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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, presumably related to a news story or article

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auga
    -0.85
    orsi
    -0.69
     curfew
    -0.68
    ĪĴ
    -0.67
    OPS
    -0.67
    angular
    -0.64
     Pixie
    -0.64
     Venezuelan
    -0.63
     Inquisition
    -0.60
    FUL
    -0.60
    POSITIVE LOGITS
    stein
    1.49
    feld
    1.46
    bard
    1.37
    baum
    1.36
    berg
    1.28
    wald
    1.19
    bach
    1.16
    enthal
    1.13
    heimer
    1.13
    berger
    1.09
    Act Density 0.114%

    No Known Activations