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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.70
    cko
    -0.62
    answered
    -0.62
    \/
    -0.61
     Became
    -0.60
    -------
    -0.58
    arial
    -0.58
     +++
    -0.56
     Remastered
    -0.56
     BELOW
    -0.56
    POSITIVE LOGITS
     but
    1.27
    but
    1.21
     nor
    0.98
     BUT
    0.91
    But
    0.83
    although
    0.83
     But
    0.80
     though
    0.75
     secondly
    0.75
    though
    0.75
    Act Density 0.080%

    No Known Activations