INDEX
Explanations
mentions of the word "cast" at various activation strengths
occurrences of the word "cast" in various contexts
New Auto-Interp
Negative Logits
aternal
-0.71
inflamm
-0.71
ansom
-0.70
aceous
-0.69
vironment
-0.67
psychiat
-0.67
uese
-0.66
Downloadha
-0.66
iped
-0.64
ujah
-0.64
POSITIVE LOGITS
casting
0.91
eer
0.82
casters
0.81
rons
0.78
aways
0.76
leton
0.76
icut
0.75
osterone
0.75
CAST
0.74
dar
0.73
Activations Density 0.012%