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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential outcomes or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.65
     BoxFit
    -0.62
    bestimmung
    -0.56
    ----</
    -0.54
    كويكب
    -0.53
     JpaRepository
    -0.50
     kasarigan
    -0.50
     démocratique
    -0.49
    currentColor
    -0.49
     arşivlendi
    -0.47
    POSITIVE LOGITS
     need
    0.56
     noticed
    0.54
     seen
    0.48
     have
    0.47
     witnessed
    0.46
     encountering
    0.45
     found
    0.44
     encountered
    0.44
    toHave
    0.44
     encounter
    0.43
    Act Density 0.118%

    No Known Activations