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

    Neuronpedia

    INDEX
    Explanations

    dates and locations mentioned in news articles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Boo
    -0.55
     incompet
    -0.54
     Wee
    -0.53
     curls
    -0.52
     gore
    -0.51
     Grow
    -0.51
    dule
    -0.51
     gib
    -0.50
     Kirin
    -0.50
     Geh
    -0.49
    POSITIVE LOGITS
    MEN
    0.63
    WASHINGTON
    0.62
    âĶĢ
    0.62
    SHARE
    0.61
    impl
    0.60
     BALL
    0.60
    CONT
    0.60
    atform
    0.59
    wikipedia
    0.57
    arbon
    0.57
    Act Density 0.097%

    No Known Activations