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

    Neuronpedia

    INDEX
    Explanations

    references to opponents and competition

    oai_token-act-pair · gpt-3.5-turbo

    references to an opponent in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olia
    -0.73
    ocratic
    -0.68
     Revival
    -0.67
    med
    -0.65
    acca
    -0.64
    gres
    -0.64
    âĵĺ
    -0.64
     Sabha
    -0.64
    MER
    -0.63
    âĸĪâĸĪâĸĪâĸĪ
    -0.62
    POSITIVE LOGITS
     batters
    0.96
     opponent
    0.89
     foe
    0.83
    onent
    0.82
    pport
    0.78
     opponents
    0.76
     combatants
    0.76
     vanquished
    0.72
    hesis
    0.70
     hitters
    0.66
    Act Density 0.032%

    No Known Activations