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

    Neuronpedia

    INDEX
    Explanations

    phrases containing a specific symbol or character

    oai_token-act-pair · gpt-3.5-turbo

    phrases or concepts related to significant social issues or ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.88
     Shroud
    -0.74
     ABE
    -0.70
     shroud
    -0.68
     Squirrel
    -0.68
     Ascension
    -0.68
    creen
    -0.67
     Feder
    -0.66
     Skydragon
    -0.65
     Statistics
    -0.63
    POSITIVE LOGITS
    Ķ
    1.18
    ł
    1.10
    IJ
    1.10
    ¹
    1.06
    ª
    1.05
    «
    1.04
    ľ
    1.01
    Ĵ
    1.01
    ĺ
    0.97
    ¬
    0.97
    Act Density 0.045%

    No Known Activations