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

    Neuronpedia

    INDEX
    Explanations

    spatial prepositions and related phrases indicating location or presence

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     me
    -0.51
     for
    -0.48
    TintMode
    -0.47
    usiai
    -0.47
     esti
    -0.45
     specifically
    -0.45
     including
    -0.45
     zij
    -0.44
     let
    -0.44
     app
    -0.43
    POSITIVE LOGITS
     purpoſe
    0.92
     houſe
    0.88
    rmtree
    0.87
     Houſe
    0.84
     Theſe
    0.82
     preſent
    0.79
     Conſ
    0.79
     ſtre
    0.77
     greateſt
    0.77
     Chriſt
    0.77
    Act Density 0.113%

    No Known Activations