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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cdti
    -0.68
    الدراسه
    -0.68
     Orrell
    -0.63
    ')));
    -0.61
    IContainer
    -0.60
    جوايز
    -0.59
     resourceCulture
    -0.59
    )։
    -0.59
    asteroide
    -0.59
    */;
    -0.58
    POSITIVE LOGITS
    Thats
    0.89
    thats
    0.87
     Thats
    0.87
    That
    0.78
     That
    0.77
     שוליים
    0.77
    THAT
    0.73
     thats
    0.71
     THAT
    0.70
    这就是
    0.69
    Act Density 0.093%

    No Known Activations