INDEX
Explanations
occurrences of the word "you" and similar personal pronouns
New Auto-Interp
Negative Logits
aminer
-0.16
uro
-0.15
å¶
-0.15
alah
-0.15
urs
-0.14
aho
-0.14
-UA
-0.14
êm
-0.14
áh
-0.14
Snowden
-0.14
POSITIVE LOGITS
ctica
0.16
Äĥng
0.16
HeaderText
0.15
adox
0.15
åĨ
0.14
Ging
0.14
ordinates
0.14
sik
0.14
oj
0.14
etur
0.13
Activations Density 0.006%