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

    Neuronpedia

    INDEX
    Explanations

    concepts related to trust in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivated
    -0.14
    ToFront
    -0.14
    yte
    -0.14
    affe
    -0.14
    ntax
    -0.14
    hci
    -0.14
    desk
    -0.14
     Tenn
    -0.13
    .fac
    -0.13
    prak
    -0.13
    POSITIVE LOGITS
     trust
    0.93
     Trust
    0.81
    trust
    0.80
    Trust
    0.75
     trusts
    0.71
     trusting
    0.62
     trusted
    0.57
    ä¿¡
    0.57
     trustworthy
    0.52
    trusted
    0.51
    Act Density 0.224%

    No Known Activations