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

    Neuronpedia

    INDEX
    Explanations

    sport-related rankings and statistics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oult
    -0.82
     survives
    -0.76
    cules
    -0.74
     distinguishes
    -0.71
    helm
    -0.67
     shines
    -0.67
    nance
    -0.67
     detects
    -0.66
    tm
    -0.66
     countered
    -0.65
    POSITIVE LOGITS
     latter
    1.07
     midst
    0.98
     pursuit
    0.96
     same
    0.94
     vicinity
    0.92
     ensuing
    0.92
     guise
    0.92
     inaugural
    0.91
     country
    0.91
     aforementioned
    0.91
    Act Density 0.405%

    No Known Activations