INDEX
Explanations
terms related to therapy and patient care in the context of addiction and mental health
New Auto-Interp
Negative Logits
.",
-0.70
.")
-0.68
++
-0.66
TestingModule
-0.56
AddHtmlAttribute
-0.53
تانيه
-0.53
!")
-0.52
__':
-0.51
`
-0.49
$",
-0.49
POSITIVE LOGITS
;
1.88
?;
1.39
);
1.32
';
1.32
;
1.31
;
1.30
%;
1.30
؛
1.27
$;
1.26
»;
1.26
Activations Density 0.540%