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

    Neuronpedia

    INDEX
    Explanations

    various types of mathematical forms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zed
    -0.16
    izi
    -0.15
    kees
    -0.15
    scri
    -0.15
    dy
    -0.15
    ucc
    -0.14
     cosa
    -0.14
    sav
    -0.14
    ena
    -0.14
     Sab
    -0.14
    POSITIVE LOGITS
    istrov
    0.17
    oug
    0.16
    imizer
    0.16
    λει
    0.15
    ality
    0.15
    atsu
    0.15
    ost
    0.15
    ovat
    0.14
     Gors
    0.14
    ulates
    0.14
    Act Density 0.045%

    No Known Activations