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

    Neuronpedia

    INDEX
    Explanations

    statistical analysis and results reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.13
    /*
    -0.87
    /**
    -0.78
    <?
    -0.71
    #!/
    -0.68
     but
    -0.68
     Walkover
    -0.67
    #
    -0.67
     either
    -0.66
    CreateIndex
    -0.66
    POSITIVE LOGITS
     increa
    1.94
     affor
    1.91
     maneu
    1.90
     emphat
    1.90
     suscep
    1.87
     impra
    1.87
     resear
    1.86
     ?...
    1.84
     unlaw
    1.84
     unden
    1.80
    Act Density 0.948%

    No Known Activations