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

    Neuronpedia

    INDEX
    Explanations

    mentions of personal matters or opinions, especially related to health, politics, or lifestyle

    oai_token-act-pair · gpt-3.5-turbo

    references to personal information and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -1.17
    UMP
    -0.79
    REG
    -0.76
    LER
    -0.73
    etting
    -0.71
    å¾
    -0.71
    LOS
    -0.68
    NESS
    -0.68
     Archdemon
    -0.67
    ÄŁ
    -0.67
    POSITIVE LOGITS
    ised
    1.28
    ized
    1.13
    ization
    1.10
    isation
    1.05
    izing
    1.03
    izations
    1.03
    ities
    1.02
     belongings
    1.02
    isations
    0.97
    izes
    0.97
    Act Density 0.056%

    No Known Activations