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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to the reader or recipient

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iban
    -0.17
    oshi
    -0.16
    ãĥ³ãĥIJ
    -0.16
    οÏĤ
    -0.15
    odos
    -0.15
     schon
    -0.14
    ilater
    -0.14
    mailto
    -0.14
    еÑĢин
    -0.14
    æĺĮ
    -0.13
    POSITIVE LOGITS
     may
    0.19
     should
    0.18
     will
    0.17
     MUST
    0.16
     must
    0.16
     mileage
    0.16
    ustain
    0.15
     can
    0.15
     retain
    0.15
    icide
    0.15
    Act Density 0.063%

    No Known Activations