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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "contest"

    oai_token-act-pair · gpt-3.5-turbo

    references to various contests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leaf
    -0.71
    âĹ¼
    -0.70
    minent
    -0.68
    ths
    -0.65
    ahon
    -0.63
    thood
    -0.63
    iami
    -0.62
    ----------
    -0.61
     veins
    -0.61
    phen
    -0.61
    POSITIVE LOGITS
    eers
    1.04
    eering
    1.02
    ing
    0.90
    arium
    0.89
    ors
    0.86
    ants
    0.85
    hips
    0.81
    naire
    0.79
    cakes
    0.76
    ivity
    0.76
    Act Density 0.015%

    No Known Activations