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

    Neuronpedia

    INDEX
    Explanations

    references to ownership or possession of entities

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

    its own

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &___
    -0.68
    AnimationsModule
    -0.62
    djangoproject
    -0.59
    PreferredItem
    -0.54
    Cyfeiriadau
    -0.53
    ukone
    -0.48
    ConverterFactory
    -0.46
    ContentAsync
    -0.43
    újo
    -0.43
    gridy
    -0.42
    POSITIVE LOGITS
     itself
    0.57
    Separate
    0.54
     separate
    0.52
     Itself
    0.51
     samostat
    0.50
     unique
    0.48
    itself
    0.48
     отдель
    0.46
     Separate
    0.44
     tunn
    0.43
    Act Density 0.019%

    No Known Activations