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

    Neuronpedia

    INDEX
    Explanations

    emotions or personal opinions expressed in the text

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I’m."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneers
    -0.77
     Skydragon
    -0.72
     Gap
    -0.60
    RAM
    -0.60
    bard
    -0.59
    rouse
    -0.58
     Pengu
    -0.58
     Bench
    -0.57
    irtual
    -0.56
     Roh
    -0.55
    POSITIVE LOGITS
    agine
    1.12
    umbai
    1.00
    ortal
    0.99
    selves
    0.98
    ighty
    0.95
    ael
    0.90
    mediately
    0.90
    ploy
    0.85
    oco
    0.83
    brace
    0.81
    Act Density 0.032%

    No Known Activations