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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and mathematical expressions related to scientific and engineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åħ¥ãĤĬ
    -0.16
     Ferr
    -0.15
    enco
    -0.15
    ä¾Ľ
    -0.14
     spar
    -0.14
     Holt
    -0.14
    orb
    -0.14
    .cv
    -0.14
    ull
    -0.13
    /dist
    -0.13
    POSITIVE LOGITS
    Exercise
    0.18
     Exercise
    0.18
    tsy
    0.16
    STAR
    0.16
    tractor
    0.16
     exercise
    0.16
    exercise
    0.15
    ův
    0.15
    ej
    0.14
     centr
    0.14
    Act Density 0.003%

    No Known Activations