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
     Nero
    -0.67
     Moro
    -0.64
     Apollo
    -0.62
    ugian
    -0.62
     kina
    -0.59
    globin
    -0.58
    databind
    -0.58
    pollo
    -0.58
     Sixt
    -0.57
    CloseOperation
    -0.57
    POSITIVE LOGITS
    didSet
    0.70
     appelez
    0.68
    principalColumn
    0.67
     StatelessWidget
    0.66
     the
    0.66
     disambiguazione
    0.65
     коп
    0.62
    Wass
    0.61
    rifice
    0.59
     that
    0.59
    Act Density 0.246%

    No Known Activations