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

    Neuronpedia

    INDEX
    Explanations

    discussion of experimental methodologies and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :///
    -0.15
    Č↵
    -0.14
    /fonts
    -0.14
     Fol
    -0.14
    è©
    -0.14
    rowave
    -0.14
    estination
    -0.14
    .builders
    -0.14
    dden
    -0.14
    king
    -0.13
    POSITIVE LOGITS
    unos
    0.15
    olo
    0.15
     Cin
    0.14
     interpret
    0.14
    inx
    0.13
    á»Ļ
    0.13
    олов
    0.13
    ÑĤим
    0.13
     NONINFRINGEMENT
    0.13
    Collector
    0.13
    Act Density 0.088%

    No Known Activations