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

    Neuronpedia

    INDEX
    Explanations

    references to political regions and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cis
    -0.17
     Clement
    -0.15
    imuth
    -0.15
    arkan
    -0.15
    OMB
    -0.14
    cus
    -0.14
    Catch
    -0.14
     Citizenship
    -0.14
    Cum
    -0.14
    apo
    -0.14
    POSITIVE LOGITS
     capital
    0.77
     Capital
    0.64
     cap
    0.61
    capital
    0.60
    Capital
    0.56
     CAPITAL
    0.55
     capit
    0.54
    -capital
    0.53
    .cap
    0.52
    _cap
    0.51
    Act Density 0.116%

    No Known Activations