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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a critical or decisive moment

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating specific situations or conditions described with the word "where."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bees
    -0.70
    rolet
    -0.69
    yi
    -0.67
     Deer
    -0.62
    fml
    -0.61
    apult
    -0.61
     Beasts
    -0.61
    mask
    -0.60
    cade
    -0.60
    Bow
    -0.60
    POSITIVE LOGITS
    upon
    1.35
    abouts
    1.05
    soever
    0.96
    nces
    0.71
    ILLE
    0.71
    imaru
    0.69
    fore
    0.69
    hov
    0.68
    earch
    0.68
    reon
    0.67
    Act Density 0.052%

    No Known Activations