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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their placement in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.03
    2:0.05
    3:0.03
    4:0.05
    5:0.03
    6:0.30
    7:0.03
    8:0.09
    9:0.18
    10:0.02
    11:0.05
    Negative Logits
     Ethiop
    -4.02
     Sinclair
    -4.01
     Eminem
    -3.77
     Temp
    -3.70
     Koreans
    -3.65
     Pesh
    -3.58
     Saf
    -3.57
     Morales
    -3.52
     Evil
    -3.50
     DeV
    -3.42
    POSITIVE LOGITS
     Bou
    10.36
     bou
    6.49
     Hou
    6.01
     Gou
    5.26
    Dou
    4.38
     Kou
    4.30
     dou
    4.24
     Cou
    4.18
     Boat
    4.08
     Bride
    3.99
    Act Density 0.002%

    No Known Activations