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

    Neuronpedia

    INDEX
    Explanations

    numerical information related to demographics and data comparisons

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oris
    -0.67
    ador
    -0.66
    hett
    -0.63
    oké
    -0.61
    oran
    -0.61
    idon
    -0.59
    illard
    -0.58
    ollo
    -0.57
     Dish
    -0.57
    ensus
    -0.56
    POSITIVE LOGITS
     20
    1.17
     10
    1.16
     25
    1.16
     15
    1.16
     750
    1.15
     30
    1.14
     35
    1.13
     300
    1.12
     36
    1.12
     120
    1.11
    Act Density 0.737%

    No Known Activations