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

    Neuronpedia

    INDEX
    Explanations

    numerical values with percentage symbols and confidence intervals

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with statistical confidence levels and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.80
    sworth
    -0.72
    anian
    -0.68
    ItemImage
    -0.68
    holder
    -0.67
    boarding
    -0.66
    Demand
    -0.65
    untu
    -0.64
    board
    -0.64
    dress
    -0.63
    POSITIVE LOGITS
    %:
    1.04
    %-
    0.92
    999
    0.91
    ¢
    0.88
    %
    0.84
    %;
    0.82
     mph
    0.81
    %);
    0.79
    kHz
    0.78
    %,
    0.78
    Act Density 0.064%

    No Known Activations