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

    Neuronpedia

    INDEX
    Explanations

    references to test files or test-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mlink
    -0.16
    orm
    -0.15
    rib
    -0.15
    397
    -0.15
    492
    -0.15
    ãģĵãģĨ
    -0.14
     Ne
    -0.14
     constitution
    -0.14
    box
    -0.14
    urs
    -0.14
    POSITIVE LOGITS
    ouro
    0.18
    ossal
    0.17
     Hüs
    0.15
    IPH
    0.15
    ÐŁÐļ
    0.15
    jf
    0.15
    tember
    0.15
    DDS
    0.15
    ibold
    0.15
    myModal
    0.15
    Act Density 0.036%

    No Known Activations