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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and complex concepts, particularly focusing on cryptocurrencies and chemical substances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hath
    -0.75
     Ake
    -0.71
    alter
    -0.68
     Cla
    -0.68
     institutions
    -0.67
    shire
    -0.67
     Barcl
    -0.66
     Lincoln
    -0.66
     Instit
    -0.65
     Governors
    -0.62
    POSITIVE LOGITS
    wave
    1.20
    aceous
    1.10
    izer
    1.08
    izers
    1.06
     vapor
    0.94
     nicotine
    0.90
    iquid
    0.89
    itate
    0.89
    iculture
    0.89
    iser
    0.88
    Act Density 0.028%

    No Known Activations