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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to relationships and connections in various contexts

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

    possessive pronouns (their, his, her, its)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.58
    Panamoan
    -0.50
    ]]]
    -0.47
    oneofs
    -0.45
    fjspx
    -0.45
     cuillère
    -0.44
    دانشنامهٔ
    -0.44
    Архівовано
    -0.43
    WriteLiteral
    -0.42
     expect
    -0.42
    POSITIVE LOGITS
     their
    0.56
     svoje
    0.55
     swoich
    0.54
     свої
    0.54
     seus
    0.53
     ihrer
    0.52
     suas
    0.52
     his
    0.52
     अपनी
    0.52
     its
    0.50
    Act Density 0.070%

    No Known Activations