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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns and possessive forms of nouns

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

    possessive nouns or contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.59
    RenderAtEndOf
    -0.52
     CreateTagHelper
    -0.43
    ValueGeneration
    -0.42
    spania
    -0.39
    sizeCache
    -0.39
    matchCondition
    -0.38
    PreInfinity
    -0.38
    ⤹
    -0.38
    depend
    -0.37
    POSITIVE LOGITS
     gonna
    1.04
     afraid
    0.91
     blevet
    0.90
     not
    0.87
     been
    0.83
    gonna
    0.82
     going
    0.80
     gone
    0.77
     trying
    0.75
     got
    0.71
    Act Density 0.039%

    No Known Activations