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

    Neuronpedia

    INDEX
    Explanations

    articles or quantifiers preceding nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yps
    -0.15
    £½
    -0.15
    uese
    -0.14
    ãĤŃãĥ¥
    -0.14
    ystem
    -0.14
    FINE
    -0.14
    ulumi
    -0.14
    ãģĹãģ¾
    -0.14
    γον
    -0.13
    ystems
    -0.13
    POSITIVE LOGITS
     actionTypes
    0.14
    (Stack
    0.14
     nisi
    0.14
    -depth
    0.14
    leet
    0.14
    оÑĤÑĮ
    0.14
    .Lock
    0.14
    USA
    0.14
     Mane
    0.14
    ÑĸÑĪ
    0.13
    Act Density 0.021%

    No Known Activations