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

    Neuronpedia

    INDEX
    Explanations

    words related to electrical sparks or figurative sparks of inspiration or energy

    oai_token-act-pair · gpt-3.5-turbo

    the word "spark" and its variants, indicating something igniting or initiating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    guyen
    -0.81
    etheless
    -0.78
    paio
    -0.76
    ordan
    -0.73
    ĨĴ
    -0.72
    phia
    -0.70
    ibaba
    -0.69
    thodox
    -0.67
     hygiene
    -0.66
    sembly
    -0.65
    POSITIVE LOGITS
    plug
    1.19
    lings
    0.96
    lers
    0.96
    le
    0.93
    lest
    0.91
    led
    0.91
    ling
    0.91
    Fun
    0.90
    LES
    0.88
    rings
    0.88
    Act Density 0.015%

    No Known Activations