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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aginator
    -0.15
    太éĥİ
    -0.15
    _consts
    -0.14
    cko
    -0.14
    rouch
    -0.14
    سطس
    -0.14
    å¸Ń
    -0.14
     Cool
    -0.13
    berman
    -0.13
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.13
    POSITIVE LOGITS
     Jeh
    0.15
    spb
    0.15
     att
    0.15
     organised
    0.14
    aney
    0.14
    uers
    0.14
     Jew
    0.14
    anke
    0.13
     Summers
    0.13
    еб
    0.13
    Act Density 0.082%

    No Known Activations