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

    Neuronpedia

    INDEX
    Explanations

    words related to fire incidents or blazes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fire incidents and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rasmussen
    -0.83
     McCull
    -0.77
     Sens
    -0.77
    subject
    -0.70
     Hus
    -0.65
     subjects
    -0.62
     gif
    -0.62
     subject
    -0.62
    McC
    -0.61
     Subjects
    -0.61
    POSITIVE LOGITS
     blaze
    2.72
    orate
    1.48
    rote
    1.27
     decorations
    1.18
    aret
    1.17
    orb
    1.14
     blazing
    1.13
     decoration
    1.12
     wildfire
    1.06
     wildfires
    1.01
    Act Density 0.063%

    No Known Activations