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

    Neuronpedia

    INDEX
    Explanations

    phrases that express repetitiveness or redundancy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    yet another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     teda
    -0.32
     lidé
    -0.31
    怎麼辦
    -0.30
     preciso
    -0.30
    Географиясе
    -0.29
     potřeb
    -0.28
     quizá
    -0.28
     terutama
    -0.28
     kvůli
    -0.28
     вдруг
    -0.27
    POSITIVE LOGITS
     another
    0.73
    expandindo
    0.66
     ANOTHER
    0.65
    another
    0.64
    IZABETH
    0.59
    __(/*!
    0.57
    IsMutable
    0.57
    interopRequire
    0.57
    Another
    0.57
     Another
    0.57
    Act Density 0.013%

    No Known Activations