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

    Neuronpedia

    INDEX
    Explanations

    programming-related constructs and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    defineProperty
    -0.56
     betweenstory
    -0.56
    Portail
    -0.53
    ReferenceEquals
    -0.52
    Reporter
    -0.50
    ruecos
    -0.50
     reporter
    -0.48
     Steff
    -0.48
    原始内容存档于
    -0.47
    ensky
    -0.47
    POSITIVE LOGITS
     parse
    1.55
    parse
    1.48
     parsing
    1.48
     Parse
    1.46
    Parse
    1.37
     parsed
    1.34
     Parsing
    1.31
     解析
    1.25
    PARSE
    1.23
    Parsing
    1.20
    Act Density 0.493%

    No Known Activations