INDEX
Explanations
specific names of individuals and their associated actions or roles, potentially in the context of quotes or articles
references to noteworthy individuals and their opinions or writings
New Auto-Interp
Negative Logits
wives
-0.68
customs
-0.66
cream
-0.63
btn
-0.62
CONC
-0.62
window
-0.61
patient
-0.61
outward
-0.59
FACE
-0.59
ctrl
-0.58
POSITIVE LOGITS
Slate
1.06
blogs
0.89
blog
0.88
insightful
0.86
blogs
0.85
NYT
0.83
Salon
0.83
aptly
0.83
Wired
0.79
column
0.77
Activations Density 0.443%