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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating the minimum amount or quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions denoting a minimum count or occurrence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¿
    -0.68
    ãĥ¼ãĤ¯
    -0.65
    bern
    -0.64
    mination
    -0.62
    ãĥİ
    -0.59
    hell
    -0.58
    Simply
    -0.57
    taboola
    -0.57
    osc
    -0.57
    vation
    -0.56
    POSITIVE LOGITS
     nine
    1.14
     seven
    1.14
     five
    1.12
     eight
    1.12
     six
    1.12
     four
    1.10
     three
    1.10
     two
    1.05
     eleven
    1.00
     fourteen
    0.97
    Act Density 0.027%

    No Known Activations