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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ³
    -0.17
    onus
    -0.16
    shm
    -0.16
    ean
    -0.15
    oran
    -0.14
     isNaN
    -0.14
     Bail
    -0.14
    inos
    -0.13
    èģ
    -0.13
    bab
    -0.13
    POSITIVE LOGITS
    cka
    0.15
    æª
    0.15
    uptime
    0.14
    .Horizontal
    0.14
    AspNet
    0.14
    object
    0.13
    otas
    0.13
    DST
    0.13
    uraa
    0.13
    etable
    0.13
    Act Density 0.000%

    No Known Activations