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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imore
    -0.20
    ternet
    -0.15
    zburg
    -0.15
    gon
    -0.14
    omite
    -0.14
    owski
    -0.14
    idla
    -0.13
    æĤŁ
    -0.13
    meli
    -0.13
    ichni
    -0.13
    POSITIVE LOGITS
     quick
    0.28
     unable
    0.24
     able
    0.23
     slow
    0.23
    unable
    0.22
     instrumental
    0.22
     silent
    0.20
     successful
    0.19
    quick
    0.19
     sued
    0.19
    Act Density 0.145%

    No Known Activations