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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual or their relative frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.68
     curfew
    -0.67
     flourish
    -0.63
    YC
    -0.63
    iculty
    -0.62
     Lovecraft
    -0.62
    ļéĨĴ
    -0.61
     frig
    -0.61
    ãģį
    -0.60
     Dangerous
    -0.59
    POSITIVE LOGITS
    kees
    1.18
    wark
    0.99
    andon
    0.99
    oda
    0.96
    ashtra
    0.96
    ril
    0.95
    pling
    0.94
    ban
    0.94
    izon
    0.94
    aya
    0.93
    Act Density 0.017%

    No Known Activations