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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĨÙĩ
    -0.17
    sek
    -0.16
    soon
    -0.15
    uen
    -0.15
    taboola
    -0.14
    uais
    -0.14
    matic
    -0.14
     tavs
    -0.14
    ounce
    -0.14
    usat
    -0.14
    POSITIVE LOGITS
    auty
    0.28
    arded
    0.27
    autiful
    0.24
    ijing
    0.24
    atrix
    0.23
    asts
    0.22
    ckett
    0.21
     fore
    0.21
    aut
    0.21
    heading
    0.21
    Act Density 0.026%

    No Known Activations