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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "once."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nt
    -0.17
    zem
    -0.17
    woke
    -0.14
    mise
    -0.14
    ]+$
    -0.14
    ãĥ¼ãĥĨ
    -0.14
    اÙģر
    -0.14
    .loadData
    -0.14
    ÑĤак
    -0.14
    owitz
    -0.13
    POSITIVE LOGITS
     again
    0.19
     Upon
    0.18
    upon
    0.18
    again
    0.16
    /if
    0.16
    maal
    0.16
    acre
    0.16
    unny
    0.16
    forth
    0.15
    linger
    0.15
    Act Density 0.017%

    No Known Activations