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

    Neuronpedia

    INDEX
    Explanations

    general terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "general" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸
    -0.87
    bley
    -0.85
    ÄŁ
    -0.85
    nown
    -0.73
    rette
    -0.72
    ZZ
    -0.72
     Tycoon
    -0.69
    lyn
    -0.69
    lda
    -0.68
    Diamond
    -0.68
    POSITIVE LOGITS
    izations
    1.24
     relativity
    1.02
    isations
    1.01
    ization
    0.98
    ignment
    0.96
    wealth
    0.92
    izing
    0.92
    ised
    0.89
    arily
    0.89
     aviation
    0.88
    Act Density 0.023%

    No Known Activations