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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs, particularly those indicating completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ureau
    -0.17
    ãģ£ãģı
    -0.16
    audi
    -0.14
    pery
    -0.14
    eder
    -0.14
    iesta
    -0.14
    )throws
    -0.14
    orz
    -0.14
    oeff
    -0.13
    aeda
    -0.13
    POSITIVE LOGITS
    ollo
    0.15
    lian
    0.15
    YN
    0.15
    kas
    0.14
    deaux
    0.14
     lawful
    0.14
    254
    0.14
     tam
    0.14
    /schema
    0.14
    bro
    0.13
    Act Density 0.006%

    No Known Activations