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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms indicating exceptions or challenges to general rules or assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.75
    oa̍t
    -0.73
    TemporalType
    -0.68
    évaluateur
    -0.66
     linkovi
    -0.61
     oprot
    -0.61
    Jereo
    -0.60
    WSGI
    -0.60
    parsedMessage
    -0.60
    webElement
    -0.59
    POSITIVE LOGITS
     exceptions
    0.93
     defied
    0.89
     surprise
    0.89
     defying
    0.88
     contrary
    0.88
     defy
    0.87
     unexpected
    0.85
     Unexpected
    0.81
     defies
    0.80
     exception
    0.79
    Act Density 0.246%

    No Known Activations