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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Adair
    -0.59
     Alar
    -0.58
    OrWhiteSpace
    -0.56
    principalTable
    -0.54
     Unito
    -0.54
    ंदीखरीदारी
    -0.54
     Bhd
    -0.54
    SharedDtor
    -0.53
     Romana
    -0.52
     Senado
    -0.51
    POSITIVE LOGITS
     autorytatywna
    0.67
     ویکی‌پدیای
    0.66
    rungsseite
    0.64
    UnusedPrivate
    0.63
    endphp
    0.61
    Literally
    0.60
     pretty
    0.59
    addContainerGap
    0.59
     basically
    0.58
     kind
    0.57
    Act Density 0.029%

    No Known Activations