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

    Neuronpedia

    INDEX
    Explanations

    words related to making promises or commitments

    oai_token-act-pair · gpt-3.5-turbo

    the word "to" in various contexts, often linked to commitment or promises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELD
    -0.73
    application
    -0.67
    quickShipAvailable
    -0.64
    ambers
    -0.64
    Application
    -0.63
    SO
    -0.62
    Reading
    -0.62
    ento
    -0.61
     Spiegel
    -0.61
    felt
    -0.60
    POSITIVE LOGITS
     donate
    1.06
     cooperate
    1.01
     uphold
    0.98
     dedicate
    0.96
     reimburse
    0.95
     improve
    0.95
     withhold
    0.92
     dismantle
    0.91
     repay
    0.91
     deliver
    0.90
    Act Density 0.081%

    No Known Activations