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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.02
    2:0.07
    3:0.03
    4:0.05
    5:0.03
    6:0.24
    7:0.05
    8:0.06
    9:0.29
    10:0.01
    11:0.03
    Negative Logits
    agogue
    -3.90
    brew
    -3.72
     kosher
    -3.67
    BG
    -3.58
     homebrew
    -3.55
    MAG
    -3.50
    Hung
    -3.46
     glyph
    -3.44
     rgb
    -3.40
    cade
    -3.40
    POSITIVE LOGITS
     Willis
    11.24
     Willow
    4.72
     Ames
    4.20
     Reeves
    4.12
     Burke
    4.03
     Duncan
    4.02
     Pierce
    3.98
     Peters
    3.93
     Wesley
    3.91
     Wes
    3.86
    Act Density 0.001%

    No Known Activations