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

    Neuronpedia

    INDEX
    Explanations

    bracketed numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [~,
    -0.17
    [
    -0.16
    alie
    -0.15
    ourse
    -0.15
    ¡
    -0.15
     CircularProgress
    -0.14
    andle
    -0.14
    æ¯Ĵ
    -0.14
     Amnesty
    -0.13
    datatable
    -0.13
    POSITIVE LOGITS
    ÐIJÑĢÑħÑĸвовано
    0.33
    +]
    0.23
    ?]
    0.21
    !]
    0.21
    sic
    0.18
    .]
    0.17
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    0.17
    UIFont
    0.17
     sic
    0.16
    .]↵↵
    0.16
    Act Density 0.033%

    No Known Activations