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

    Neuronpedia

    INDEX
    Explanations

    instances of various introductory elements or sentence openers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uebas
    -0.46
     pull
    -0.42
     san
    -0.41
    CancelButton
    -0.41
     total
    -0.41
    joel
    -0.40
    ips
    -0.40
     ailleurs
    -0.40
    Bronnen
    -0.39
    tetten
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.95
    ьажоргаш
    0.92
    PerformLayout
    0.88
     defaultstate
    0.84
    tagHelperRunner
    0.82
     <=",
    0.81
     يتيمه
    0.79
     Waray
    0.78
     Empieza
    0.78
    CloseOperation
    0.77
    Act Density 0.302%

    No Known Activations