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

    Neuronpedia

    INDEX
    Explanations

    some specific technical terms and commands related to programming

    oai_token-act-pair · gpt-3.5-turbo

    file types and programming-related syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patron
    -0.83
     Disorder
    -0.83
     Flavoring
    -0.81
     Referred
    -0.79
     Cous
    -0.79
     Fas
    -0.78
     Aires
    -0.77
     Dise
    -0.77
     Leban
    -0.76
     Seasons
    -0.75
    POSITIVE LOGITS
    ascript
    1.04
    pd
    1.02
    cs
    0.96
    cd
    0.95
    df
    0.92
    wd
    0.91
    drm
    0.91
    rc
    0.91
    admin
    0.89
    ml
    0.88
    Act Density 0.125%

    No Known Activations