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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations or people

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document or the end of a thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     awa
    -0.71
     disadvant
    -0.69
    avorite
    -0.66
     proble
    -0.59
     challeng
    -0.59
     undermin
    -0.57
     unrecogn
    -0.57
     destro
    -0.56
     shove
    -0.55
     conduc
    -0.55
    POSITIVE LOGITS
    photos
    0.71
    HY
    0.62
     Contribut
    0.61
     ):
    0.58
     archive
    0.58
     Photos
    0.56
    archive
    0.55
     (@
    0.55
    º
    0.54
    ļ
    0.53
    Act Density 0.829%

    No Known Activations