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

    Neuronpedia

    INDEX
    Explanations

    terms referring to organizations, institutions, and formal entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.89
     Diſ
    -0.87
     myſelf
    -0.80
     poffe
    -0.79
     Monfieur
    -0.77
    HtmlAttribute
    -0.70
     Reſ
    -0.69
     himſelf
    -0.69
     pleaſure
    -0.67
    AndEndTag
    -0.67
    POSITIVE LOGITS
     he
    0.54
    ighed
    0.52
    OMEN
    0.50
     nào
    0.50
     him
    0.49
    ிறது
    0.48
     never
    0.48
     S
    0.48
     Mc
    0.48
    níků
    0.47
    Act Density 0.638%

    No Known Activations