INDEX
Explanations
phrases related to breaking or cracking something
instances of the word "crack" in various contexts
New Auto-Interp
Negative Logits
ikk
-0.81
Pwr
-0.73
folk
-0.68
Leth
-0.66
Fenrir
-0.65
Jinn
-0.63
attention
-0.62
amins
-0.60
anamo
-0.59
Dayton
-0.59
POSITIVE LOGITS
pots
1.21
Berry
1.00
pot
0.92
ible
0.89
lings
0.89
cracking
0.81
ling
0.81
cocaine
0.79
ibly
0.78
ework
0.78
Activations Density 0.020%