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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or relationships

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

    possessive its characteristic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CrossRef
    -0.42
    MigrationBuilder
    -0.36
     Kruse
    -0.35
     ph
    -0.32
    ATTACH
    -0.31
    kom
    -0.31
     BOTT
    -0.31
     ju
    -0.31
    TextNode
    -0.31
    masta
    -0.31
    POSITIVE LOGITS
    whose
    1.13
     whose
    1.10
     whofe
    1.01
     whoſe
    0.95
     cuja
    0.93
     cujo
    0.91
     Whose
    0.91
     cuyo
    0.90
    Whose
    0.88
     cuya
    0.85
    Act Density 0.114%

    No Known Activations