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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.56
    UnusedPrivate
    -0.56
     AssemblyCulture
    -0.52
     eût
    -0.51
    aneously
    -0.51
    στά
    -0.50
     actuels
    -0.49
    setupUi
    -0.49
    ząt
    -0.48
     مشين
    -0.48
    POSITIVE LOGITS
     bureau
    0.74
     Bureau
    0.73
     bureaus
    0.72
    Bureau
    0.67
     disgu
    0.65
     BUREAU
    0.64
    ειτουργ
    0.64
     disguise
    0.59
     كومونز
    0.58
    UnknownFields
    0.58
    Act Density 3.101%

    No Known Activations