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

    Neuronpedia

    INDEX
    Explanations

    references to the quantity "some."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raud
    -0.17
    uder
    -0.17
    adece
    -0.16
    uled
    -0.15
    ãĥ¼ãĥĬ
    -0.15
    æľī人
    -0.15
    plode
    -0.14
    iteli
    -0.14
    "default
    -0.14
    neys
    -0.14
    POSITIVE LOGITS
     of
    0.24
     pretty
    0.19
     truly
    0.18
    of
    0.18
     very
    0.17
     finest
    0.17
    otta
    0.17
    pretty
    0.15
    js
    0.15
     Ñģамом
    0.15
    Act Density 0.031%

    No Known Activations