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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and questions related to existence and knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doesn
    -1.08
    NOT
    -1.04
    Nothing
    -1.01
    Doesn
    -0.99
    never
    -0.99
    didn
    -0.97
    None
    -0.96
    Never
    -0.96
    Don
    -0.96
    NEVER
    -0.95
    POSITIVE LOGITS
    __*/
    0.59
    الحياه
    0.57
    ThroughAttribute
    0.56
    ollectionView
    0.56
    évaluateur
    0.54
     للاسماء
    0.52
     consultato
    0.52
     مرئيه
    0.51
    ')";
    0.51
     المعيارى
    0.50
    Act Density 0.309%

    No Known Activations