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

    Neuronpedia

    INDEX
    Explanations

    numerical information or measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of assistance or help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lyn
    -0.96
    Leon
    -0.88
     Lac
    -0.87
     McInt
    -0.87
     323
    -0.85
     Lynch
    -0.83
    Diamond
    -0.82
     Lyn
    -0.82
     Lyon
    -0.81
     325
    -0.81
    POSITIVE LOGITS
    way
    1.04
     WAY
    1.03
    WAY
    1.02
     Way
    0.99
    Way
    0.97
     way
    0.89
     Hok
    0.84
     roadway
    0.81
     GO
    0.81
     Tok
    0.81
    Act Density 0.364%

    No Known Activations