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

    Neuronpedia

    INDEX
    Explanations

    terms related to personal and sensitive information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elo
    -0.15
    icide
    -0.15
    eln
    -0.15
    TypeID
    -0.14
    lon
    -0.14
    Âłmiles
    -0.14
    lust
    -0.14
    erras
    -0.13
    lernen
    -0.13
    irtual
    -0.13
    POSITIVE LOGITS
     information
    0.28
     data
    0.25
     identifiable
    0.23
     identifying
    0.23
    information
    0.22
    ä¿¡æģ¯
    0.21
     identification
    0.21
    æķ°æį®
    0.20
    -data
    0.20
     Ident
    0.19
    Act Density 0.008%

    No Known Activations