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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     получают
    -0.57
     krijgt
    -0.52
     (%)
    -0.52
     Iglesias
    -0.52
     vrijwilli
    -0.50
    addPreferredGap
    -0.48
     QtCore
    -0.47
    (%)
    -0.47
    ныя
    -0.46
     alright
    -0.45
    POSITIVE LOGITS
     be
    2.18
     Be
    1.95
    Be
    1.95
    be
    1.69
     BE
    1.49
    BE
    1.21
     beryllium
    1.07
     soient
    1.04
    Bef
    1.03
    NotBe
    0.95
    Act Density 0.112%

    No Known Activations