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

    Neuronpedia

    INDEX
    Explanations

    personal reflections or introspection

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing personal identity or self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angering
    -0.70
    Detailed
    -0.69
    SpaceEngineers
    -0.67
     targeting
    -0.67
    Officials
    -0.66
    Leaks
    -0.65
    Consumer
    -0.65
    CPU
    -0.63
    Intel
    -0.63
    Demand
    -0.63
    POSITIVE LOGITS
     autobi
    1.13
     kindred
    0.92
     poet
    0.91
     Twain
    0.87
     biography
    0.86
     psychologist
    0.86
     poems
    0.85
     novelist
    0.85
     autobiography
    0.84
     narrator
    0.82
    Act Density 1.482%

    No Known Activations