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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers, variables, or parameters within structured data or code contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.79
     TextAppearance
    -0.68
     Mep
    -0.67
    thée
    -0.65
    RectangleBorder
    -0.63
    исленность
    -0.63
    HtmlAttribute
    -0.62
    SourceChecksum
    -0.62
    TagMode
    -0.62
    TagHelper
    -0.61
    POSITIVE LOGITS
     etc
    0.55
     ddelweddau
    0.53
     but
    0.52
    ثیر
    0.44
    RDONLY
    0.43
     present
    0.42
     same
    0.42
    というのも
    0.42
    directives
    0.42
    辞典
    0.41
    Act Density 1.210%

    No Known Activations