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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating correctness or appropriateness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.96
     $_"
    -0.94
     purpoſe
    -0.90
     Monfieur
    -0.90
     للاسماء
    -0.89
     Diſ
    -0.88
     photolibrary
    -0.86
     Houſe
    -0.86
     pleaſure
    -0.86
     ſind
    -0.86
    POSITIVE LOGITS
    WEBPACK
    0.56
    XMLSchema
    0.55
     ab
    0.45
     so
    0.45
     per
    0.44
     
    0.44
     вс
    0.43
    rentino
    0.43
    <eos>
    0.41
     напо
    0.41
    Act Density 0.340%

    No Known Activations