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

    Neuronpedia

    INDEX
    Explanations

    references to fire or burning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.71
     Jacobsen
    -0.71
     utafitiHapana
    -0.68
     EClass
    -0.67
     vario
    -0.66
     Vario
    -0.65
     betweenstory
    -0.65
    μιουργ
    -0.65
    ostante
    -0.65
    GOTREF
    -0.65
    POSITIVE LOGITS
     fire
    3.75
     Fire
    3.46
    Fire
    3.39
    fire
    3.32
     FIRE
    3.15
    FIRE
    2.99
     fires
    2.80
    fires
    2.49
     Fires
    2.37
     fuego
    2.24
    Act Density 0.028%

    No Known Activations