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

    Neuronpedia

    INDEX
    Explanations

    descriptive articles or forms of the verb "to be" in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.17
     pleaſure
    -1.15
     Chriftian
    -1.14
     ſtate
    -1.13
     itſelf
    -1.13
     ſever
    -1.10
     houſe
    -1.10
     ſeveral
    -1.10
     dafs
    -1.09
     Monfieur
    -1.07
    POSITIVE LOGITS
     a
    1.09
     is
    1.02
     è
    1.00
     be
    0.99
     ist
    0.93
     là
    0.86
     an
    0.83
     suis
    0.83
     Is
    0.82
     part
    0.82
    Act Density 0.014%

    No Known Activations