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

    Neuronpedia

    INDEX
    Explanations

    references to fireworks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fireworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocide
    -0.74
    ele
    -0.72
    zee
    -0.70
    ŃĶ
    -0.70
    ovan
    -0.69
    nee
    -0.66
    laus
    -0.65
    aer
    -0.65
    lege
    -0.64
    avery
    -0.64
    POSITIVE LOGITS
     fireworks
    1.20
     displays
    0.85
    aurus
    0.82
     display
    0.78
     explode
    0.78
    ptions
    0.73
     hoops
    0.72
     flares
    0.72
     balls
    0.71
    aukee
    0.71
    Act Density 0.016%

    No Known Activations