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

    Neuronpedia

    INDEX
    Explanations

    occurrences of quotation marks and punctuation that suggest speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esternos
    -0.54
    </h5>
    -0.52
    abestanden
    -0.49
     autorytatywna
    -0.44
    AddTagHelper
    -0.43
     ModelExpression
    -0.42
    rungsseite
    -0.39
     «
    -0.39
    KommentareTeilen
    -0.37
     («
    -0.36
    POSITIVE LOGITS
    ”
    1.16
    .”
    1.16
    ."
    1.12
    」
    1.12
    ”.
    1.07
    ".
    1.03
    "
    1.03
    ")
    1.03
    ()"
    1.03
    !”
    1.02
    Act Density 0.246%

    No Known Activations