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

    Neuronpedia

    INDEX
    Explanations

    words related to fire or passion

    oai_token-act-pair · gpt-3.5-turbo

    references to fire or fire-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vide
    -0.78
    DonaldTrump
    -0.74
    undo
    -0.74
    sembly
    -0.74
     Weld
    -0.73
    achu
    -0.70
    eters
    -0.69
     Freed
    -0.69
    atem
    -0.69
     Citizen
    -0.68
    POSITIVE LOGITS
    flies
    1.25
    storm
    1.18
    proof
    1.04
    balls
    1.02
     exting
    1.01
    fly
    1.00
    storms
    0.98
    brand
    0.97
    cakes
    0.96
    locks
    0.92
    Act Density 0.027%

    No Known Activations