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

    Neuronpedia

    INDEX
    Explanations

    words related to various countries

    oai_token-act-pair · gpt-3.5-turbo

    words related to wealth and affluent individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonexistent
    -0.67
     otherwise
    -0.67
     obs
    -0.64
     slow
    -0.63
     INS
    -0.59
     kan
    -0.58
     mol
    -0.58
     Inf
    -0.57
     orth
    -0.57
     ramp
    -0.56
    POSITIVE LOGITS
    aire
    4.94
    aires
    3.37
    naire
    2.35
    naires
    1.40
    ary
    1.39
    airs
    1.33
    air
    1.32
    aries
    1.26
    arie
    1.25
    ario
    1.24
    Act Density 0.014%

    No Known Activations