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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases indicating frequency or universality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //
    -0.67
    Bauer
    -0.65
    zt
    -0.64
    Cone
    -0.60
    /
    -0.59
    йом
    -0.58
    Azur
    -0.58
     dados
    -0.58
    Shane
    -0.57
     lze
    -0.56
    POSITIVE LOGITS
    every
    1.97
     every
    1.94
     EVERY
    1.88
     Every
    1.83
    EVERY
    1.81
    Every
    1.81
     Ogni
    1.43
     Jedes
    1.31
    Chaque
    1.24
    Ogni
    1.24
    Act Density 0.117%

    No Known Activations