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

    Neuronpedia

    INDEX
    Explanations

    personal experiences or opinions

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -1.04
    ktop
    -0.78
     Tens
    -0.76
    XM
    -0.73
    vous
    -0.69
    LER
    -0.68
    UMP
    -0.68
    eeks
    -0.67
    ERY
    -0.67
    LOS
    -0.66
    POSITIVE LOGITS
    ised
    1.18
    ized
    1.02
    ization
    0.97
     pronouns
    0.94
    isations
    0.92
     belongings
    0.91
    ities
    0.91
    isation
    0.89
     hygiene
    0.88
    istically
    0.86
    Act Density 0.015%

    No Known Activations