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

    Neuronpedia

    INDEX
    Explanations

    arguments related to the presence or absence of evidence in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -1.06
    tagHelperRunner
    -0.91
    AddTagHelper
    -0.83
     Мексичка
    -0.81
     ModelExpression
    -0.81
     Савезне
    -0.76
    WriteTagHelper
    -0.71
    adaptiveStyles
    -0.65
     betweenstory
    -0.64
     ویکی‌پدی
    -0.62
    POSITIVE LOGITS
     […]
    0.65
    0.55
    ­
    0.53
    […]
    0.48
    <%=
    0.48
    [...]
    0.43
     
    0.43
     [...]
    0.42
    ‐
    0.42
     
    0.41
    Act Density 90.726%
    No Known Activations