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

    Neuronpedia

    INDEX
    Explanations

    numbers or measurements in a document

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.12
    ⓧ
    -0.86
    <?
    -0.83
    
    -0.82
    /***
    -0.72
    /**
    -0.68
     AssemblyCompany
    -0.56
     gynnwys
    -0.56
    💼
    -0.55
    Transcripción
    -0.52
    POSITIVE LOGITS
     maroc
    1.06
     vinci
    0.97
     ados
    0.96
     brava
    0.92
     nomine
    0.91
     ananas
    0.90
     broderie
    0.88
     comesti
    0.87
     frambo
    0.87
     cioc
    0.86
    Act Density 0.297%

    No Known Activations