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

    Neuronpedia

    INDEX
    Explanations

    references to values and numeric assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.96
     فريبيس
    -0.85
    ConstraintMaker
    -0.83
     Superhosts
    -0.81
    AnchorStyles
    -0.75
     ISNI
    -0.74
     AssemblyCompany
    -0.72
    Datuak
    -0.70
    SourceChecksum
    -0.69
     ویکی‌پدیای
    -0.69
    POSITIVE LOGITS
     values
    1.09
     Values
    0.91
    values
    0.87
     value
    0.87
    Values
    0.85
     Value
    0.78
     VALUE
    0.76
    value
    0.76
    Wert
    0.74
    VALUE
    0.74
    Act Density 0.148%

    No Known Activations