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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.82
    EFIAPI
    -0.82
    \}_{
    -0.82
    Билгалдахарш
    -0.81
     Chwiliwch
    -0.81
    ⓧ
    -0.81
    onedDateTime
    -0.81
    tvguidetime
    -0.80
     utafitiHapana
    -0.79
    odotus
    -0.79
    POSITIVE LOGITS
    .
    1.20
    ).
    0.94
    ↵↵
    0.94
     The
    0.85
     This
    0.84
     Although
    0.83
    <bos>
    0.83
    。
    0.79
     However
    0.79
     If
    0.78
    Act Density 2.395%

    No Known Activations