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

    Neuronpedia

    INDEX
    Explanations

    the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ser
    -0.36
    MigrationBuilder
    -0.35
     KE
    -0.35
     blink
    -0.35
     TE
    -0.34
     bel
    -0.34
    topic
    -0.34
     الاع
    -0.33
     un
    -0.33
     Mark
    -0.33
    POSITIVE LOGITS
    SequentialGroup
    0.81
    Personendaten
    0.67
    хьтан
    0.65
    __*/
    0.63
     محفوظة
    0.63
    RegressionTest
    0.61
     ویکی‌پدی
    0.60
     plufieurs
    0.59
     Jefus
    0.58
     opgenomen
    0.58
    Act Density 0.017%

    No Known Activations