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

    Neuronpedia

    INDEX
    Explanations

    financial terms and terms related to learning or education

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     maneu
    -0.64
     vry
    -0.54
     resear
    -0.52
     Oester
    -0.51
     Heere
    -0.51
     Karls
    -0.50
     fortn
    -0.50
     Öster
    -0.49
     Leip
    -0.48
     unve
    -0.48
    POSITIVE LOGITS
     susun
    0.66
     referrerpolicy
    0.65
    <bos>
    0.64
     silang
    0.62
     pagkak
    0.57
    OGND
    0.57
     and
    0.56
     siyang
    0.55
     itong
    0.54
     và
    0.53
    Act Density 0.216%

    No Known Activations