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

    Neuronpedia

    INDEX
    Explanations

    elements found in lists or outlines

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.76
     Canaver
    -0.65
    sav
    -0.65
    roller
    -0.64
    sung
    -0.62
    ux
    -0.61
    aths
    -0.61
     Nadu
    -0.61
    bara
    -0.61
    bos
    -0.61
    POSITIVE LOGITS
     responders
    1.26
     baseman
    1.18
     glance
    0.95
     impressions
    0.93
     blush
    0.93
     foray
    0.87
     lady
    0.85
     glimpse
    0.82
     impression
    0.82
     installment
    0.81
    Act Density 0.801%

    No Known Activations