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

    Neuronpedia

    INDEX
    Explanations

    phrases related to things being turned or oriented in a certain direction

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words related to the concept of "upside" or positive potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iston
    -0.86
    imens
    -0.84
    ateurs
    -0.84
    ocally
    -0.80
    assetsadobe
    -0.80
    ingham
    -0.75
    naire
    -0.74
     Cosponsors
    -0.74
    ifiable
    -0.74
    è¦ļéĨĴ
    -0.71
    POSITIVE LOGITS
     upside
    0.93
     down
    0.84
    ï¸
    0.84
    verted
    0.84
    Down
    0.79
     heel
    0.79
    side
    0.77
     downwards
    0.76
    down
    0.72
    visible
    0.71
    Act Density 0.023%

    No Known Activations