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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.59
     jSON
    -0.58
     purpoſe
    -0.57
    PerformLayout
    -0.57
     fédé
    -0.55
     ainfi
    -0.55
     acrylique
    -0.54
     Meksi
    -0.53
    pecies
    -0.53
    SerializedSize
    -0.53
    POSITIVE LOGITS
     without
    1.83
    without
    1.77
    Without
    1.77
     Without
    1.73
     WITHOUT
    1.58
    WITHOUT
    1.57
    Ohne
    1.36
     zonder
    1.33
     Ohne
    1.31
     senza
    1.29
    Act Density 0.126%

    No Known Activations