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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing significant quantities or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ataka
    -0.17
    leared
    -0.16
    кÑĢаÑĹ
    -0.16
    itto
    -0.15
    lingen
    -0.15
    /Foundation
    -0.15
    inspace
    -0.14
    rica
    -0.14
    kins
    -0.13
     Container
    -0.13
    POSITIVE LOGITS
    acre
    0.17
    ta
    0.17
    nard
    0.16
     Went
    0.14
    vider
    0.14
    SPELL
    0.14
     Strap
    0.14
    urally
    0.14
    antu
    0.14
    .Selenium
    0.13
    Act Density 0.003%

    No Known Activations