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

    Neuronpedia

    INDEX
    Explanations

    prefixes associated with political or advocacy positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing pro and con perspectives on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.82
    ulhu
    -0.80
     unfocusedRange
    -0.75
     Nig
    -0.71
    çīĪ
    -0.70
     Burr
    -0.69
     Twain
    -0.68
     depths
    -0.68
     SHARES
    -0.67
     ILCS
    -0.67
    POSITIVE LOGITS
    social
    1.08
    government
    1.06
    establishment
    1.01
    sent
    0.95
    looking
    0.94
    internet
    0.93
    choice
    0.93
    sounding
    0.92
    capitalist
    0.90
    govern
    0.90
    Act Density 0.043%

    No Known Activations