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

    Neuronpedia

    INDEX
    Explanations

    references to fire and firefighting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.81
    DockStyle
    -0.75
     للمعارف
    -0.70
    <unused14>
    -0.70
    <unused52>
    -0.70
    [@BOS@]
    -0.70
    <unused28>
    -0.70
    <unused79>
    -0.70
    <unused3>
    -0.69
    <unused8>
    -0.69
    POSITIVE LOGITS
     fire
    1.22
     Fire
    1.17
    Fire
    1.08
     burning
    1.02
     FIRE
    0.99
     incendio
    0.96
    fire
    0.96
     flame
    0.95
     Burning
    0.94
     flames
    0.93
    Act Density 0.327%

    No Known Activations