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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating disappointment or failure

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

    negative outcomes or shortcomings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.55
     AssemblyVersion
    -0.46
    queryInterface
    -0.45
     CreateTagHelper
    -0.42
    tslib
    -0.39
    DllImport
    -0.39
    Regressor
    -0.39
     Paglinawan
    -0.39
     htmlFor
    -0.38
    ----</
    -0.38
    POSITIVE LOGITS
     EconPapers
    0.52
    ajinan
    0.40
     OFDb
    0.39
     gyhoeddwyd
    0.36
    あく
    0.36
     slow
    0.36
    Phillip
    0.36
    意思
    0.36
     lambat
    0.35
     circonstances
    0.35
    Act Density 0.230%

    No Known Activations