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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or snippets of information related to a variety of topics or events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ãĥĺ
    -0.89
    aneers
    -0.82
    ãĥł
    -0.80
    ¨
    -0.79
    rued
    -0.76
    gas
    -0.73
    alties
    -0.72
    Disk
    -0.71
    lees
    -0.70
    FontSize
    -0.68
    POSITIVE LOGITS
     rundown
    0.95
     synopsis
    0.91
     excerpt
    0.89
     overview
    0.86
     breakdown
    0.85
     tentative
    0.83
     summary
    0.78
     preliminary
    0.77
     caveat
    0.76
     kicker
    0.75
    Act Density 0.078%

    No Known Activations