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

    Neuronpedia

    INDEX
    Explanations

    qualifiers that express degree, such as "bit" and "little."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     greatly
    -0.69
     sufficiently
    -0.62
     entirely
    -0.62
     utterly
    -0.61
     completely
    -0.61
     tremendously
    -0.60
     sepenuhnya
    -0.57
     enormously
    -0.57
    丝毫
    -0.56
     essentially
    -0.56
    POSITIVE LOGITS
    ValueStyle
    0.75
     bit
    0.72
    tagext
    0.65
     OFDb
    0.65
     longer
    0.65
    ずつ
    0.63
    PROLOG
    0.61
    longer
    0.61
    SequentialGroup
    0.61
    SourceChecksum
    0.60
    Act Density 0.143%

    No Known Activations