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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specific phrases related to data processing and analytics

    oai_token-act-pair · gpt-3.5-turbo

    nouns and specific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Azerb
    -0.59
     Gaw
    -0.55
    ãĥ¼ãĥĨ
    -0.54
     Thompson
    -0.52
    Thompson
    -0.51
     McKay
    -0.51
    âĸ¬
    -0.51
     Corps
    -0.50
    athan
    -0.50
     Kurd
    -0.50
    POSITIVE LOGITS
    ource
    1.15
    peed
    1.04
    ystem
    1.02
    heet
    1.02
    ync
    1.01
    pace
    1.01
    ilver
    1.00
    hip
    0.97
    afety
    0.95
    etting
    0.94
    Act Density 0.172%

    No Known Activations