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

    Neuronpedia

    INDEX
    Explanations

    technical details about software development and experimental projects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.78
    guang
    -0.56
    <?
    -0.56
    engeance
    -0.55
    Referències
    -0.51
    xiang
    -0.51
    /**
    -0.51
    qiao
    -0.49
     operate
    -0.49
     engage
    -0.49
    POSITIVE LOGITS
     CN
    1.39
     PN
    1.31
     BN
    1.28
     LN
    1.27
     Hn
    1.21
     Cn
    1.20
     DN
    1.18
     quoique
    1.18
    CN
    1.17
     GN
    1.16
    Act Density 0.256%

    No Known Activations