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

    Neuronpedia

    INDEX
    Explanations

    file paths within a Unix directory structure

    oai_token-act-pair · gpt-3.5-turbo

    file paths and system directories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phal
    -0.63
     plural
    -0.61
     Halls
    -0.61
     Kah
    -0.60
     Ãľ
    -0.60
     Tao
    -0.60
    sole
    -0.59
     flank
    -0.59
     Garfield
    -0.59
     Kur
    -0.58
    POSITIVE LOGITS
    ilogy
    0.87
    racuse
    0.87
     certs
    0.83
    etheless
    0.83
    alg
    0.82
    urable
    0.82
    wcsstore
    0.80
    config
    0.79
    ecd
    0.77
    cdn
    0.77
    Act Density 0.010%

    No Known Activations