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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially commas and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.75
    **
    -0.73
    原始内容存档于
    -0.69
     ComVisible
    -0.68
     InputDecoration
    -0.66
    fortawesome
    -0.62
     برانيه
    -0.61
     '-':
    -0.60
    disambiguation
    -0.60
    Sklici
    -0.60
    POSITIVE LOGITS
     Whilst
    0.81
     However
    0.75
    Whilst
    0.70
     whilst
    0.69
    (
    0.67
     poichè
    0.65
    However
    0.64
     therefor
    0.64
     Cependant
    0.64
     welches
    0.63
    Act Density 0.481%

    No Known Activations