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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and apostrophes

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

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parís
    -0.53
     Winkler
    -0.49
     saveiro
    -0.46
    <strong>
    -0.44
    ambilan
    -0.43
    <td>
    -0.42
    ︎
    -0.42
     Jensen
    -0.41
    க்
    -0.41
    ️
    -0.41
    POSITIVE LOGITS
    ",
    1.13
    ',
    1.10
    >",
    1.01
    .",
    0.88
    ),
    0.81
    (),
    0.80
    ]),
    0.79
    "),
    0.78
    ],
    0.77
    \",\
    0.77
    Act Density 0.005%

    No Known Activations