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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.92
     Saltar
    -0.91
     Shakspeare
    -0.85
     Weyl
    -0.81
     tric
    -0.79
     itſelf
    -0.79
    neſs
    -0.78
     Hift
    -0.77
     fevere
    -0.77
    )");
    -0.77
    POSITIVE LOGITS
     or
    1.59
     یا
    1.37
     eller
    1.36
     atau
    1.36
     Or
    1.35
     oder
    1.27
     OR
    1.23
    หรือ
    1.23
    or
    1.22
     vagy
    1.21
    Act Density 0.244%

    No Known Activations