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

    Neuronpedia

    INDEX
    Explanations

    references to coding parameters and variables in programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agit
    -0.16
    orsi
    -0.15
    abay
    -0.14
    irc
    -0.14
    ordin
    -0.14
    ãĤħ
    -0.14
    tee
    -0.14
    iani
    -0.14
     Wert
    -0.14
    away
    -0.13
    POSITIVE LOGITS
    à¸Ńส
    0.14
    hx
    0.14
    asmus
    0.14
    ubber
    0.13
    ãĥĭãĥ¼
    0.13
    ç·Ĵ
    0.13
     Conserv
    0.13
     Kang
    0.13
    naire
    0.13
    alties
    0.13
    Act Density 0.028%

    No Known Activations