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

    Neuronpedia

    INDEX
    Explanations

    words associated with identity and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    **
    -0.13
    avatar
    -0.13
    âĢĮ
    -0.12
    wiÄħ
    -0.12
    exit
    -0.12
    еÑĤелÑĮ
    -0.12
    -
    -0.12
    OrNull
    -0.11
    orama
    -0.11
    anmar
    -0.11
    POSITIVE LOGITS
    /Foundation
    0.15
    /Framework
    0.14
    ongyang
    0.13
    !=-
    0.13
    026
    0.13
    ecko
    0.13
     BITTE
    0.13
    lessly
    0.12
    ebo
    0.12
    nts
    0.12
    Act Density 1.923%

    No Known Activations