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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation, particularly commas and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     significant
    -0.39
    ,
    -0.38
    ↵
    -0.38
     and
    -0.34
    ↵↵
    -0.34
     Reif
    -0.34
     SEVER
    -0.33
    ’
    -0.32
     severe
    -0.30
    '
    -0.29
    POSITIVE LOGITS
    ),”
    1.23
    .’”
    1.23
    ,’”
    1.22
    ?”
    1.20
    ?”.
    1.19
    ...”
    1.17
    ).”
    1.17
    ,”
    1.17
    ,'"
    1.17
    .”
    1.16
    Act Density 0.197%

    No Known Activations