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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to decisions, positions, and significant issues in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alike
    -0.16
     pri
    -0.15
     Sor
    -0.15
     Benz
    -0.15
     sor
    -0.14
     br
    -0.14
     Eigen
    -0.14
    licht
    -0.14
    appearance
    -0.14
     OMIT
    -0.14
    POSITIVE LOGITS
    à¹Ģย
    0.16
    nings
    0.15
     YT
    0.15
    ëĭ´
    0.15
    lycer
    0.14
     thôi
    0.14
    HITE
    0.14
    ibility
    0.14
    Å¡lo
    0.14
    IID
    0.13
    Act Density 0.276%

    No Known Activations