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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns such as dates and statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nomine
    -0.70
     snowball
    -0.69
     exha
    -0.68
     plateau
    -0.68
     culminated
    -0.67
    ÃŃs
    -0.67
    ierrez
    -0.64
     DRAG
    -0.64
    enhagen
    -0.63
     tops
    -0.61
    POSITIVE LOGITS
    79
    1.23
    708
    1.22
    806
    1.20
    67
    1.20
    86
    1.19
    503
    1.19
    66
    1.18
    709
    1.18
    89
    1.17
    88
    1.17
    Act Density 0.125%

    No Known Activations