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

    Neuronpedia

    INDEX
    Explanations

    references to the general public or population

    oai_token-act-pair · gpt-3.5-turbo

    references to the general public or common societal sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄŁ
    -0.78
    Fax
    -0.71
    Diamond
    -0.70
     Incarn
    -0.70
     Tycoon
    -0.70
    XL
    -0.69
    lda
    -0.69
    vana
    -0.68
    ï¸
    -0.68
     Manz
    -0.68
    POSITIVE LOGITS
    izations
    1.24
     relativity
    1.09
    ization
    1.04
    isations
    1.02
    ignment
    0.99
    ities
    0.99
    isation
    0.96
     aviation
    0.94
    izing
    0.94
    ised
    0.92
    Act Density 0.029%

    No Known Activations