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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.98
    Personendaten
    -0.90
     autorytatywna
    -0.89
    homonymie
    -0.86
     Numerade
    -0.85
     gyhoeddwyd
    -0.81
    cèse
    -0.81
    UnusedPrivate
    -0.77
    transQ
    -0.77
    ThroughAttribute
    -0.76
    POSITIVE LOGITS
    be
    4.22
    BE
    3.03
    Be
    2.95
     Be
    2.70
     BE
    2.52
     be
    2.21
    beh
    1.56
    bej
    1.49
    бе
    1.48
    bes
    1.47
    Act Density 0.059%

    No Known Activations