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

    Neuronpedia

    INDEX
    Explanations

    references to various indexes or tables

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.27
    ⓧ
    -0.86
    EndProject
    -0.81
    /**
    -0.80
    <?
    -0.77
    /***
    -0.67
     елның
    -0.67
    
    -0.66
     AssemblyCompany
    -0.65
    EndGlobalSection
    -0.62
    POSITIVE LOGITS
     maneu
    1.51
     bandung
    1.45
     affor
    1.42
     Minang
    1.41
     increa
    1.39
     emphat
    1.31
     stockholm
    1.31
     jacques
    1.29
     Juf
    1.29
     volunte
    1.28
    Act Density 0.051%

    No Known Activations