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

    Neuronpedia

    INDEX
    Explanations

    mentions of rumors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rumors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athetic
    -0.88
    iterranean
    -0.73
    arching
    -0.70
    ais
    -0.68
    ells
    -0.67
    aque
    -0.67
    abus
    -0.66
    otent
    -0.66
    ACP
    -0.65
    orney
    -0.65
    POSITIVE LOGITS
     rumors
    1.47
     rumor
    1.30
     rumours
    1.29
    Rum
    1.04
     rumored
    0.96
     speculation
    0.90
     Rum
    0.89
     whispers
    0.88
     gossip
    0.87
     sightings
    0.86
    Act Density 0.021%

    No Known Activations