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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to various cities and people

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Varoufakis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Passenger
    -0.71
    ãĢ
    -0.65
    xual
    -0.63
    manship
    -0.63
     penetration
    -0.63
     VIDEOS
    -0.60
     explan
    -0.59
     perfection
    -0.58
    İ
    -0.58
     Applicant
    -0.57
    POSITIVE LOGITS
    iety
    1.40
    ieties
    1.39
    ietal
    1.33
    ieg
    1.19
    iances
    1.05
    iola
    1.01
    ouf
    0.99
    args
    0.99
    mint
    0.92
    ious
    0.90
    Act Density 0.051%

    No Known Activations