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

    Neuronpedia

    INDEX
    Explanations

    concepts related to the interpretation and understanding of machine learning models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¥Ī
    -0.17
    lage
    -0.16
     Buen
    -0.14
    taj
    -0.14
    isky
    -0.14
    BigInteger
    -0.14
    ogram
    -0.14
    SetUp
    -0.14
    pletion
    -0.14
    platz
    -0.14
    POSITIVE LOGITS
    Explanation
    0.22
     Explanation
    0.20
     explanation
    0.19
     explanations
    0.18
     expl
    0.18
     explain
    0.18
     understandable
    0.17
    explain
    0.17
     output
    0.17
     ranked
    0.16
    Act Density 0.012%

    No Known Activations