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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proportions or statistical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mund
    -0.14
    CTest
    -0.14
     Eg
    -0.14
    rud
    -0.13
    icense
    -0.13
    rvine
    -0.13
    illes
    -0.13
    zell
    -0.13
    agnostic
    -0.13
    948
    -0.13
    POSITIVE LOGITS
    oplevel
    0.15
    errat
    0.14
    opal
    0.14
    /MPL
    0.14
    avax
    0.14
    avage
    0.14
    abelle
    0.14
    åij½
    0.14
    xae
    0.14
    ¯
    0.13
    Act Density 0.040%

    No Known Activations