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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

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

    Mr. followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ientras
    -1.16
    httphttps
    -1.13
    ſcher
    -1.05
    SequentialGroup
    -1.03
    iſen
    -1.02
    mpagne
    -1.02
    iſchen
    -1.01
    ágenes
    -1.01
    ésultats
    -1.00
    iſten
    -0.99
    POSITIVE LOGITS
    .
    0.59
    ,
    0.48
    <bos>
    0.48
    *
    0.48
    !
    0.46
    ↵
    0.46
    </tr>
    0.44
     &
    0.44
    $.
    0.44
     of
    0.42
    Act Density 0.021%

    No Known Activations