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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of numerical values in a structured format

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    InkWell
    -0.73
    marginVertical
    -0.70
    ⓧ
    -0.66
    marginHorizontal
    -0.66
    URBANA
    -0.56
    Δείτε
    -0.55
    Πηγή
    -0.55
    তথ্যসূত্র
    -0.54
    Caratter
    -0.54
    paddingVertical
    -0.54
    POSITIVE LOGITS
     autrefois
    0.61
     these
    0.59
     heti
    0.56
     them
    0.56
     quelquefois
    0.56
     gaily
    0.55
     saad
    0.54
     tolerably
    0.54
    ……"
    0.53
     soudain
    0.53
    Act Density 0.159%

    No Known Activations