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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurement units or numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     urusan
    -0.31
    farwydd
    -0.27
    령
    -0.26
     wę
    -0.26
    OPLE
    -0.25
     burung
    -0.25
     espirituales
    -0.25
     almendras
    -0.25
     antemano
    -0.24
     skå
    -0.24
    POSITIVE LOGITS
     pon
    1.50
     Pon
    1.47
     Penn
    1.45
    Pon
    1.45
     Penny
    1.42
     pen
    1.40
     Пен
    1.39
    Penn
    1.38
     Pen
    1.37
     PEN
    1.37
    Act Density 1.198%

    No Known Activations