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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "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
    nee
    -0.84
    zee
    -0.74
    vern
    -0.72
    ocide
    -0.71
    lege
    -0.69
    ele
    -0.68
    sole
    -0.67
    CE
    -0.66
    wait
    -0.66
    vo
    -0.65
    POSITIVE LOGITS
     fireworks
    1.38
    aurus
    0.85
     displays
    0.80
     unlaw
    0.80
    avorite
    0.73
     decorations
    0.72
     champagne
    0.71
     explode
    0.71
    ModLoader
    0.71
     display
    0.70
    Act Density 0.005%

    No Known Activations