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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names, particularly related to people and geographical locations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.71
     ſta
    -0.66
     poffible
    -0.65
    ViewFeatures
    -0.63
     themſelves
    -0.63
    Viitteet
    -0.62
    ſelf
    -0.62
    actéristique
    -0.61
     acús
    -0.61
     Shetterly
    -0.61
    POSITIVE LOGITS
    Getenv
    0.61
    BASELINE
    0.58
     pro
    0.50
     Don
    0.45
     dAtA
    0.45
     cav
    0.44
     bas
    0.43
     "..\..\..\
    0.43
     don
    0.42
    وث
    0.42
    Act Density 0.148%

    No Known Activations