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

    Neuronpedia

    INDEX
    Explanations

    terms related to awards and recognition

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "distribution."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -1.22
    ppo
    -0.83
    swick
    -0.83
    terday
    -0.80
    tes
    -0.75
    gery
    -0.71
    fter
    -0.70
    ENA
    -0.69
    BOX
    -0.69
    uberty
    -0.68
    POSITIVE LOGITS
    ribut
    1.43
    ributed
    1.36
    ribution
    1.28
    inguished
    1.22
    ribute
    1.21
    illery
    1.15
    rict
    1.13
    ortion
    1.06
    enfranch
    1.06
    inct
    1.03
    Act Density 0.008%

    No Known Activations