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

    Neuronpedia

    INDEX
    Explanations

    expressions of extreme preferences or comparisons involving life and marriage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    better than, rather than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.49
     propOrder
    -0.43
     Simpli
    -0.41
     intptr
    -0.41
    JsonPropertyName
    -0.40
     Matéri
    -0.39
     endfor
    -0.38
    Trie
    -0.38
     newList
    -0.37
     tyle
    -0.37
    POSITIVE LOGITS
     préfère
    0.50
    awtextra
    0.49
    Than
    0.49
     estekak
    0.45
     فريبيس
    0.44
    enumii
    0.43
     préfé
    0.42
     than
    0.41
    ╕
    0.41
    empty
    0.40
    Act Density 0.032%

    No Known Activations