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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.67
     Anſ
    -0.65
     ſes
    -0.62
     leſs
    -0.61
    Lähteet
    -0.61
    AndroidJUnit
    -0.61
     Conſ
    -0.61
     neceſſ
    -0.61
     Reſ
    -0.61
    iſen
    -0.60
    POSITIVE LOGITS
    ToBe
    0.55
     be
    0.53
    tobe
    0.45
     бути
    0.41
     быть
    0.40
    <tr>
    0.40
    toBe
    0.39
    arynge
    0.38
    ToDo
    0.37
     להיות
    0.36
    Act Density 0.198%

    No Known Activations