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

    Neuronpedia

    INDEX
    Explanations

    the word "its" and variations of possessive pronouns

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

    Ordinal numbers following "its", "his", or "the"

    np_acts-logits-general · gemini-2.0-flash

    possessive pronoun followed by ordinal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.50
    uni
    -0.47
    once
    -0.46
     einmal
    -0.46
    대로
    -0.46
     enf
    -0.45
     ấy
    -0.45
    Chham
    -0.44
    ALS
    -0.44
    mappedBy
    -0.42
    POSITIVE LOGITS
     fifth
    1.73
     fourth
    1.66
     seventh
    1.66
     sixth
    1.66
     ninth
    1.62
     eighth
    1.61
     third
    1.55
     tenth
    1.51
     eleventh
    1.47
     twelfth
    1.41
    Act Density 0.256%

    No Known Activations