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

    Neuronpedia

    INDEX
    Explanations

    references to the Boost software library

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     Transform
    -0.82
    /******/
    -0.79
     transform
    -0.75
    transform
    -0.75
    Transform
    -0.74
     transformed
    -0.73
     transforms
    -0.72
     transformation
    -0.70
    transformed
    -0.69
     Transformations
    -0.68
    POSITIVE LOGITS
    boost
    2.00
    Boost
    1.02
     Boost
    0.70
    booster
    0.70
    awtextra
    0.60
     boosters
    0.60
    nalpot
    0.56
    Архівовано
    0.55
     cauza
    0.53
     booster
    0.51
    Act Density 0.002%

    No Known Activations