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

    Neuronpedia

    INDEX
    Explanations

    specific version numbers or identifiers related to Python packages or modules

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    渾
    -0.54
    fiés
    -0.54
    以上
    -0.52
    Matthias
    -0.51
    inguém
    -0.50
    :✨
    -0.50
    gmd
    -0.49
    guien
    -0.48
     oreilles
    -0.47
    StructEnd
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.77
     Pakistan
    0.67
     PhpStorm
    0.66
    __":
    0.64
    󠁢
    0.64
     Вікіпе
    0.64
    __":
    0.63
    Pakistan
    0.62
     StatefulWidget
    0.60
    ädie
    0.59
    Act Density 0.006%

    No Known Activations