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

    Neuronpedia

    INDEX
    Explanations

    references to availability, release, and services related to products or software

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    fet
    -0.91
    ritical
    -0.90
    cig
    -0.90
    tal
    -0.90
    vous
    -0.89
    Bre
    -0.88
    sty
    -0.88
    orio
    -0.88
    eur
    -0.86
    ilde
    -0.86
    POSITIVE LOGITS
     ILCS
    0.89
     reversible
    0.87
     separately
    0.87
     NX
    0.87
     DISTR
    0.86
     here
    0.85
    OUP
    0.83
     legally
    0.83
     through
    0.82
     electronically
    0.82
    Act Density 0.757%

    No Known Activations