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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical notations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.80
    Personensuche
    -0.75
    msgTypes
    -0.71
     sumpay
    -0.69
    ьажоргаш
    -0.69
    WebElementEntity
    -0.66
     Мексичка
    -0.66
     autorytatywna
    -0.65
    ſelf
    -0.65
    aarrggbb
    -0.65
    POSITIVE LOGITS
     
    0.45
    それで
    0.44
     $
    0.44
    <td>
    0.39
     élevé
    0.38
    连忙
    0.37
     total
    0.36
    (
    0.36
     between
    0.36
     szint
    0.35
    Act Density 0.744%

    No Known Activations