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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and user interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     juntas
    -0.55
     éclat
    -0.53
     själva
    -0.49
    Together
    -0.48
    괄
    -0.47
     admiten
    -0.47
     preventiva
    -0.45
    am
    -0.44
     juntos
    -0.44
    mêmes
    -0.43
    POSITIVE LOGITS
     himself
    1.02
    himself
    0.96
     فريبيس
    0.94
    تقاوى
    0.84
    
    0.77
     незавершена
    0.77
    oretical
    0.74
     wireType
    0.73
    getMenuInflater
    0.70
     }}"></
    0.70
    Act Density 0.533%

    No Known Activations