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

    Neuronpedia

    INDEX
    Explanations

    coding-related terms and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /browse
    -0.15
    ucs
    -0.15
    ç
    -0.14
    álo
    -0.14
    iale
    -0.14
    acular
    -0.14
    obus
    -0.14
    oord
    -0.13
    oom
    -0.13
    />\
    -0.13
    POSITIVE LOGITS
     brackets
    0.38
     braces
    0.36
     bracket
    0.34
     Bracket
    0.29
     brace
    0.29
    -br
    0.28
    br
    0.28
    Bracket
    0.27
    Br
    0.27
     opening
    0.26
    Act Density 0.127%

    No Known Activations