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

    Neuronpedia

    INDEX
    Explanations

    end punctuation marks for quoted speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.67
    ​
    -0.67
    t
    -0.59
    -
    -0.56
    ^{
    -0.55
    flink
    -0.55
    --
    -0.54
    vaux
    -0.54
    {
    -0.54
     Tsche
    -0.54
    POSITIVE LOGITS
     …”
    1.57
    …"
    1.52
    …”
    1.52
    ...");
    1.52
    …’
    1.52
    …]
    1.50
    …»
    1.49
    …)
    1.47
    ...")
    1.45
     ..."
    1.44
    Act Density 0.124%

    No Known Activations