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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.22
    Ùĩ
    -0.17
    tti
    -0.16
    ÑĮ
    -0.16
    ilden
    -0.15
    vido
    -0.15
    нг
    -0.15
    YNAM
    -0.15
    owski
    -0.14
    igner
    -0.14
    POSITIVE LOGITS
    richt
    0.14
    amp
    0.14
    ment
    0.13
    fluence
    0.13
    them
    0.13
    imately
    0.13
    mate
    0.13
    ãĥ¼ãĥĸ
    0.13
     Evelyn
    0.13
    ripp
    0.13
    Act Density 0.025%

    No Known Activations