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

    Neuronpedia

    INDEX
    Explanations

    proper names mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cory."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     discriminating
    -0.67
    slave
    -0.66
     withholding
    -0.65
     rehab
    -0.64
    ा
    -0.64
     supervised
    -0.64
     vested
    -0.63
     confisc
    -0.63
     servicing
    -0.63
     discipl
    -0.61
    POSITIVE LOGITS
     Cory
    1.12
    pheus
    0.97
    caster
    0.90
    mons
    0.88
     Gardner
    0.80
    zon
    0.79
     Ort
    0.78
    casters
    0.78
     Briggs
    0.77
    nan
    0.77
    Act Density 0.006%

    No Known Activations