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

    Neuronpedia

    INDEX
    Explanations

    present tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.24
     meiner
    -0.19
    æĪijçļĦ
    -0.18
     my
    -0.18
     minha
    -0.17
     meu
    -0.17
     mijn
    -0.16
    CRET
    -0.15
    ç»ĻæĪij
    -0.15
    .my
    -0.15
    POSITIVE LOGITS
     sorry
    0.24
     mere
    0.19
     so
    0.19
     firm
    0.18
     huge
    0.18
     here
    0.18
     fortunate
    0.18
     all
    0.18
     big
    0.17
     told
    0.17
    Act Density 0.075%

    No Known Activations