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

    Neuronpedia

    INDEX
    Explanations

    references to measurements, statistics, and quantifiable data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MR
    -0.17
    ẫn
    -0.16
    haar
    -0.15
    bson
    -0.15
    HEADER
    -0.14
     Lands
    -0.14
     irre
    -0.14
    ãĤ¿ãĥ«
    -0.14
    ewis
    -0.14
    dz
    -0.14
    POSITIVE LOGITS
    adan
    0.17
     Ec
    0.15
    omor
    0.15
    .gwt
    0.14
     Cand
    0.14
    SEC
    0.14
    .Uri
    0.14
     crus
    0.14
    -mf
    0.14
    ugh
    0.14
    Act Density 0.018%

    No Known Activations