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

    Neuronpedia

    INDEX
    Explanations

    names of individuals of interest

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    agements
    -0.74
    aries
    -0.73
    agers
    -0.73
    ostic
    -0.72
    ishes
    -0.67
    rd
    -0.66
    amins
    -0.65
    ests
    -0.65
    ish
    -0.65
    aging
    -0.64
    POSITIVE LOGITS
    llular
    1.10
    idon
    0.95
    llor
    0.95
    lyn
    0.90
    llan
    0.87
    lla
    0.85
    ptives
    0.80
    vich
    0.80
    lli
    0.79
    flight
    0.76
    Act Density 0.045%

    No Known Activations