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

    Neuronpedia

    INDEX
    Explanations

    elements related to classifications or types of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SWG
    -0.15
     Pond
    -0.15
    OfClass
    -0.15
    Å¡ka
    -0.14
    ndon
    -0.14
    roud
    -0.14
    acket
    -0.14
    inces
    -0.13
     Thames
    -0.13
     Judith
    -0.13
    POSITIVE LOGITS
    addir
    0.14
    -Bold
    0.14
    оÑĩка
    0.14
    EMPLARY
    0.14
    çĮª
    0.14
    kening
    0.14
    ãĤŃãĥ³ãĤ°
    0.14
    uste
    0.14
    elah
    0.14
     æĴ
    0.14
    Act Density 0.010%

    No Known Activations