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

    Neuronpedia

    INDEX
    Explanations

    the verb "to be" in various forms and related verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.90
     Transvaal
    -0.84
     poffible
    -0.79
     Económica
    -0.78
     Dure
    -0.78
     moschino
    -0.77
    uidado
    -0.76
    хьтан
    -0.76
     soñ
    -0.76
     Avignon
    -0.74
    POSITIVE LOGITS
     be
    1.05
     have
    0.90
     also
    0.78
     make
    0.75
     not
    0.68
     
    0.68
     a
    0.66
     do
    0.63
     start
    0.59
     them
    0.59
    Act Density 0.306%

    No Known Activations