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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to technology and geography

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ü
    -0.59
    achine
    -0.57
    NRS
    -0.56
    wcs
    -0.56
     ACTIONS
    -0.55
    answered
    -0.53
    à¹
    -0.52
    ESA
    -0.52
    Reviewed
    -0.52
    aroo
    -0.51
    POSITIVE LOGITS
     Dragonbound
    0.67
    ateral
    0.61
    ument
    0.60
     Oo
    0.59
    uala
    0.59
    romy
    0.57
    redd
    0.55
    ajo
    0.53
    uments
    0.53
    ĸļ
    0.53
    Act Density 0.985%

    No Known Activations