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

    Neuronpedia

    INDEX
    Explanations

    phrases describing concepts or qualities

    oai_token-act-pair · gpt-3.5-turbo

    words associated with relationships, characterizations, and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Notting
    -0.77
     Ryder
    -0.68
    "},"
    -0.67
    avier
    -0.64
    ergic
    -0.64
    ochond
    -0.64
    burgh
    -0.63
    jay
    -0.62
     Normandy
    -0.62
    ixels
    -0.62
    POSITIVE LOGITS
    tesy
    0.89
    ¥ŀ
    0.80
    ¿½
    0.77
    itaire
    0.77
    tained
    0.76
    tains
    0.75
    itiz
    0.73
    itled
    0.71
     sus
    0.71
     citiz
    0.71
    Act Density 0.279%

    No Known Activations