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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "translate" and its variations, indicating a focus on translation-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ding
    -0.18
    icity
    -0.17
    des
    -0.17
    raig
    -0.17
    istol
    -0.16
    illa
    -0.15
    hole
    -0.15
    Ñģлов
    -0.15
    ÑĥÑĪ
    -0.15
    lessly
    -0.14
    POSITIVE LOGITS
    /trans
    0.27
     into
    0.23
    Into
    0.22
     Into
    0.21
    AutoresizingMaskIntoConstraints
    0.19
    into
    0.19
    -speaking
    0.18
    è¿ĩæĿ¥
    0.18
     INTO
    0.18
    oria
    0.18
    Act Density 0.018%

    No Known Activations