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

    Neuronpedia

    INDEX
    Explanations

    and emphasize specific names of people or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.71
    eers
    -0.69
    creen
    -0.68
     cov
    -0.67
    eq
    -0.66
    eas
    -0.64
     Fraz
    -0.61
     Clover
    -0.60
     rise
    -0.60
     Gent
    -0.59
    POSITIVE LOGITS
    abbit
    1.33
    acing
    1.22
    ussia
    1.18
    ifle
    1.16
    uder
    1.12
    angers
    1.12
    outine
    1.12
    aceutical
    1.09
    agnar
    1.09
    ansom
    1.06
    Act Density 0.084%

    No Known Activations