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
    0:0.18
    1:0.04
    2:0.05
    3:0.06
    4:0.13
    5:0.05
    6:0.03
    7:0.05
    8:0.17
    9:0.07
    10:0.06
    11:0.06
    Negative Logits
    imes
    -1.97
    uner
    -1.90
    ashtra
    -1.87
    tackle
    -1.78
    Overview
    -1.73
    inent
    -1.71
    ゼウス
    -1.70
    EStream
    -1.67
    yip
    -1.66
    exempt
    -1.65
    POSITIVE LOGITS
     AU
    1.71
    1.65
     702
    1.64
     alike
    1.64
     Editors
    1.61
     Aux
    1.57
    ALSE
    1.56
    ONG
    1.54
     ally
    1.53
     [|
    1.51
    Act Density 0.001%

    No Known Activations