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

    Neuronpedia

    INDEX
    Explanations

    phrases related to destruction and criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.78
    travel
    -0.73
    duino
    -0.70
    uana
    -0.69
    rouse
    -0.67
    omez
    -0.66
    ele
    -0.64
    Track
    -0.64
    zbek
    -0.63
    isure
    -0.63
    POSITIVE LOGITS
     havoc
    1.06
     wrought
    0.97
     rubble
    0.90
    adoes
    0.89
     wreckage
    0.85
     wrecked
    0.81
    ember
    0.79
     remnants
    0.79
     ruins
    0.78
     furnace
    0.78
    Act Density 1.263%

    No Known Activations