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

    Neuronpedia

    INDEX
    Explanations

    references to fire and firefighting activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fire
    -0.65
    fire
    -0.55
     חיצוניים
    -0.51
     Fire
    -0.49
    Fire
    -0.49
     fires
    -0.49
     FIRE
    -0.48
    FIRE
    -0.47
    eluarkan
    -0.42
     fired
    -0.41
    POSITIVE LOGITS
    cracker
    0.74
    flies
    0.71
    crackers
    0.70
    nze
    0.60
    storm
    0.58
    starter
    0.58
    fly
    0.56
    fights
    0.54
    fight
    0.52
    truck
    0.52
    Act Density 0.134%

    No Known Activations