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

    Neuronpedia

    INDEX
    Explanations

    references to tests and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heid
    -0.16
    smith
    -0.15
    TestFixture
    -0.15
    iser
    -0.15
    teen
    -0.15
    alty
    -0.15
    zon
    -0.14
    elves
    -0.14
    izont
    -0.14
    itecture
    -0.14
    POSITIVE LOGITS
    imonials
    0.19
    osterone
    0.18
    imonial
    0.18
    ovacÃŃ
    0.18
    imony
    0.17
    isOk
    0.16
    .UnitTesting
    0.16
    chio
    0.15
    еб
    0.15
    icles
    0.15
    Act Density 0.065%

    No Known Activations