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

    Neuronpedia

    INDEX
    Explanations

    URLs in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endencies
    -0.15
    Äįe
    -0.15
    ]={↵
    -0.15
    ump
    -0.14
    nbsp
    -0.14
    .hh
    -0.14
    hausen
    -0.14
    luet
    -0.13
     fits
    -0.13
    azor
    -0.13
    POSITIVE LOGITS
    ://
    0.25
     Mant
    0.17
    agle
    0.16
    ynthia
    0.16
    479
    0.14
    ament
    0.14
    éŀ
    0.14
    rib
    0.13
    -Ray
    0.13
    ag
    0.13
    Act Density 0.014%

    No Known Activations