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

    Neuronpedia

    INDEX
    Explanations

    year ranges or specific years indicated in parentheses

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     retard
    -0.81
     entitle
    -0.72
    emonic
    -0.70
     wre
    -0.66
     hazards
    -0.66
     incarn
    -0.65
     everyday
    -0.65
     spatial
    -0.65
     tenants
    -0.64
     rog
    -0.64
    POSITIVE LOGITS
    formerly
    1.44
    which
    1.42
    whose
    1.38
    who
    1.34
    although
    1.29
    where
    1.29
    pictured
    1.27
    excluding
    1.19
    via
    1.18
    albeit
    1.16
    Act Density 0.147%

    No Known Activations