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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal conditions or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Keuangan
    -0.67
     Jenderal
    -0.60
     Komunikasi
    -0.58
     Kebijakan
    -0.54
     Masyarakat
    -0.54
     Umum
    -0.52
     Hitam
    -0.50
     Pemerintah
    -0.50
    ințe
    -0.49
     Informasi
    -0.49
    POSITIVE LOGITS
    脚注の使い方
    0.80
     propOrder
    0.75
     And
    0.65
     Of
    0.65
    Билгалдахарш
    0.63
    ArgsConstructor
    0.61
    tvguidetime
    0.61
     Or
    0.61
    Спасылкі
    0.59
    endpush
    0.59
    Act Density 0.370%

    No Known Activations