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

    Neuronpedia

    INDEX
    Explanations

    references to personal matters and information

    oai_token-act-pair · gpt-3.5-turbo

    references to personal information and privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -1.09
     Removal
    -0.72
    XM
    -0.71
    ORN
    -0.71
    UMP
    -0.71
     Tens
    -0.69
    ï¸
    -0.69
    IRD
    -0.69
    IVERS
    -0.68
    REG
    -0.68
    POSITIVE LOGITS
    ised
    1.18
    ized
    1.04
     belongings
    0.99
     pronouns
    0.97
    ization
    0.95
     hygiene
    0.91
    isations
    0.90
    izes
    0.89
    ities
    0.89
    izing
    0.88
    Act Density 0.022%

    No Known Activations