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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific regulations or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yapı
    -0.12
    è¾ħ
    -0.12
    728
    -0.12
    ãĤ¤ãĥ¤
    -0.11
    PCM
    -0.11
    ÑģÑĤиÑĤÑĥ
    -0.11
     gord
    -0.11
    äºĮ人
    -0.11
    @endsection
    -0.11
     introdu
    -0.11
    POSITIVE LOGITS
    ummings
    0.14
    éf
    0.14
    usan
    0.14
    -lnd
    0.14
    utterstock
    0.13
    WEEN
    0.13
    nete
    0.13
    LOPT
    0.13
    anian
    0.13
    INFRINGEMENT
    0.13
    Act Density 0.013%

    No Known Activations