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

    Neuronpedia

    INDEX
    Explanations

    occurrences of string literals and data structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avin
    -0.15
    avel
    -0.14
     Lik
    -0.14
    ahu
    -0.14
    edef
    -0.14
     Twitch
    -0.14
    orz
    -0.14
    oron
    -0.14
    onaut
    -0.14
    ANNEL
    -0.14
    POSITIVE LOGITS
    ween
    0.18
    วà¸ĩ
    0.16
     Shapiro
    0.15
     Ris
    0.15
    .uc
    0.14
     Svg
    0.14
     Din
    0.14
     respectively
    0.14
    icol
    0.14
     Danh
    0.14
    Act Density 0.123%

    No Known Activations