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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms related to performance or outcome, particularly focusing on positive and impactful descriptors

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ®
    -0.84
    atel
    -0.75
     urgently
    -0.72
    wiki
    -0.72
    govtrack
    -0.70
    thur
    -0.69
    chu
    -0.69
    Tube
    -0.69
     Canaver
    -0.68
    bara
    -0.68
    POSITIVE LOGITS
     performances
    1.11
     positional
    1.11
     streak
    1.08
     defensive
    1.08
     teammate
    1.07
     lineback
    1.07
     postseason
    1.07
     goalt
    1.06
     offseason
    1.01
     offensive
    1.01
    Act Density 0.156%

    No Known Activations