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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases and specific numerical references

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ebook
    -0.98
    sonian
    -0.97
    deals
    -0.91
    DragonMagazine
    -0.91
    kefeller
    -0.90
    idable
    -0.89
    reon
    -0.85
    assies
    -0.84
    alos
    -0.83
    istani
    -0.83
    POSITIVE LOGITS
     opener
    0.99
     elapsed
    0.98
     replay
    0.86
     Ago
    0.85
     stopp
    0.83
     Bees
    0.82
     clip
    0.82
     halftime
    0.77
     ILCS
    0.74
     apiece
    0.74
    Act Density 0.417%

    No Known Activations