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

    Neuronpedia

    INDEX
    Explanations

    references to historical or cultural criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.78
    ,
    -0.77
     to
    -0.76
     in
    -0.76
     for
    -0.70
     of
    -0.69
     he
    -0.69
     im
    -0.66
     i
    -0.64
     with
    -0.63
    POSITIVE LOGITS
    ########.
    0.95
    RegistryLite
    0.94
    setVerticalGroup
    0.92
    __':
    0.91
    )':
    0.91
    Tikang
    0.91
     autorytatywna
    0.91
    quelize
    0.89
    ')):
    0.87
     للاسماء
    0.86
    Act Density 0.206%

    No Known Activations