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

    Neuronpedia

    INDEX
    Explanations

    terms related to destructive events, especially explosions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "explosion."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lege
    -0.83
    nda
    -0.77
    leg
    -0.75
    jud
    -0.75
    iff
    -0.67
    tern
    -0.66
    vag
    -0.64
    stra
    -0.64
    aunder
    -0.63
    abor
    -0.61
    POSITIVE LOGITS
     explosion
    0.97
     furnace
    0.87
     explosions
    0.87
     ignition
    0.84
     detonated
    0.83
     explodes
    0.82
     Explosion
    0.82
    hower
    0.82
     furn
    0.78
     fireball
    0.76
    Act Density 0.026%

    No Known Activations