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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.81
     ļ
    -0.74
     mī
    -0.71
     šķ
    -0.71
     spē
    -0.70
     Puoi
    -0.69
     Weiden
    -0.68
     Schmel
    -0.67
     iesp
    -0.66
     Queste
    -0.64
    POSITIVE LOGITS
     Sén
    0.74
     Kohl
    0.69
    hl
    0.67
     Moby
    0.64
     Travail
    0.62
     Ashley
    0.61
     Ahl
    0.61
     Ohl
    0.61
     Docteur
    0.60
     carrefour
    0.59
    Act Density 0.725%

    No Known Activations