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

    Neuronpedia

    INDEX
    Explanations

    descriptions of retaining certain qualities while incorporating new elements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Suppose
    -0.76
     intercepted
    -0.71
     PRESIDENT
    -0.71
     overhe
    -0.71
     worthless
    -0.70
     interceptions
    -0.68
    ulia
    -0.67
     filib
    -0.67
     papers
    -0.67
    deb
    -0.67
    POSITIVE LOGITS
     homage
    1.27
     styl
    1.07
     themes
    1.06
     minimalist
    1.05
    ampunk
    1.04
     genres
    1.04
     realism
    1.03
     genre
    1.02
     nostalgic
    1.01
     futuristic
    1.01
    Act Density 0.583%

    No Known Activations