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

    Neuronpedia

    INDEX
    Explanations

    words related to reassurance and reinforcement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reassurance and confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Horse
    -0.66
     crime
    -0.62
    netflix
    -0.62
    tis
    -0.62
     Kafka
    -0.61
    lihood
    -0.61
    ̶
    -0.61
    Fake
    -0.60
     Greeks
    -0.60
    ById
    -0.60
    POSITIVE LOGITS
    ignment
    1.20
    essment
    1.20
    urance
    1.14
    essed
    1.12
    urances
    1.09
    igned
    1.08
    ortment
    1.02
    essing
    1.00
    igning
    0.99
    imar
    0.99
    Act Density 0.040%

    No Known Activations