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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negation and absence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culosis
    -0.73
    alion
    -0.68
    icism
    -0.68
    erity
    -0.59
    bara
    -0.58
    CRE
    -0.58
    issance
    -0.58
    fty
    -0.56
     Royale
    -0.56
    EMA
    -0.56
    POSITIVE LOGITS
    abouts
    0.78
     themselves
    0.77
    types
    0.73
     expressions
    0.69
     extensions
    0.69
     embodiments
    0.68
     selves
    0.68
     interchangeable
    0.66
     mouths
    0.65
    products
    0.65
    Act Density 0.791%

    No Known Activations