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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to various topics like history, politics, movies, and awards ceremonies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Brach
    -1.03
    #$
    -1.00
     Hebdo
    -0.95
    ++++
    -0.92
     recess
    -0.89
    FactoryReloaded
    -0.88
    NESS
    -0.86
    velt
    -0.85
     ASC
    -0.85
     IMAGES
    -0.85
    POSITIVE LOGITS
    adic
    1.50
    inally
    1.46
    inates
    1.42
     nom
    1.35
    ás
    1.34
    atis
    1.33
    atively
    1.23
     Nom
    1.23
    inate
    1.22
    ril
    1.18
    Act Density 1.595%

    No Known Activations