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

    Neuronpedia

    INDEX
    Explanations

    elements related to rules and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     all
    -0.21
     sometimes
    -0.20
     various
    -0.20
     each
    -0.20
     altogether
    -0.19
     every
    -0.19
     everywhere
    -0.19
     often
    -0.18
     Various
    -0.17
     certain
    -0.16
    POSITIVE LOGITS
     nÃło
    0.23
     кÑĢоме
    0.22
     WHATSOEVER
    0.22
     olursa
    0.20
     Äįi
    0.20
     anywhere
    0.19
     whatsoever
    0.19
     kromÄĽ
    0.17
    gne
    0.16
    aside
    0.16
    Act Density 0.220%

    No Known Activations