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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interactive experiences and activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.95
    /***
    -0.80
    /*++
    -0.68
    <?
    -0.68
    HasAnnotation
    -0.63
    Vegeu
    -0.61
    DeleteMapping
    -0.60
     Савезне
    -0.60
    件事情
    -0.60
    ///**
    -0.58
    POSITIVE LOGITS
     Juf
    1.33
     stockholm
    1.32
     affor
    1.30
     Intere
    1.23
     Middles
    1.23
     scrat
    1.22
     Eft
    1.21
     Augu
    1.21
     desir
    1.16
     panama
    1.16
    Act Density 0.093%

    No Known Activations