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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a text document

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unlaw
    -1.82
     belliger
    -1.78
     despotism
    -1.75
     unspeak
    -1.71
     ruinous
    -1.67
     disgra
    -1.67
     impractica
    -1.57
     odious
    -1.52
     nukes
    -1.51
     massacres
    -1.49
    POSITIVE LOGITS
    <bos>
    17.52
    expandindo
    2.89
    GEBURTSDATUM
    2.89
     betweenstory
    2.87
     Administrativna
    2.76
    تقاوى
    2.73
    Autoritní
    2.71
     Italijani
    2.59
     Италијани
    2.57
     Мексичка
    2.49
    Act Density 0.176%

    No Known Activations