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

    Neuronpedia

    INDEX
    Explanations

    phrases related to written or journalistic works

    oai_token-act-pair · gpt-3.5-turbo

    references to written works or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsius
    -0.87
     Predators
    -0.78
     Answer
    -0.64
     Nadu
    -0.64
     Monitor
    -0.64
     Sector
    -0.61
     Snapdragon
    -0.59
     runaway
    -0.58
     Predator
    -0.58
     Sear
    -0.57
    POSITIVE LOGITS
    meal
    1.88
    toe
    0.88
    work
    0.86
    book
    0.82
     piece
    0.81
    glass
    0.80
    umen
    0.80
    bare
    0.79
    horn
    0.78
    worm
    0.74
    Act Density 0.015%

    No Known Activations