Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the presence of structured formats or categories in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    — 
    -0.47
    خواندن
    -0.45
     free
    -0.44
     درا
    -0.42
    ienda
    -0.42
    AGE
    -0.41
     
    -0.40
    ESAR
    -0.39
     Free
    -0.39
    bilt
    -0.39
    POSITIVE LOGITS
    #+#
    1.06
    ########.
    0.98
     مرئيه
    0.98
    脚注の使い方
    0.90
     للاسماء
    0.85
     nahilalakip
    0.85
     StatelessWidget
    0.83
    :+:
    0.81
    rungsseite
    0.79
    发表于
    0.79
    Act Density 0.231%

    No Known Activations