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

    Neuronpedia

    INDEX
    Explanations

    references to traditional or conventional practices and approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    webtoken
    -0.15
    ses
    -0.15
     ÙĪاÙĤع
    -0.14
     Tradition
    -0.14
    ht
    -0.13
     Trad
    -0.13
    .joda
    -0.13
    -0.13
    fal
    -0.13
    anford
    -0.12
    POSITIVE LOGITS
     wisdom
    0.30
    ists
    0.27
    wis
    0.26
     Wisdom
    0.25
    ist
    0.25
    mente
    0.22
    -looking
    0.21
    -style
    0.20
    dehyde
    0.20
    izing
    0.20
    Act Density 0.038%

    No Known Activations