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

    Neuronpedia

    INDEX
    Explanations

    mentions of people and their actions or characteristics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Augu
    -1.13
     wherea
    -1.10
     volunte
    -1.09
     secon
    -1.04
     increa
    -1.03
     depic
    -1.03
     michelin
    -1.02
     lill
    -1.02
     oner
    -1.01
     encomp
    -1.01
    POSITIVE LOGITS
     except
    0.66
    MessageOf
    0.64
     either
    0.62
    except
    0.59
    ViewFeatures
    0.58
    intios
    0.57
     usually
    0.56
     ostavi
    0.56
    complexContent
    0.55
    зулта
    0.54
    Act Density 0.339%

    No Known Activations