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

    Neuronpedia

    INDEX
    Explanations

    words related to explosions

    oai_token-act-pair · gpt-3.5-turbo

    references to explosions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nda
    -0.81
    tern
    -0.69
    hist
    -0.68
    epad
    -0.68
    ãĤ±
    -0.66
    dden
    -0.66
    ña
    -0.65
    ĻĤ
    -0.65
    travel
    -0.65
    guyen
    -0.65
    POSITIVE LOGITS
     explosion
    0.94
     explosions
    0.82
    hower
    0.82
     Explosion
    0.81
     furnace
    0.78
     furn
    0.77
     radius
    0.76
     bursting
    0.76
     burst
    0.73
     blasts
    0.73
    Act Density 0.016%

    No Known Activations