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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "parentheses."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    parentheses for annotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UrlResolution
    -0.55
     protoimpl
    -0.46
     iVar
    -0.46
    libft
    -0.45
    viewWillAppear
    -0.41
    IsContent
    -0.41
     Swar
    -0.40
    dersfield
    -0.40
     tartalomajánló
    -0.38
    ┏
    -0.38
    POSITIVE LOGITS
     parentheses
    2.44
     parenthesis
    1.72
    heses
    1.01
     '('
    0.88
     brackets
    0.86
    括
    0.80
     "("
    0.75
    PAREN
    0.75
    brackets
    0.69
     bracket
    0.64
    Act Density 0.004%

    No Known Activations