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

    Neuronpedia

    INDEX
    Explanations

    technical or programming-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Argb
    -0.14
     Metropolitan
    -0.14
     Club
    -0.14
    黨
    -0.13
     MetroFramework
    -0.13
    .Clamp
    -0.13
     metro
    -0.13
    rape
    -0.13
    iode
    -0.13
     Tur
    -0.13
    POSITIVE LOGITS
     grammar
    0.36
     Grammar
    0.33
    grammar
    0.32
     productions
    0.32
     gram
    0.32
    Grammar
    0.31
     gramm
    0.30
     lexer
    0.30
     parser
    0.30
     Gram
    0.30
    Act Density 0.018%

    No Known Activations