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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical events and actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.69
     Canaver
    -0.68
     Gould
    -0.63
    sav
    -0.63
     Nadu
    -0.63
    aths
    -0.60
    cling
    -0.58
    morph
    -0.58
    sung
    -0.58
    retched
    -0.58
    POSITIVE LOGITS
     responders
    1.28
     baseman
    1.19
     glance
    0.94
     impressions
    0.92
     blush
    0.89
     lady
    0.84
     impression
    0.82
     foray
    0.80
     glimpse
    0.78
    born
    0.77
    Act Density 0.343%

    No Known Activations