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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "new."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampo
    -0.15
    ımıza
    -0.15
    994
    -0.15
    829
    -0.14
    wizard
    -0.14
    otto
    -0.14
    acea
    -0.14
    ojis
    -0.13
    ımızda
    -0.13
    -known
    -0.13
    POSITIVE LOGITS
     York
    0.27
    roz
    0.24
     England
    0.23
     Testament
    0.23
     Year
    0.23
     Deal
    0.22
     Age
    0.22
    bie
    0.22
     testament
    0.21
     Orleans
    0.21
    Act Density 0.063%

    No Known Activations