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

    Neuronpedia

    INDEX
    Explanations

    titles or mentions of individuals holding temporary roles or positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to acting roles or positions in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.80
    nda
    -0.71
    joy
    -0.70
    sbm
    -0.67
    pled
    -0.66
    ppa
    -0.65
     Plate
    -0.64
    front
    -0.62
    uckle
    -0.61
    roe
    -0.61
    POSITIVE LOGITS
    uary
    0.97
    uate
    0.86
    uated
    0.81
    ional
    0.77
    uations
    0.76
     prov
    0.75
    Director
    0.72
    uating
    0.70
    icter
    0.69
     director
    0.68
    Act Density 0.017%

    No Known Activations