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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conversational interruptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.59
     fossa
    -0.59
    ՚
    -0.56
     eenige
    -0.56
    idak
    -0.55
     Etrus
    -0.55
    🔕
    -0.54
    CDATA
    -0.54
     QWidget
    -0.53
    ặng
    -0.53
    POSITIVE LOGITS
     I
    0.68
    LEncoder
    0.63
    <bos>
    0.62
    SourceChecksum
    0.60
    memoized
    0.58
     The
    0.58
     let
    0.55
    ngdoc
    0.55
     excuse
    0.54
    $}
    0.54
    Act Density 0.057%

    No Known Activations