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

    Neuronpedia

    INDEX
    Explanations

    indents or whitespace that could signify structured coding or formatted blocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -1.12
    aarrggbb
    -0.99
     wireType
    -0.98
    AndroidJUnit
    -0.98
    ########.
    -0.95
    AddHtmlAttribute
    -0.94
    SourceChecksum
    -0.93
    bootstrapcdn
    -0.90
    AnchorStyles
    -0.90
    AddTagHelper
    -0.90
    POSITIVE LOGITS
    <eos>
    0.47
    .
    0.41
     
    0.40
    \
    0.40
    一郎
    0.39
      
    0.39
    1
    0.37
     ä
    0.36
    <b>
    0.36
     (
    0.35
    Act Density 0.041%

    No Known Activations