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

    Neuronpedia

    INDEX
    Explanations

    reverences to historical events and notable figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    undy
    -0.67
    und
    -0.65
    ãģ®å
    -0.64
    è¦ļéĨĴ
    -0.63
    Offline
    -0.62
     Manufact
    -0.61
    âĢ¢âĢ¢
    -0.60
    priv
    -0.59
     Forty
    -0.59
    ixt
    -0.59
    POSITIVE LOGITS
     nonetheless
    1.49
     nevertheless
    1.45
     still
    1.13
     didn
    1.10
     ain
    1.09
     doesn
    1.06
    'll
    1.06
     certainly
    1.04
     did
    1.01
     shouldn
    1.01
    Act Density 0.174%

    No Known Activations