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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially colons and formatting tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.72
     للمعارف
    -0.66
     Administrativna
    -0.64
    存于互联网档案馆
    -0.60
    AndEndTag
    -0.57
     CreateTagHelper
    -0.55
     فريبيس
    -0.54
    ReusableCell
    -0.52
    GEBURTS
    -0.50
    principalColumn
    -0.50
    POSITIVE LOGITS
    $:
    0.41
    ”:
    0.40
    *:
    0.39
    :
    0.39
    TotalCount
    0.38
    +:
    0.37
    »:
    0.37
    ：「
    0.37
    ’:
    0.37
    :*
    0.36
    Act Density 0.184%

    No Known Activations