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

    Neuronpedia

    INDEX
    Explanations

    references to historic and cultural landmarks or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zatÃŃm
    -0.17
    AGAIN
    -0.14
    abaj
    -0.14
    γι
    -0.14
    eldom
    -0.14
    ilib
    -0.13
    ellido
    -0.13
    udden
    -0.13
    åħ¶ä¸Ń
    -0.13
     ún
    -0.13
    POSITIVE LOGITS
     decades
    0.60
     years
    0.56
     back
    0.56
     way
    0.45
     centuries
    0.44
    years
    0.41
     long
    0.40
     YEARS
    0.40
     many
    0.40
     Years
    0.38
    Act Density 0.798%

    No Known Activations