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

    Neuronpedia

    INDEX
    Explanations

    punctuation that signifies dialogue or quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.29
     ―――――
    -1.20
     auffi
    -1.20
     Monfieur
    -1.17
     Diſ
    -1.17
     faſt
    -1.15
     fubject
    -1.15
     ſeveral
    -1.14
     ſche
    -1.14
     itſelf
    -1.12
    POSITIVE LOGITS
    ".
    1.61
    ”,
    1.55
    ”.
    1.53
    ",
    1.52
    '.
    1.24
    ',
    1.09
    "
    1.09
    ’,
    1.02
    ”
    1.01
    ’.
    0.99
    Act Density 0.159%

    No Known Activations