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

    Neuronpedia

    INDEX
    Explanations

    references to explosions or explosive events

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     rând
    -0.76
     Normdatei
    -0.72
     déchir
    -0.66
     Lari
    -0.64
     chargés
    -0.62
     rê
    -0.61
    vail
    -0.58
     fiebre
    -0.58
     zape
    -0.58
     rêver
    -0.58
    POSITIVE LOGITS
     Explosion
    1.38
     explosion
    1.35
     explosions
    1.35
     exploded
    1.17
     Explo
    1.10
     exploding
    1.06
     explodes
    1.05
     explode
    1.05
     explosives
    1.02
    explosion
    1.01
    Act Density 0.007%

    No Known Activations