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

    Neuronpedia

    INDEX
    Explanations

    references to advertisements and advertising-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.88
    bred
    -0.76
    lihood
    -0.76
    otype
    -0.70
     Cyprus
    -0.69
    20439
    -0.68
     Patriarch
    -0.68
    theless
    -0.68
     Caribbean
    -0.66
     hatch
    -0.64
    POSITIVE LOGITS
    vertising
    1.22
    verts
    0.98
    vertis
    0.95
     ads
    0.94
    vertisements
    0.93
    idas
    0.93
    vertisement
    0.91
    elaide
    0.90
    strip
    0.88
    blocking
    0.84
    Act Density 0.013%

    No Known Activations