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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.09
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.07
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
    usted
    -1.63
    choes
    -1.55
     unse
    -1.52
     peg
    -1.51
    corruption
    -1.49
    imp
    -1.48
    icky
    -1.47
    abuse
    -1.46
    redo
    -1.45
    idy
    -1.45
    POSITIVE LOGITS
     pharmacies
    1.83
    ModLoader
    1.75
    Sov
    1.63
    ヘ
    1.61
    /,
    1.60
     Scand
    1.57
     Vanderbilt
    1.56
     colleges
    1.52
     Shutterstock
    1.52
     Pharmaceutical
    1.49
    Act Density 0.000%

    No Known Activations