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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical or statistical matrix concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]")]
    -0.39
    Monkey
    -0.37
     Father
    -0.36
    URLs
    -0.36
    wards
    -0.36
    TextWatcher
    -0.35
     phone
    -0.35
     lit
    -0.35
     mug
    -0.35
     Monkey
    -0.34
    POSITIVE LOGITS
     matrix
    1.88
     matrices
    1.67
     Matrix
    1.63
    matrix
    1.58
    Matrix
    1.52
     MATRIX
    1.49
    矩阵
    1.45
     Matrices
    1.41
     матри
    1.39
     matriz
    1.38
    Act Density 1.085%

    No Known Activations