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

    Neuronpedia

    INDEX
    Explanations

    mentions of email notifications or registration forms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.46
    ⓧ
    -0.56
    MemoryWarning
    -0.56
    Referencie
    -0.55
    Iné
    -0.54
     бъ
    -0.54
    RectangleBorder
    -0.52
    <?
    -0.52
    Vanjske
    -0.51
    @[+][
    -0.51
    POSITIVE LOGITS
     lele
    1.03
     chèvre
    0.89
     Manufact
    0.89
     thuy
    0.86
     notification
    0.84
     sirup
    0.84
     withal
    0.83
     Aéroport
    0.83
     toul
    0.82
     myn
    0.82
    Act Density 0.401%

    No Known Activations