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

    Neuronpedia

    INDEX
    Explanations

    adjectives and adverbs that emphasize qualities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.04
    /*!
    -0.92
    <?
    -0.89
    ⓧ
    -0.88
    /***
    -0.88
    
    -0.84
    /**
    -0.81
    <?
    -0.78
    fputs
    -0.69
    /*++
    -0.66
    POSITIVE LOGITS
     bandung
    1.30
     Minang
    1.28
     jaya
    1.25
     lele
    1.23
     jawa
    1.16
     surabaya
    1.06
     seksi
    1.05
     malang
    1.04
     vne
    1.03
     alip
    1.01
    Act Density 0.734%

    No Known Activations