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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    943
    -0.15
    ngine
    -0.14
     Wheeler
    -0.14
    aversal
    -0.14
    anagan
    -0.14
    dux
    -0.14
    ournal
    -0.14
     Partner
    -0.14
     spir
    -0.14
     NSStringFromClass
    -0.14
    POSITIVE LOGITS
     binary
    0.22
     Indicator
    0.20
    indicator
    0.19
     Binary
    0.19
     indicator
    0.19
    binary
    0.18
    Indicator
    0.18
    _indicator
    0.17
     Dich
    0.17
    Binary
    0.17
    Act Density 0.229%

    No Known Activations