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

    Neuronpedia

    INDEX
    Explanations

    references to quantities or measures

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities and measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    helm
    -0.83
    arna
    -0.82
    INA
    -0.79
    inka
    -0.74
    warts
    -0.72
    ̶
    -0.69
    Blade
    -0.68
    NetMessage
    -0.67
    OTA
    -0.67
    ilver
    -0.67
    POSITIVE LOGITS
     amount
    0.87
     allowable
    0.85
    liest
    0.82
     closest
    0.75
     equivalent
    0.73
     number
    0.72
     extent
    0.72
     amounts
    0.68
     difference
    0.68
     of
    0.67
    Act Density 0.208%

    No Known Activations