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

    Neuronpedia

    INDEX
    Explanations

    phrases centered around the concept of discussing or talking about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.67
    <?
    -0.74
    /**
    -0.71
    /***
    -0.68
    ⓧ
    -0.68
    ///**
    -0.66
    
    -0.61
    font
    -0.59
    /*++
    -0.57
    <?
    -0.57
    POSITIVE LOGITS
     bandung
    1.43
     sovere
    1.36
     Minang
    1.35
     lidl
    1.32
     Juf
    1.32
     autunno
    1.31
     eiffel
    1.30
     affor
    1.28
     Czechos
    1.27
     milano
    1.27
    Act Density 0.161%

    No Known Activations