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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and expressions involving functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haft
    -0.15
    yre
    -0.15
    íıIJ
    -0.14
    erc
    -0.14
    eldorf
    -0.14
    ewitness
    -0.14
    ftime
    -0.14
    loquent
    -0.14
     Antar
    -0.14
    dex
    -0.13
    POSITIVE LOGITS
    auge
    0.15
     Spiel
    0.14
    forman
    0.14
     McCl
    0.14
    461
    0.14
    \"
    0.13
    imate
    0.13
    IRROR
    0.13
     Feder
    0.13
     ration
    0.13
    Act Density 0.046%

    No Known Activations