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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or specific people

    oai_token-act-pair · gpt-3.5-turbo

    specific classifications or categories related to artistic works or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.73
    unic
    -0.67
    pora
    -0.67
     havens
    -0.63
    pees
    -0.63
     quar
    -0.62
     err
    -0.62
     balloons
    -0.59
     colonies
    -0.59
     surg
    -0.59
    POSITIVE LOGITS
    illin
    0.75
     Centauri
    0.72
    iddled
    0.63
    phe
    0.62
    ript
    0.61
    lehem
    0.60
     Baghd
    0.60
    å§
    0.60
    lamm
    0.59
    ת
    0.59
    Act Density 0.259%

    No Known Activations