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

    Neuronpedia

    INDEX
    Explanations

    statements highlighting specific objectives or aims in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.57
     plomo
    -0.45
    存于互联网档案馆
    -0.44
     HasFactory
    -0.43
     defaultstate
    -0.43
    featureID
    -0.42
     Wikiseite
    -0.42
    IFORNIA
    -0.42
     Efq
    -0.41
    UnusedPrivate
    -0.41
    POSITIVE LOGITS
     đ
    0.66
    ד
    0.65
     Đ
    0.65
    Đ
    0.64
    đ
    0.63
    つ
    0.60
     wildlife
    0.58
     objective
    0.56
    ad
    0.56
    Objective
    0.52
    Act Density 0.222%

    No Known Activations