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

    Neuronpedia

    INDEX
    Explanations

    references to advertisements and advertising-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NUKAT
    -0.59
    DockStyle
    -0.56
     Caine
    -0.53
    зю
    -0.52
     कोशिश
    -0.51
     Himo
    -0.49
    ที่มา
    -0.48
     sabem
    -0.47
    principalTable
    -0.47
     Infirmary
    -0.47
    POSITIVE LOGITS
     Ad
    1.69
    Ad
    1.51
     ad
    1.33
     Ads
    0.95
    idiary
    0.79
     Adj
    0.78
    ]--;
    0.78
    Ads
    0.75
     Ад
    0.75
     ads
    0.74
    Act Density 0.075%

    No Known Activations