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

    Neuronpedia

    INDEX
    Explanations

    references to Intent objects and their actions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.66
    :✨
    -0.60
     Walkover
    -0.58
    IBIL
    -0.54
    uminense
    -0.52
     expédié
    -0.51
    irsi
    -0.51
    liferay
    -0.51
    :][
    -0.50
     raison
    -0.48
    POSITIVE LOGITS
    RetentionPolicy
    0.79
    ^(@)
    0.75
     Efq
    0.73
    RectangleBorder
    0.69
    PositiveButton
    0.69
    ſelf
    0.67
     tecnici
    0.67
     Majefty
    0.66
     Menschheit
    0.66
     greateſt
    0.66
    Act Density 0.021%

    No Known Activations