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

    Neuronpedia

    INDEX
    Explanations

    international political and geographical terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    htbp
    -0.55
     of
    -0.54
    <bos>
    -0.54
     so
    -0.53
     just
    -0.52
     for
    -0.50
     in
    -0.50
     at
    -0.50
    过期
    -0.49
     on
    -0.49
    POSITIVE LOGITS
     praktik
    1.36
     alkoh
    1.32
     keramik
    1.30
     kosme
    1.30
     antik
    1.28
     Strukt
    1.26
     konkre
    1.24
     Simult
    1.20
     silikon
    1.18
     mikrofon
    1.16
    Act Density 0.179%

    No Known Activations