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

    Neuronpedia

    INDEX
    Explanations

    statements involving political figures and activities

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to legality and moral implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anges
    -0.56
    WHERE
    -0.53
    é¾į
    -0.51
    Ĥª
    -0.50
    vironments
    -0.49
    Ùĩ
    -0.48
    UTC
    -0.48
    venth
    -0.48
    PUT
    -0.46
    antage
    -0.44
    POSITIVE LOGITS
     or
    2.16
     nor
    1.56
     Or
    1.46
     OR
    1.43
    Or
    1.38
    or
    1.22
    nor
    1.04
     Alternatively
    0.95
     either
    0.90
    Either
    0.89
    Act Density 2.776%

    No Known Activations