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

    Neuronpedia

    INDEX
    Explanations

    statements related to trust and belief

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to trust and confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nano
    -0.78
     nano
    -0.78
    assic
    -0.70
    phalt
    -0.70
     sax
    -0.70
    irez
    -0.70
    ihu
    -0.68
     Olson
    -0.68
    ames
    -0.68
    illin
    -0.66
    POSITIVE LOGITS
     trust
    2.04
    trust
    1.82
     trusting
    1.78
    Trust
    1.71
     confidence
    1.67
     faith
    1.64
     Trust
    1.64
     belief
    1.61
     trusts
    1.61
     trusted
    1.58
    Act Density 0.378%

    No Known Activations