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

    Neuronpedia

    INDEX
    Explanations

    Descriptive terms related to technological advancements

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordinate
    -0.83
    onds
    -0.75
    icult
    -0.72
    worms
    -0.71
    perate
    -0.71
    orts
    -0.71
    ilit
    -0.71
     foc
    -0.70
    ignty
    -0.69
    uder
    -0.69
    POSITIVE LOGITS
    ————
    1.53
    ————————
    1.51
    ————————————————
    1.26
    ––
    1.05
    ——
    1.05
    âĢķ
    0.96
     âĢķ
    0.86
    —-
    0.86
    CNN
    0.79
    Marginal
    0.77
    Act Density 0.065%

    No Known Activations