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

    Neuronpedia

    INDEX
    Explanations

    mentions of trust and trust-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERP
    -0.17
    olics
    -0.16
    enas
    -0.15
    nip
    -0.14
    ãģŃ
    -0.14
    бав
    -0.14
    InstanceOf
    -0.14
    thon
    -0.14
    abis
    -0.14
    aab
    -0.14
    POSITIVE LOGITS
    /Foundation
    0.19
    ably
    0.15
    dl
    0.15
    ÛĮÙĩ
    0.14
    worth
    0.14
    ReturnValue
    0.14
    lama
    0.14
    uide
    0.14
     Hale
    0.14
     Maiden
    0.14
    Act Density 0.011%

    No Known Activations