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

    Neuronpedia

    INDEX
    Explanations

    phrases related to breaking or disruption

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "broke."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulp
    -0.66
    umatic
    -0.65
    apixel
    -0.65
    atures
    -0.64
    ogical
    -0.63
    alty
    -0.62
    alogy
    -0.61
    oran
    -0.61
    uther
    -0.61
    metics
    -0.60
    POSITIVE LOGITS
     broke
    1.11
    break
    0.86
    breaks
    0.86
     breaks
    0.83
     break
    0.83
    neck
    0.77
    owship
    0.74
    breakers
    0.72
    rael
    0.72
     broken
    0.72
    Act Density 0.013%

    No Known Activations