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

    Neuronpedia

    INDEX
    Explanations

    references to fire or related concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fire and flames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettings
    -0.81
    alth
    -0.79
    nai
    -0.78
    ournal
    -0.78
    alian
    -0.77
    iago
    -0.71
    Birth
    -0.70
    ortment
    -0.69
    guyen
    -0.69
    llah
    -0.69
    POSITIVE LOGITS
     flame
    1.06
    flies
    1.01
     flames
    1.00
     extinguished
    0.96
     hotter
    0.92
     retard
    0.92
     exting
    0.91
     torch
    0.90
    blast
    0.90
     licking
    0.87
    Act Density 0.019%

    No Known Activations