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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating topics or elements being listed or included

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jednoc
    -0.61
    Personensuche
    -0.58
     MotionEvent
    -0.55
    ArgumentParser
    -0.52
    ConstraintSet
    -0.51
    RRect
    -0.51
     Púb
    -0.50
    iritto
    -0.50
     játé
    -0.50
     }}"></
    -0.50
    POSITIVE LOGITS
     include
    0.84
    ✨:
    0.83
    :
    0.82
     للاسماء
    0.82
     antaranya
    0.75
    分别是
    0.74
     including
    0.70
     Include
    0.70
    antaranya
    0.67
     includes
    0.66
    Act Density 0.243%

    No Known Activations