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

    Neuronpedia

    INDEX
    Explanations

    frequency of specific punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .G
    -0.23
    _G
    -0.21
    _g
    -0.19
     Ú¯
    -0.19
    	G
    -0.18
     à¤Ĺ
    -0.18
    .g
    -0.18
    -G
    -0.18
     ãĤ°
    -0.17
     G
    -0.17
    POSITIVE LOGITS
     H
    0.18
     Holt
    0.18
     h
    0.17
     Hor
    0.16
     Hist
    0.15
     HOR
    0.15
    ecycle
    0.15
    .RegisterType
    0.15
     Hur
    0.15
     Ho
    0.14
    Act Density 0.023%

    No Known Activations