INDEX
Explanations
references to a specific person named Adam
the name "Adam" in various contexts
New Auto-Interp
Negative Logits
awaru
-0.85
ngth
-0.82
href
-0.79
wrapper
-0.75
umblr
-0.71
olulu
-0.70
luster
-0.70
liquids
-0.70
mediated
-0.68
heed
-0.67
POSITIVE LOGITS
antine
1.00
Warlock
0.87
son
0.85
Clayton
0.82
Curtis
0.81
urai
0.79
Smith
0.78
Adam
0.77
aum
0.76
Sachs
0.74
Activations Density 0.014%