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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    pronouns related to individuals and entities in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ));
    -0.67
    izo
    -0.63
     )))
    -0.63
     Zoro
    -0.62
    CVE
    -0.61
    oké
    -0.60
     lasting
    -0.60
     ())
    -0.59
     ))
    -0.58
     Weston
    -0.57
    POSITIVE LOGITS
    foundland
    0.86
    %"
    0.79
     nomine
    0.78
    pherd
    0.77
    heid
    0.75
    ablishment
    0.75
    anmar
    0.74
    chwitz
    0.73
    estine
    0.72
    anamo
    0.72
    Act Density 0.272%

    No Known Activations