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

    Neuronpedia

    INDEX
    Explanations

    instances of structure markers or formatting indications in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.69
    SourceChecksum
    -0.68
    parsedMessage
    -0.66
     itſelf
    -0.64
    ſelves
    -0.64
    EDEFAULT
    -0.62
     propOrder
    -0.60
    ValueStyle
    -0.59
    ſelf
    -0.58
     térm
    -0.58
    POSITIVE LOGITS
     realism
    0.69
     believable
    0.65
     realistic
    0.65
     detail
    0.65
     Realistic
    0.62
     réaliste
    0.60
     character
    0.59
    リアル
    0.56
    Realistic
    0.56
     detalla
    0.54
    Act Density 0.289%

    No Known Activations