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

    Neuronpedia

    INDEX
    Explanations

    references to accidents, explosions, and incidents involving disasters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Anhalt
    -0.49
     الحره
    -0.49
    Cot
    -0.46
    widual
    -0.45
    הח
    -0.45
    Campe
    -0.44
     Trin
    -0.44
     Benin
    -0.44
    bernate
    -0.44
    фициаль
    -0.43
    POSITIVE LOGITS
     explosion
    1.08
     explosions
    1.04
    explosion
    0.97
     explodes
    0.96
     explode
    0.96
     ftre
    0.95
     exploding
    0.95
     Explo
    0.94
     fays
    0.94
     Explosion
    0.91
    Act Density 0.092%

    No Known Activations