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

    Neuronpedia

    INDEX
    Explanations

    phrases related to amazement or surprise

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "behold" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hiroshima
    -0.73
     Atkinson
    -0.70
     Aberdeen
    -0.70
     Scotia
    -0.67
     Kaiser
    -0.66
     MacArthur
    -0.65
     McCann
    -0.62
     Okinawa
    -0.61
     Parenthood
    -0.61
     Hurricanes
    -0.60
    POSITIVE LOGITS
     behold
    1.15
    entimes
    1.02
    ers
    0.92
    masters
    0.90
    iful
    0.84
    erers
    0.84
    ibilities
    0.83
    leground
    0.83
    elines
    0.82
    !--
    0.81
    Act Density 0.011%

    No Known Activations