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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.07
    7:0.07
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    ゴ
    -3.07
    Tweet
    -2.79
    pod
    -2.65
     Tweet
    -2.56
    weet
    -2.55
     tweet
    -2.53
     twin
    -2.30
     plush
    -2.29
    spr
    -2.28
     stripes
    -2.27
    POSITIVE LOGITS
     Aber
    2.74
     Asheville
    2.69
     Scotia
    2.67
     Negro
    2.50
     Carnage
    2.45
    chery
    2.45
     Presbyter
    2.42
     Brigham
    2.40
     Fischer
    2.38
     sinful
    2.38
    Act Density 0.000%

    No Known Activations