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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'liberal'

    oai_token-act-pair · gpt-3.5-turbo

    references to liberal ideology and related political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.86
    Downloadha
    -0.82
    pty
    -0.75
    âĵĺ
    -0.74
    AUT
    -0.73
    upon
    -0.72
    agn
    -0.72
    ADRA
    -0.70
    Pause
    -0.69
    RIP
    -0.68
    POSITIVE LOGITS
     arts
    1.03
    ization
    0.98
    izing
    0.92
     enclave
    0.91
    ized
    0.88
    izes
    0.88
     bloc
    0.87
    izers
    0.85
    izer
    0.83
     activist
    0.80
    Act Density 0.014%

    No Known Activations