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

    Neuronpedia

    INDEX
    Explanations

    the start of a new section or paragraph, indicated by the special token <bos>

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Conſ
    -0.83
     pleaſure
    -0.83
     Efq
    -0.83
     Majefty
    -0.81
     Diſ
    -0.80
     ſtate
    -0.80
     Reſ
    -0.79
     poffible
    -0.78
     Chriftian
    -0.77
     ſta
    -0.76
    POSITIVE LOGITS
    MENAFN
    0.85
    ernalia
    0.69
    PerformLayout
    0.65
    webElementXpaths
    0.61
    MergeFrom
    0.60
     mẽ
    0.59
    。
    0.58
    Diwedd
    0.57
    SharedCtor
    0.57
    Hozzáférés
    0.57
    Act Density 0.146%

    No Known Activations