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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conflicts or disruptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "broke," particularly in contexts related to conflicts or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alogy
    -0.66
    erva
    -0.65
    ulp
    -0.64
    etheless
    -0.64
    idency
    -0.63
    essee
    -0.61
    onz
    -0.61
    metics
    -0.60
    anto
    -0.60
    oran
    -0.60
    POSITIVE LOGITS
    neck
    0.92
     broke
    0.89
    breaks
    0.87
    owship
    0.80
    red
    0.78
    break
    0.77
    LEASE
    0.77
     break
    0.77
     breaks
    0.76
    breakers
    0.74
    Act Density 0.014%

    No Known Activations