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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific structural elements in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -1.08
    ]")]
    -1.00
    #+#
    -0.91
    IsContent
    -0.90
    TagMode
    -0.88
    XmlAccessType
    -0.88
    principalColumn
    -0.87
     autorytatywna
    -0.87
    LookAnd
    -0.86
     مشين
    -0.84
    POSITIVE LOGITS
     &_
    0.37
    🏻
    0.37
     on
    0.37
     formales
    0.37
    Referències
    0.36
    🏽
    0.35
    Warsaw
    0.34
    🏼
    0.34
    🏻‍♀️
    0.34
    bih
    0.34
    Act Density 0.000%

    No Known Activations