INDEX
Explanations
instances of the word "crack"
occurrences of the word "crack" in various contexts
New Auto-Interp
Negative Logits
ikk
-0.80
Leth
-0.71
Jinn
-0.65
Pwr
-0.63
folk
-0.62
Fenrir
-0.61
dracon
-0.61
DK
-0.59
attention
-0.59
isted
-0.58
POSITIVE LOGITS
pots
1.17
Berry
1.02
ible
0.93
lings
0.89
pot
0.88
ibly
0.86
cracking
0.81
cocaine
0.81
ling
0.77
breakers
0.77
Activations Density 0.015%