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

    Neuronpedia

    INDEX
    Explanations

    statements related to legal judgments or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambre
    -0.17
    atcher
    -0.15
    ve
    -0.15
    inate
    -0.15
    omain
    -0.14
    657
    -0.14
    iran
    -0.14
    legg
    -0.13
    ожеÑĤ
    -0.13
    ester
    -0.13
    POSITIVE LOGITS
     bahwa
    0.25
     that
    0.22
     rằng
    0.18
     dass
    0.18
     ÏĮÏĦι
    0.16
     daÃŁ
    0.16
    that
    0.15
     дека
    0.15
    .scalablytyped
    0.15
    leck
    0.15
    Act Density 0.465%

    No Known Activations