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

    Neuronpedia

    INDEX
    Explanations

    references to lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.76
    ⓧ
    -1.02
    /***
    -0.94
    <?
    -0.87
    
    -0.86
    //---
    -0.74
    /**
    -0.70
    <?
    -0.66
    ///**
    -0.66
     /**
    -0.66
    POSITIVE LOGITS
     list
    1.09
     kani
    1.06
     Minang
    1.05
     jawa
    1.05
     affor
    1.03
     lists
    1.01
     jati
    1.00
     jaya
    1.00
     Lists
    0.98
     maneu
    0.96
    Act Density 0.053%

    No Known Activations