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

    Neuronpedia

    INDEX
    Explanations

    names of sports positions and statistics

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ur
    -0.76
    Material
    -0.74
    :(
    -0.72
    vertis
    -0.72
    Web
    -0.71
    yll
    -0.69
     ®
    -0.69
    DX
    -0.68
    store
    -0.68
    .—
    -0.67
    POSITIVE LOGITS
     then
    0.93
     athleticism
    0.89
     thus
    0.86
     coaches
    0.85
    romeda
    0.84
     scoring
    0.81
     assorted
    0.79
     averaged
    0.79
     preseason
    0.78
     injuries
    0.77
    Act Density 0.333%

    No Known Activations