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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical notation and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (!_
    -0.58
    ্ত
    -0.54
     Bul
    -0.53
    Địa
    -0.53
     становника
    -0.52
    Giới
    -0.52
     吴
    -0.51
    وزه
    -0.50
    OrNil
    -0.50
    దు
    -0.49
    POSITIVE LOGITS
    Chham
    0.78
     المعيارى
    0.74
    kuuta
    0.70
    <blockquote>
    0.69
    Diweddarwch
    0.68
     consultato
    0.65
    ंदीखरीदारी
    0.65
    Zeneca
    0.65
    <tr>
    0.64
     Lacan
    0.64
    Act Density 0.181%

    No Known Activations