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

    Neuronpedia

    INDEX
    Explanations

    concepts related to trust and reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fleet
    -0.15
    affe
    -0.15
    oplay
    -0.15
    zcze
    -0.14
     Hra
    -0.14
    inya
    -0.14
    .managed
    -0.14
    createClass
    -0.14
    lion
    -0.13
    ÙģÙĩ
    -0.13
    POSITIVE LOGITS
     trust
    0.65
    trust
    0.56
     Trust
    0.54
    Trust
    0.53
     trusts
    0.47
     trusted
    0.44
     trustworthy
    0.43
    trusted
    0.42
     trusting
    0.42
    ä¿¡
    0.41
    Act Density 0.283%

    No Known Activations