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

    Neuronpedia

    INDEX
    Explanations

    short sentence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    {?>
    -0.68
     basque
    -0.67
     sogni
    -0.66
     tecnici
    -0.64
     proprietario
    -0.63
     giapp
    -0.63
     drap
    -0.63
     fidanz
    -0.62
     ufficiali
    -0.62
     nemici
    -0.61
    POSITIVE LOGITS
     barran
    0.71
    Flere
    0.67
     nearby
    0.62
     Siglo
    0.60
     Jardín
    0.59
    Hvem
    0.56
    Izvori
    0.56
     Catedral
    0.56
    Več
    0.56
     coû
    0.55
    Act Density 0.370%

    No Known Activations