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

    Neuronpedia

    INDEX
    Explanations

    technical terms and acronyms related to scientific analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egie
    -0.16
    uned
    -0.16
    adol
    -0.15
    idot
    -0.14
     Pac
    -0.14
    uhe
    -0.14
    _tests
    -0.14
    emez
    -0.14
     Decoder
    -0.14
    jee
    -0.14
    POSITIVE LOGITS
     bench
    0.22
     Cary
    0.20
     instrument
    0.20
    instrument
    0.18
     instrumental
    0.18
     spect
    0.18
    仪
    0.18
     Bench
    0.17
    ware
    0.17
     benches
    0.17
    Act Density 0.051%

    No Known Activations