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

    Neuronpedia

    INDEX
    Explanations

    references to straps or strapping mechanisms in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eker
    -0.18
    ermo
    -0.15
    apolis
    -0.15
     ster
    -0.14
    erdale
    -0.14
    osa
    -0.14
     Ramp
    -0.14
    regnum
    -0.13
     CV
    -0.13
    stery
    -0.13
    POSITIVE LOGITS
    ола
    0.16
    ulator
    0.16
    lobal
    0.15
    antan
    0.15
    inner
    0.14
    ÏĦολ
    0.13
    deaux
    0.13
     Huss
    0.13
     Yue
    0.13
    oly
    0.13
    Act Density 0.004%

    No Known Activations