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

    Neuronpedia

    INDEX
    Explanations

    references to fire or flames

    oai_token-act-pair · gpt-3.5-turbo

    references to fire and flames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alian
    -0.88
    alth
    -0.83
    nai
    -0.82
    ettings
    -0.80
    riad
    -0.75
    ournal
    -0.73
    guyen
    -0.72
    States
    -0.70
    chant
    -0.70
    Roberts
    -0.69
    POSITIVE LOGITS
     flame
    1.05
    flies
    1.02
     retard
    1.02
     extinguished
    0.91
     flames
    0.89
    orescence
    0.88
     torches
    0.83
     hotter
    0.83
     furnace
    0.82
     torch
    0.82
    Act Density 0.020%

    No Known Activations