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

    Neuronpedia

    INDEX
    Explanations

    references to previous studies or findings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    awtextra
    -0.82
    httphttps
    -0.80
    SourceChecksum
    -0.76
    脚注の使い方
    -0.74
     Exacts
    -0.73
    __":
    -0.72
     kaarangay
    -0.71
    COUVER
    -0.71
    Hentet
    -0.68
    Geplaatst
    -0.68
    POSITIVE LOGITS
     or
    0.47
     is
    0.46
     personal
    0.43
    useEffect
    0.41
    ேர
    0.39
     family
    0.39
    GeneratedValue
    0.39
     vendre
    0.39
     that
    0.39
    面目
    0.39
    Act Density 0.015%

    No Known Activations