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

    Neuronpedia

    INDEX
    Explanations

    quoted speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    opening quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.90
     ujednoznacz
    -0.89
    ロウィン
    -0.70
    BibitemShut
    -0.66
    careous
    -0.64
    <unused41>
    -0.63
    ſſung
    -0.63
    <unused16>
    -0.63
    <unused8>
    -0.63
    [@BOS@]
    -0.63
    POSITIVE LOGITS
    “
    0.88
    "
    0.57
    „
    0.42
    «
    0.42
    ‘
    0.42
    ("
    0.41
    <bos>
    0.36
    ('
    0.36
    「
    0.36
    "(
    0.35
    Act Density 0.029%

    No Known Activations