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

    Neuronpedia

    INDEX
    Explanations

    references to previous instances or versions

    oai_token-act-pair · gpt-3.5-turbo

    references to prior events or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hots
    -0.70
     ware
    -0.66
    rage
    -0.66
    hop
    -0.65
    acer
    -0.65
    mass
    -0.64
     Scher
    -0.64
    von
    -0.62
    haw
    -0.62
    kamp
    -0.62
    POSITIVE LOGITS
    ebin
    0.99
     installments
    0.87
     incarnation
    0.87
     incarn
    0.83
     occupant
    0.80
     previous
    0.79
     generations
    0.79
    foundland
    0.79
    etheless
    0.75
     Previous
    0.75
    Act Density 0.017%

    No Known Activations