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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and results related to experimental research in machine learning and feature extraction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    709
    -0.16
     surpr
    -0.16
     picture
    -0.15
    996
    -0.14
    ores
    -0.14
     Oaks
    -0.14
    044
    -0.14
    uest
    -0.14
    ieties
    -0.13
     mechan
    -0.13
    POSITIVE LOGITS
    978
    0.15
    æµħ
    0.15
    olars
    0.15
    acebook
    0.15
     Fusion
    0.14
    輪
    0.14
    opoulos
    0.14
    uhan
    0.14
    ISIBLE
    0.14
    uzzy
    0.14
    Act Density 0.186%

    No Known Activations