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

    Neuronpedia

    INDEX
    Explanations

    words related to explosive events

    oai_token-act-pair · gpt-3.5-turbo

    references to explosions and explosive events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nda
    -0.74
    esan
    -0.73
    orses
    -0.68
    agra
    -0.67
    appiness
    -0.65
     outsourcing
    -0.64
    ĻĤ
    -0.63
    éĸ
    -0.63
    Sense
    -0.60
    awan
    -0.59
    POSITIVE LOGITS
     furnace
    1.20
     detonated
    1.10
     fireball
    1.03
     explosions
    1.01
    hower
    1.00
     ignition
    0.97
     explosion
    0.97
     furn
    0.96
     deton
    0.95
     grenades
    0.92
    Act Density 0.101%

    No Known Activations