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

    Neuronpedia

    INDEX
    Explanations

    punctuation and certain control characters in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing braces and semicolons that end code blocks or statements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    AsUp
    -0.68
     stället
    -0.67
    蚪
    -0.66
    MLLoader
    -0.65
    WithIOException
    -0.64
    providedIn
    -0.62
     AssemblyCulture
    -0.62
     miniaturka
    -0.61
    ANTLR
    -0.61
    /**
    -0.61
    POSITIVE LOGITS
    pe
    0.32
    BE
    0.32
    あって
    0.31
    pet
    0.31
    首先
    0.31
    IMAL
    0.31
    精
    0.31
    be
    0.31
    ÇA
    0.30
     pe
    0.30
    Act Density 0.529%

    No Known Activations