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

    Neuronpedia

    INDEX
    Explanations

    references to scientific research and experimental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Evel
    -0.14
    è½
    -0.14
    attr
    -0.14
    ramer
    -0.14
     Haram
    -0.13
     continual
    -0.13
    822
    -0.13
     sá»Ń
    -0.13
    rent
    -0.13
    ounter
    -0.13
    POSITIVE LOGITS
    zcze
    0.19
    enstein
    0.15
    akin
    0.15
    stuff
    0.15
     stuff
    0.14
    anou
    0.14
     jež
    0.14
    Inlining
    0.14
    enko
    0.14
    ç¼ĺ
    0.13
    Act Density 0.099%

    No Known Activations