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

    Neuronpedia

    INDEX
    Explanations

    references to academic topics and study habits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rud
    -0.18
    é¡ĺãģĦ
    -0.14
    ixer
    -0.14
     Esper
    -0.14
    resh
    -0.14
    heed
    -0.13
    rung
    -0.13
    adge
    -0.13
    길
    -0.13
    byter
    -0.13
    POSITIVE LOGITS
     revision
    0.27
     Revision
    0.27
    Revision
    0.25
     mocks
    0.23
    revision
    0.23
    _revision
    0.23
     mock
    0.21
    Mock
    0.21
     doubt
    0.20
     Mock
    0.20
    Act Density 0.027%

    No Known Activations