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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.09
    7:0.07
    8:0.07
    9:0.09
    10:0.07
    11:0.07
    Negative Logits
     Towns
    -3.19
     Cynthia
    -3.17
     Darwin
    -3.14
     Arche
    -3.01
     Kirby
    -2.92
     Coy
    -2.88
     Nasa
    -2.86
     Rarity
    -2.82
    aces
    -2.81
     Brigham
    -2.78
    POSITIVE LOGITS
     delinqu
    3.47
    rimp
    3.02
     challeng
    2.90
     delinquent
    2.81
     inhibitor
    2.78
     surpr
    2.75
    女
    2.72
     gren
    2.71
     disarm
    2.66
     burgl
    2.65
    Act Density 0.000%

    No Known Activations