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

    Neuronpedia

    INDEX
    Explanations

    themes related to the concepts of autonomy and individualism in societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettel
    -0.15
    illet
    -0.15
    amarin
    -0.15
    adders
    -0.14
    iscopal
    -0.14
     Decompiled
    -0.14
    earable
    -0.14
    unker
    -0.13
    ÄĽtÅ¡
    -0.13
     Brill
    -0.13
    POSITIVE LOGITS
     sup
    0.61
     supers
    0.59
     trump
    0.50
     replace
    0.43
     Sup
    0.42
     suppl
    0.41
     replaces
    0.40
     replacing
    0.39
     eclips
    0.36
     eclipse
    0.35
    Act Density 0.396%

    No Known Activations