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

    Neuronpedia

    INDEX
    Explanations

    words related to explosives

    oai_token-act-pair · gpt-3.5-turbo

    words related to explosive devices and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Brow
    -0.84
    rals
    -0.72
     Mothers
    -0.67
    mor
    -0.65
    yright
    -0.65
    serv
    -0.64
     Nurs
    -0.63
    ctors
    -0.63
     cares
    -0.63
    Done
    -0.62
    POSITIVE LOGITS
     explosive
    3.73
     Explosive
    2.49
     explosives
    2.25
     incendiary
    2.01
     explos
    1.97
     Explos
    1.75
     explosion
    1.67
     exploding
    1.56
     combust
    1.53
     explode
    1.52
    Act Density 0.027%

    No Known Activations