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

    Neuronpedia

    INDEX
    Explanations

    themes related to trust and relationships within a community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    desk
    -0.18
    hci
    -0.16
    fleet
    -0.15
    exion
    -0.15
    agner
    -0.14
    acente
    -0.14
    prak
    -0.14
    etty
    -0.14
    oley
    -0.14
    ipay
    -0.14
    POSITIVE LOGITS
     trust
    1.00
     Trust
    0.83
    trust
    0.82
     confidence
    0.82
    Trust
    0.80
     trusts
    0.75
     faith
    0.72
     Confidence
    0.68
     trusting
    0.66
    confidence
    0.66
    Act Density 0.253%

    No Known Activations