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

    Neuronpedia

    INDEX
    Explanations

    mentions of gorillas

    oai_token-act-pair · gpt-3.5-turbo

    references to gorillas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     broadcast
    -0.73
     titanium
    -0.63
     tele
    -0.62
     Speaker
    -0.62
     prop
    -0.62
     release
    -0.61
     ab
    -0.61
     TD
    -0.61
     examination
    -0.60
     refund
    -0.60
    POSITIVE LOGITS
    illas
    4.40
    illa
    1.59
    anches
    1.26
    illes
    1.20
    adas
    1.04
    ierrez
    1.03
    antes
    1.02
    cules
    1.02
    alez
    1.02
    illi
    0.99
    Act Density 0.012%

    No Known Activations