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

    Neuronpedia

    INDEX
    Explanations

    words related to technology, computing, and financial terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     mef
    -1.22
     aen
    -1.19
     inev
    -1.17
     inder
    -1.17
     wien
    -1.14
     fuf
    -1.14
     Juf
    -1.13
     fte
    -1.11
     fta
    -1.11
     mme
    -1.09
    POSITIVE LOGITS
     easier
    0.79
     safer
    0.70
    шибка
    0.69
     alive
    0.67
     become
    0.64
     impossible
    0.63
     harder
    0.62
     profitable
    0.62
     accessible
    0.62
     make
    0.61
    Act Density 0.228%

    No Known Activations