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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a short amount of time or duration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "brief."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.86
    JV
    -0.78
    ceans
    -0.70
    GAN
    -0.70
    GO
    -0.69
    Drive
    -0.68
    Detect
    -0.67
    rogens
    -0.66
     Taxi
    -0.65
    SEA
    -0.64
    POSITIVE LOGITS
    cases
    1.09
    case
    1.04
     glimps
    0.93
    aneously
    0.91
     stint
    0.85
    ebin
    0.82
     outline
    0.80
    isode
    0.77
     bouts
    0.76
     impressions
    0.76
    Act Density 0.005%

    No Known Activations