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

    Neuronpedia

    INDEX
    Explanations

    instances of dashes or punctuation that indicate breaks or sections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ₄
    -0.71
     PLE
    -0.70
     VL
    -0.68
    Климат
    -0.67
    btnLogin
    -0.67
     Ching
    -0.66
    Czytaj
    -0.66
     Ong
    -0.66
    dopodob
    -0.65
     Benoit
    -0.64
    POSITIVE LOGITS
    ”—
    1.26
    ?—
    1.23
    ——
    1.19
    !—
    1.19
    —(
    1.17
    —————
    1.16
    ,—
    1.15
    —
    1.15
    —“
    1.14
    .”—
    1.10
    Act Density 0.108%

    No Known Activations