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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rica
    -0.68
     Rican
    -0.63
    redo
    -0.63
     Rico
    -0.59
    rost
    -0.59
    inosaur
    -0.58
     Haz
    -0.58
    ucha
    -0.56
     warranted
    -0.56
    OPLE
    -0.54
    POSITIVE LOGITS
    essage
    1.06
    achus
    0.98
    mble
    0.93
    ãģĨ
    0.89
    ophon
    0.88
    achine
    0.88
    useum
    0.87
    giving
    0.87
    eter
    0.86
    ichael
    0.85
    Act Density 0.059%

    No Known Activations