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

    Neuronpedia

    INDEX
    Explanations

    references to different potential results or consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of outcomes and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brakes
    -0.77
    ondo
    -0.75
    yi
    -0.72
    andise
    -0.71
    ker
    -0.71
    sis
    -0.66
    aps
    -0.66
    afort
    -0.65
    udi
    -0.65
    king
    -0.63
    POSITIVE LOGITS
     outcome
    1.02
     outcomes
    0.98
    bringer
    0.83
     thereof
    0.81
    romeda
    0.72
     Yanuk
    0.68
    TPPStreamerBot
    0.67
     probabilities
    0.67
    fulness
    0.67
     expectancy
    0.67
    Act Density 0.020%

    No Known Activations