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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fire and flames

    oai_token-act-pair · gpt-3.5-turbo

    references to fire or flames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alian
    -0.74
    nai
    -0.72
    ties
    -0.72
    sum
    -0.71
    istan
    -0.70
    laus
    -0.70
    pai
    -0.68
    Lean
    -0.67
    Birth
    -0.67
    guyen
    -0.67
    POSITIVE LOGITS
    flies
    1.02
     furnace
    0.99
     flame
    0.98
     hotter
    0.96
     flames
    0.92
     extinguished
    0.89
     extingu
    0.87
     exting
    0.87
    balls
    0.86
     ashes
    0.86
    Act Density 0.051%

    No Known Activations