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

    Neuronpedia

    INDEX
    Explanations

    references to different types of halls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.21
    yah
    -0.19
    yk
    -0.17
    emia
    -0.17
    eval
    -0.17
    emple
    -0.17
    ect
    -0.17
    excel
    -0.17
    ovich
    -0.17
    ãĥ¼
    -0.16
    POSITIVE LOGITS
    iday
    0.32
    ways
    0.29
    marks
    0.25
    oran
    0.22
    ows
    0.21
    ships
    0.20
    iard
    0.20
    ibur
    0.20
    igram
    0.19
    ignment
    0.18
    Act Density 0.035%

    No Known Activations