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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "thumb"

    oai_token-act-pair · gpt-3.5-turbo

    references to "thumb" and related expressions indicating approval or disapproval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kell
    -0.77
    ption
    -0.73
     Scotia
    -0.73
    acle
    -0.71
    rera
    -0.68
    abella
    -0.68
    ologne
    -0.67
    Story
    -0.65
     Yards
    -0.65
    ulkan
    -0.64
    POSITIVE LOGITS
    \\\\\\\\
    0.86
    eenth
    0.81
    ington
    0.73
    sticks
    0.70
    etsk
    0.70
    esome
    0.69
    enance
    0.68
    wings
    0.66
     nomine
    0.66
    shire
    0.66
    Act Density 0.101%

    No Known Activations