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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.14
    rungsseite
    -0.85
     unknownFields
    -0.84
    AndEndTag
    -0.67
    twimg
    -0.66
    Искәрмәләр
    -0.64
    Demografia
    -0.64
    UnsafeEnabled
    -0.61
    Hentet
    -0.61
    Personensuche
    -0.61
    POSITIVE LOGITS
    lective
    0.62
     greateſt
    0.61
    раздо
    0.61
    ^(@)
    0.60
     beſt
    0.60
    
    0.57
    NUMX
    0.56
     Gai
    0.55
     Ruman
    0.55
     indiv
    0.55
    Act Density 0.013%

    No Known Activations