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

    Neuronpedia

    INDEX
    Explanations

    nouns and their associated roles or titles in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.70
    <?>>
    -0.60
    kháu
    -0.58
    كويكب
    -0.56
    kurat
    -0.51
    ீர
    -0.49
    aleg
    -0.48
    istö
    -0.47
     Alhambra
    -0.47
     presentes
    -0.47
    POSITIVE LOGITS
     former
    0.68
    former
    0.67
     favorite
    0.60
    RegressionTest
    0.60
    JsonHelper
    0.59
    favorite
    0.58
    isContained
    0.58
     renowned
    0.57
     favourite
    0.57
    RectangleBorder
    0.56
    Act Density 0.196%

    No Known Activations