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

    Neuronpedia

    INDEX
    Explanations

    political and legal terms or concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.72
    RectangleBorder
    -0.72
     Halen
    -0.71
     bú
    -0.67
    tafogo
    -0.65
     tré
    -0.63
     BorderSide
    -0.63
     sedia
    -0.62
     perla
    -0.62
    WriteTagHelper
    -0.61
    POSITIVE LOGITS
     reluct
    1.60
     disagre
    1.57
     shenan
    1.53
     unwarran
    1.52
     affor
    1.50
     increa
    1.48
     pamph
    1.47
     impra
    1.46
     unspeak
    1.44
     encomp
    1.43
    Act Density 1.114%

    No Known Activations