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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "look" followed by a number or a specific phrase structure indicating a comparison

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.64
    <?
    -1.15
    ⓧ
    -0.95
    
    -0.94
    /**
    -0.92
    <?
    -0.90
    /*
    -0.86
    /***
    -0.68
    lateinit
    -0.65
    pub
    -0.59
    POSITIVE LOGITS
     maneu
    1.65
     affor
    1.60
     shenan
    1.54
     accla
    1.52
     impra
    1.50
     disreg
    1.47
     increa
    1.42
     unspeak
    1.42
     disagre
    1.41
     inev
    1.38
    Act Density 0.603%

    No Known Activations