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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sections of breaks within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    互联网档案馆
    -0.68
    PerformLayout
    -0.59
    auto
    -0.53
     endblock
    -0.53
    ArgsConstructor
    -0.53
    mea
    -0.52
    Eloquent
    -0.50
    RunWith
    -0.49
     JAXBElement
    -0.48
    IsString
    -0.48
    POSITIVE LOGITS
    ########.
    1.20
    ंदीखरीदारी
    0.95
    <bos>
    0.94
    ⓧ
    0.66
    tvguidetime
    0.61
    amsmath
    0.60
    ’
    0.58
    '
    0.56
    ագրություններ
    0.56
    onomous
    0.56
    Act Density 0.622%

    No Known Activations