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

    Neuronpedia

    INDEX
    Explanations

    linguistic patterns and structures in non-English languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ields
    -0.16
    าà¸ĩ
    -0.14
    uilder
    -0.14
    flatMap
    -0.13
    686
    -0.13
     Monter
    -0.13
     Nobel
    -0.13
     Hughes
    -0.13
     Romance
    -0.13
    azaar
    -0.13
    POSITIVE LOGITS
    259
    0.15
    ÑĢок
    0.14
    strup
    0.14
    -capital
    0.14
     ank
    0.13
    dictions
    0.13
    ALLERY
    0.13
     intra
    0.13
    µ
    0.13
    iminal
    0.13
    Act Density 0.021%

    No Known Activations