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

    Neuronpedia

    INDEX
    Explanations

    references to social media professionals and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wife
    -0.17
     Families
    -0.15
    妻
    -0.15
     wife
    -0.15
    wife
    -0.15
    raud
    -0.14
    itizen
    -0.14
    ÑĦоÑĢ
    -0.14
    achment
    -0.13
    idon
    -0.13
    POSITIVE LOGITS
     Gran
    0.17
     Bip
    0.16
     halluc
    0.16
     suicidal
    0.16
     Pop
    0.15
     bipolar
    0.15
     something
    0.15
    Gran
    0.15
     text
    0.15
     herself
    0.15
    Act Density 0.009%

    No Known Activations