01

Pos logit contributions
wcs+5.259
Cra+4.955
yip+4.660
kinson+4.624
atos+4.612
Neg logit contributions
igible-4.911
iless-4.866
 checkpoints-4.583
idated-4.423
itimate-4.371
Token The
Token ID383
Feature activation-4.18e-01

Pos logit contributions
wcs+0.118
Cra+0.114
yip+0.110
kinson+0.105
 ingred+0.105
Neg logit contributions
iless-0.102
igible-0.101
 checkpoints-0.097
idated-0.092
itimate-0.090
Token desire
Token ID6227
Feature activation-1.40e+00

Pos logit contributions
wcs+0.311
Cra+0.300
yip+0.290
 ingred+0.279
kinson+0.276
Neg logit contributions
iless-0.280
igible-0.278
 checkpoints-0.266
idated-0.253
itimate-0.249
Token for
Token ID329
Feature activation-9.62e-01

Pos logit contributions
wcs+0.981
Cra+0.944
yip+0.912
 ingred+0.869
kinson+0.869
Neg logit contributions
iless-0.992
igible-0.984
 checkpoints-0.949
idated-0.903
ulnerable-0.890
Token foreign
Token ID3215
Feature activation-4.59e+00

Pos logit contributions
wcs+0.716
Cra+0.690
yip+0.671
 ingred+0.644
atos+0.638
Neg logit contributions
iless-0.645
igible-0.639
 checkpoints-0.603
idated-0.583
itimate-0.568
Token ready
Token ID3492
Feature activation-1.76e+00

Pos logit contributions
iless+0.766
igible+0.761
 checkpoints+0.731
idated+0.691
ulnerable+0.678
Neg logit contributions
wcs-0.920
Cra-0.891
yip-0.864
 ingred-0.827
hovah-0.824
Token to
Token ID284
Feature activation-2.25e+00

Pos logit contributions
wcs+1.225
Cra+1.176
yip+1.136
 ingred+1.088
kinson+1.084
Neg logit contributions
iless-1.251
igible-1.251
 checkpoints-1.207
idated-1.154
itimate-1.133
Token go
Token ID467
Feature activation-1.86e+00

Pos logit contributions
wcs+1.700
Cra+1.630
yip+1.592
atos+1.548
 ingred+1.538
Neg logit contributions
iless-1.437
igible-1.421
 checkpoints-1.354
idated-1.328
itimate-1.275
Token,
Token ID11
Feature activation+9.61e-01

Pos logit contributions
wcs+1.212
Cra+1.158
yip+1.116
atos+1.061
kinson+1.061
Neg logit contributions
iless-1.398
igible-1.396
 checkpoints-1.339
idated-1.304
itimate-1.272
Token but
Token ID475
Feature activation-6.27e-01

Pos logit contributions
iless+0.700
igible+0.695
 checkpoints+0.670
idated+0.640
ulnerable+0.629
Neg logit contributions
wcs-0.657
Cra-0.634
yip-0.612
 ingred-0.583
kinson-0.580
Token then
Token ID788
Feature activation-5.01e+00

Pos logit contributions
wcs+0.462
Cra+0.450
yip+0.434
 ingred+0.418
kinson+0.415
Neg logit contributions
iless-0.418
igible-0.416
 checkpoints-0.394
idated-0.381
ulnerable-0.373
Token why
Token ID1521
Feature activation-1.61e+00

Pos logit contributions
wcs+3.366
Cra+3.315
yip+3.169
 ingred+3.088
atos+3.081
Neg logit contributions
igible-3.499
iless-3.478
 checkpoints-3.240
idated-3.214
ulnerable-3.144
Token is
Token ID318
Feature activation-9.78e-01

Pos logit contributions
wcs+1.159
Cra+1.130
yip+1.077
 ingred+1.049
atos+1.041
Neg logit contributions
igible-1.100
iless-1.098
 checkpoints-1.033
idated-1.001
ulnerable-0.982
Token nothing
Token ID2147
Feature activation-2.21e+00

Pos logit contributions
wcs+0.760
Cra+0.742
yip+0.711
 ingred+0.690
atos+0.685
Neg logit contributions
iless-0.620
igible-0.614
 checkpoints-0.577
idated-0.554
ulnerable-0.543
Token happening
Token ID5836
Feature activation+1.59e+00

Pos logit contributions
wcs+1.418
Cra+1.357
yip+1.282
 ingred+1.251
atos+1.228
Neg logit contributions
iless-1.697
igible-1.686
 checkpoints-1.600
idated-1.553
ulnerable-1.530
Token?
Token ID30
Feature activation+3.25e+00

Pos logit contributions
iless+0.994
igible+0.986
 checkpoints+0.948
idated+0.892
itimate+0.876
Neg logit contributions
wcs-1.247
Cra-1.209
yip-1.174
 ingred-1.125
hovah-1.124
Token exited
Token ID34710
Feature activation-2.45e+00

Pos logit contributions
wcs+1.865
Cra+1.782
yip+1.684
atos+1.643
kinson+1.624
Neg logit contributions
igible-2.077
iless-2.065
 checkpoints-1.964
idated-1.908
ulnerable-1.886
Token his
Token ID465
Feature activation-2.23e+00

Pos logit contributions
wcs+1.751
Cra+1.706
yip+1.625
 ingred+1.565
atos+1.562
Neg logit contributions
igible-1.686
iless-1.681
 checkpoints-1.600
idated-1.533
ulnerable-1.514
Token vehicle
Token ID4038
Feature activation-6.48e-01

Pos logit contributions
wcs+1.710
Cra+1.669
yip+1.593
 ingred+1.549
atos+1.538
Neg logit contributions
iless-1.431
igible-1.417
 checkpoints-1.345
idated-1.279
ulnerable-1.263
Token and
Token ID290
Feature activation+5.65e-01

Pos logit contributions
wcs+0.455
Cra+0.439
yip+0.425
 ingred+0.405
hovah+0.403
Neg logit contributions
iless-0.461
igible-0.458
 checkpoints-0.442
idated-0.420
ulnerable-0.413
Token observed
Token ID6515
Feature activation-2.41e+00

Pos logit contributions
iless+0.394
igible+0.392
 checkpoints+0.377
idated+0.359
itimate+0.352
Neg logit contributions
wcs-0.404
Cra-0.390
yip-0.377
 ingred-0.360
hovah-0.359
Token another
Token ID1194
Feature activation-5.54e+00

Pos logit contributions
wcs+1.716
Cra+1.683
yip+1.611
 ingred+1.547
kinson+1.542
Neg logit contributions
iless-1.656
igible-1.651
 checkpoints-1.557
idated-1.515
ulnerable-1.486
Token vehicle
Token ID4038
Feature activation-9.69e-01

Pos logit contributions
wcs+3.801
Cra+3.749
yip+3.501
atos+3.431
 ingred+3.414
Neg logit contributions
iless-3.886
igible-3.813
 checkpoints-3.622
idated-3.527
ulnerable-3.458
Token adjacent
Token ID15909
Feature activation-7.44e-01

Pos logit contributions
wcs+0.704
Cra+0.680
yip+0.659
 ingred+0.629
hovah+0.628
Neg logit contributions
iless-0.667
igible-0.663
 checkpoints-0.640
idated-0.605
ulnerable-0.595
Token to
Token ID284
Feature activation-9.82e-02

Pos logit contributions
wcs+0.542
Cra+0.524
yip+0.508
 ingred+0.485
hovah+0.483
Neg logit contributions
iless-0.510
igible-0.506
 checkpoints-0.489
idated-0.463
itimate-0.455
Token his
Token ID465
Feature activation-1.59e+00

Pos logit contributions
wcs+0.071
Cra+0.069
yip+0.066
 ingred+0.063
kinson+0.063
Neg logit contributions
iless-0.068
igible-0.067
 checkpoints-0.065
idated-0.061
ulnerable-0.060
Token own
Token ID898
Feature activation-4.57e-01

Pos logit contributions
wcs+1.145
Cra+1.108
yip+1.068
 ingred+1.023
kinson+1.017
Neg logit contributions
iless-1.105
igible-1.098
 checkpoints-1.054
idated-1.003
ulnerable-0.986