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

    Neuronpedia

    INDEX
    Explanations

    detailed technical information and descriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.65
    Merit
    -0.57
    ':
    -0.51
    Picture
    -0.50
    estern
    -0.49
    ylum
    -0.49
    ¶
    -0.48
     Proposition
    -0.46
    ASHINGTON
    -0.46
    olitics
    -0.45
    POSITIVE LOGITS
    .).
    0.92
    !).
    0.86
    ).[
    0.84
    ).
    0.80
    )."
    0.79
    ?).
    0.77
    )).
    0.75
    %).
    0.73
     afterwards
    0.72
     accordingly
    0.71
    Act Density 12.520%

    No Known Activations