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

    Neuronpedia

    INDEX
    Explanations

    dates, locations, and specific events or details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fta
    -1.39
     ftu
    -1.37
     thut
    -1.29
     vnt
    -1.24
     mef
    -1.24
     fte
    -1.23
     »>
    -1.23
     fup
    -1.22
     aen
    -1.20
     fign
    -1.18
    POSITIVE LOGITS
     
    0.81
    2
    0.63
     $
    0.59
    1
    0.56
     however
    0.55
     at
    0.55
     while
    0.55
     ,
    0.55
     but
    0.54
     in
    0.54
    Act Density 0.113%

    No Known Activations