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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "be" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mana
    -0.17
    esar
    -0.17
    leta
    -0.15
    legg
    -0.15
    ecal
    -0.14
     Pan
    -0.14
    çĽ
    -0.14
     pan
    -0.14
     trope
    -0.14
    quier
    -0.13
    POSITIVE LOGITS
    beh
    0.15
     yet
    0.15
    ienne
    0.15
    ÏĥÏĦαν
    0.15
    akan
    0.14
    пов
    0.14
    iele
    0.14
    ols
    0.14
    jist
    0.14
     kli
    0.14
    Act Density 0.000%

    No Known Activations