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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases, especially involving the word "if."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     doubtnut
    -0.98
    rungsseite
    -0.96
     ―――――
    -0.96
    Autoritní
    -0.95
    contentLoaded
    -0.91
    >--}}
    -0.90
     */
    -0.88
     ویکی‌پدیای
    -0.88
     nahilalakip
    -0.86
    ."</
    -0.86
    POSITIVE LOGITS
     T
    0.58
     B
    0.57
     The
    0.56
     L
    0.55
     N
    0.55
     m
    0.50
     C
    0.50
     Y
    0.50
    <h2>
    0.49
     n
    0.49
    Act Density 0.014%

    No Known Activations