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

    Neuronpedia

    INDEX
    Explanations

    references to explosive devices like bombs

    oai_token-act-pair · gpt-3.5-turbo

    references to explosive devices, specifically bombs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iors
    -0.86
    eways
    -0.83
    IOR
    -0.73
    eway
    -0.72
     Riding
    -0.72
     Owners
    -0.71
    winter
    -0.71
     Cullen
    -0.70
    owners
    -0.70
    ivia
    -0.69
    POSITIVE LOGITS
     bomb
    3.79
     bombs
    2.86
    bomb
    2.57
     Bomb
    2.35
    Bomb
    2.16
     bombing
    2.02
     Bombs
    1.97
     bomber
    1.84
     bombings
    1.82
     bombed
    1.80
    Act Density 0.014%

    No Known Activations