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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences or opinions

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.89
     Tens
    -0.78
     Apply
    -0.71
    UG
    -0.70
     Removal
    -0.70
    REG
    -0.70
    ï¸
    -0.69
    ORK
    -0.69
    UMP
    -0.68
    fed
    -0.68
    POSITIVE LOGITS
    ised
    1.06
     belongings
    0.99
     personal
    0.93
     pronouns
    0.88
     autobi
    0.85
     consolation
    0.83
    personal
    0.82
    isations
    0.82
    isable
    0.82
     wellbeing
    0.82
    Act Density 0.014%

    No Known Activations