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

    Neuronpedia

    INDEX
    Explanations

    words related to fireworks

    oai_token-act-pair · gpt-3.5-turbo

    references to fireworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocide
    -0.77
    ele
    -0.74
    avery
    -0.73
    zee
    -0.72
    sole
    -0.72
    laus
    -0.71
    ovan
    -0.71
    ļéĨĴ
    -0.70
    lege
    -0.68
    nee
    -0.68
    POSITIVE LOGITS
     fireworks
    1.18
     displays
    0.83
     explode
    0.80
    aurus
    0.79
     display
    0.77
    aukee
    0.75
     balls
    0.73
    ptions
    0.73
     hoops
    0.71
    alore
    0.69
    Act Density 0.033%

    No Known Activations