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

    Neuronpedia

    INDEX
    Explanations

    references to religious or familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocy
    -0.15
    ibel
    -0.15
    ROC
    -0.15
    rica
    -0.15
    ayer
    -0.15
    abis
    -0.15
    rada
    -0.15
    orris
    -0.14
    errupt
    -0.14
    oca
    -0.14
    POSITIVE LOGITS
     of
    0.23
     thereof
    0.21
     của
    0.19
     od
    0.17
    /master
    0.17
    们
    0.17
    inders
    0.15
    ãĥ¼ãĤ¿
    0.15
    536
    0.14
    /client
    0.14
    Act Density 0.131%

    No Known Activations