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

    Neuronpedia

    INDEX
    Explanations

    the presence of punctuation marks and parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (
    -0.19
    of
    -0.17
    $
    -0.17
    &
    -0.16
    ),
    -0.15
     ],
    -0.15
    ],
    -0.15
    retty
    -0.15
    ifu
    -0.15
     },
    -0.15
    POSITIVE LOGITS
    âĢ¦)↵↵
    0.20
     Note
    0.17
    edir
    0.17
    Uvs
    0.16
    Note
    0.15
    NB
    0.15
     NOTE
    0.15
    à¹ij
    0.15
     note
    0.15
    alten
    0.15
    Act Density 0.041%

    No Known Activations