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

    Neuronpedia

    INDEX
    Explanations

    references to structured events or discussions, particularly regarding policies and community impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agg
    -0.17
    irut
    -0.15
    ROKE
    -0.15
    amble
    -0.15
     Alternate
    -0.15
    rea
    -0.15
    ãĤ¢ãĥ³
    -0.14
    ance
    -0.14
    irim
    -0.14
    éļĬ
    -0.14
    POSITIVE LOGITS
    idth
    0.15
     Sm
    0.14
    çª
    0.14
    rian
    0.14
    357
    0.14
    è¯Ŀ
    0.14
    ãĥĢãĤ¤
    0.14
    quential
    0.14
    uet
    0.13
    Sm
    0.13
    Act Density 0.544%

    No Known Activations