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

    Neuronpedia

    INDEX
    Explanations

    keywords related to personal matters or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to personal information or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -1.20
    LER
    -0.78
    GGGG
    -0.77
    UMP
    -0.76
     Removal
    -0.73
    vous
    -0.71
    LOS
    -0.70
    IVERS
    -0.70
    ource
    -0.69
    ktop
    -0.69
    POSITIVE LOGITS
    ised
    1.17
    ities
    1.04
    ization
    1.03
    ized
    1.03
     belongings
    0.99
    izing
    0.95
    isations
    0.94
    izations
    0.92
    ité
    0.92
    isation
    0.92
    Act Density 0.034%

    No Known Activations