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

    Neuronpedia

    INDEX
    Explanations

    instances of evidence and demonstration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ston
    -0.17
    zer
    -0.15
    ubu
    -0.15
     McCabe
    -0.14
    ette
    -0.14
    jvu
    -0.14
    ardin
    -0.14
    _ENUM
    -0.14
    erox
    -0.14
     اÙĪت
    -0.14
    POSITIVE LOGITS
    bread
    0.17
    gua
    0.15
    outu
    0.14
    ents
    0.14
    LIK
    0.14
    _tem
    0.14
     пÑĢовед
    0.14
    chy
    0.14
    rz
    0.14
    azed
    0.13
    Act Density 0.118%

    No Known Activations