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

    Neuronpedia

    INDEX
    Explanations

    phrases related to logistics and pick-up arrangements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to choices or selections made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.00
    issance
    -0.79
    cular
    -0.73
    parable
    -0.72
    ĨĴ
    -0.72
    rency
    -0.71
    orescence
    -0.70
    xual
    -0.67
    tions
    -0.67
    cule
    -0.66
    POSITIVE LOGITS
    axe
    0.78
     grapes
    0.75
     apples
    0.75
     flakes
    0.72
    sticks
    0.71
     axe
    0.66
    jee
    0.64
     mt
    0.64
     paddle
    0.63
     Ging
    0.62
    Act Density 0.082%

    No Known Activations