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

    Neuronpedia

    INDEX
    Explanations

    words related to sparks and ignition

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "spark" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©Ł
    -0.76
    ordan
    -0.72
    paio
    -0.72
    phia
    -0.66
    guyen
    -0.66
     cogn
    -0.64
    ibaba
    -0.63
    ablishment
    -0.62
     cartel
    -0.62
     parasites
    -0.62
    POSITIVE LOGITS
    plug
    1.24
    lers
    1.08
    le
    1.02
    lest
    0.97
    led
    0.97
    les
    0.96
    lights
    0.95
    rings
    0.95
    LES
    0.95
    ling
    0.94
    Act Density 0.047%

    No Known Activations