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

    Neuronpedia

    INDEX
    Explanations

    numerical values or ratings related to a scoring system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukes
    -0.16
    lav
    -0.16
    alse
    -0.15
    reu
    -0.15
     Lever
    -0.15
    ги
    -0.14
    ä¸ĸ
    -0.14
    ÙħاÙĦ
    -0.14
    RITE
    -0.14
    ritten
    -0.14
    POSITIVE LOGITS
    ãģªãģĮ
    0.15
    adium
    0.15
    iard
    0.14
    egra
    0.13
    errupted
    0.13
    teenth
    0.13
    ãĥīãĥ©
    0.13
    iani
    0.13
    GPC
    0.13
    loyd
    0.13
    Act Density 0.001%

    No Known Activations