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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly parentheses and quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.34
    (
    -0.24
    &nbsp
    -0.23
    's
    -0.22
    "
    -0.20
    're
    -0.20
    :
    -0.20
    ↵↵
    -0.20
    ’s
    -0.20
    <br
    -0.19
    POSITIVE LOGITS
    /'
    0.20
    ï¸ı
    0.15
    âĢ²
    0.14
    ãģĹãģªãģĦ
    0.14
    bsites
    0.14
    eff
    0.14
    ãĢģ“
    0.14
    ãĢģãĢĮ
    0.14
    evi
    0.13
    istrovstvÃŃ
    0.13
    Act Density 0.838%

    No Known Activations