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

    Neuronpedia

    INDEX
    Explanations

    references to privacy policies and related privacy terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mor
    -0.19
    nder
    -0.16
    orman
    -0.16
    ÙĪØ·
    -0.15
    íĴĪ
    -0.15
    loff
    -0.15
    æĿIJ
    -0.15
    tra
    -0.15
    isters
    -0.15
    ora
    -0.14
    POSITIVE LOGITS
    -sector
    0.17
    angel
    0.16
    /conf
    0.16
    /public
    0.16
    -conscious
    0.15
    krom
    0.15
    uits
    0.15
    ARY
    0.15
    carousel
    0.14
    adder
    0.14
    Act Density 0.006%

    No Known Activations