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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating formal processes or roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.86
    ";
    -0.64
    ".
    -0.63
    emp
    -0.60
    "...
    -0.59
     ende
    -0.59
    idepress
    -0.59
    hetto
    -0.59
     ".
    -0.58
     Deity
    -0.58
    POSITIVE LOGITS
    actionDate
    0.91
    +)
    0.78
    -)
    0.74
    LV
    0.67
    )'
    0.65
    )=
    0.64
    esides
    0.61
    )\
    0.59
     oldest
    0.57
     newcomer
    0.57
    Act Density 0.763%

    No Known Activations