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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to mathematical computations and comparisons

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Assist
    -0.08
    car
    -0.07
    uff
    -0.07
    rome
    -0.07
    ome
    -0.07
    UFF
    -0.07
    uggy
    -0.06
    hem
    -0.06
    aux
    -0.06
    aste
    -0.06
    POSITIVE LOGITS
     resil
    0.07
    elik
    0.07
    chsel
    0.07
    ozor
    0.06
    ãĥ¼ãĥª
    0.06
    âĨIJ
    0.06
    ovah
    0.06
    ãĢĤãĢĤ↵↵
    0.06
    _FA
    0.06
    adolu
    0.06
    Act Density 0.019%

    No Known Activations