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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "Global" at varying activation levels in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Global" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chers
    -0.83
    manship
    -0.81
    INO
    -0.76
    FUL
    -0.76
    ÄŁ
    -0.75
    oÄŁ
    -0.75
    Ô
    -0.74
    deen
    -0.74
    _-
    -0.72
    HOU
    -0.72
    POSITIVE LOGITS
    ization
    0.99
     Position
    0.88
    izing
    0.88
     warming
    0.88
    warming
    0.87
     Witness
    0.85
    izable
    0.84
     Affairs
    0.84
    isation
    0.84
     Entry
    0.81
    Act Density 0.020%

    No Known Activations