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

    Neuronpedia

    INDEX
    Explanations

    a pattern related to subscription or signing up for something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Iš
    -0.69
     Į
    -0.64
    
    -0.62
     robus
    -0.61
     bēr
    -0.61
     habet
    -0.61
    Katso
    -0.60
     ļ
    -0.60
     šķ
    -0.59
     potest
    -0.57
    POSITIVE LOGITS
     disreg
    0.59
     chré
    0.59
     pathfinder
    0.58
     thank
    0.56
    <bos>
    0.56
     wrangler
    0.55
     lakers
    0.55
     bytu
    0.55
     DONOR
    0.55
     cryst
    0.54
    Act Density 0.051%

    No Known Activations