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

    Neuronpedia

    INDEX
    Explanations

    notations related to mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eastwood
    -0.68
     Medina
    -0.64
     Goldberg
    -0.64
     restos
    -0.62
     Hagen
    -0.62
    ondo
    -0.60
    hemia
    -0.60
     Grande
    -0.60
     verde
    -0.60
    щита
    -0.59
    POSITIVE LOGITS
    LLocation
    0.91
     Roskov
    0.89
     Sodom
    0.84
     UCI
    0.83
     reaſon
    0.81
    #\
    0.81
     Kier
    0.80
    ;\
    0.80
    BagConstraints
    0.79
     Strepto
    0.79
    Act Density 0.031%

    No Known Activations