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

    Neuronpedia

    INDEX
    Explanations

    words related to writing or inscriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.75
    ⓧ
    -1.20
    /**
    -1.14
    <?
    -1.10
    
    -1.02
    /*
    -0.90
    /***
    -0.83
    /*++
    -0.77
    <?
    -0.68
    Transcripción
    -0.62
    POSITIVE LOGITS
     practition
    1.09
     maneu
    1.04
     Keny
    1.00
     Minang
    1.00
     maroc
    1.00
     disreg
    0.99
     despotism
    0.98
     Juf
    0.94
     EEU
    0.94
     shenan
    0.93
    Act Density 1.442%

    No Known Activations