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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to architectural description and composition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weren
    -0.17
     sigu
    -0.16
     were
    -0.15
     Anc
    -0.15
    940
    -0.14
    ÃŃ
    -0.14
     могли
    -0.14
    æ²Ļ
    -0.14
     Arch
    -0.14
    Ïĥαν
    -0.14
    POSITIVE LOGITS
     se
    0.24
     tiene
    0.19
     is
    0.18
     está
    0.18
    :animated
    0.18
     viene
    0.18
     prov
    0.17
     ÎŃÏĩει
    0.17
     είναι
    0.16
     ÑıвлÑıеÑĤÑģÑı
    0.16
    Act Density 0.101%

    No Known Activations