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

    Neuronpedia

    INDEX
    Explanations

    references to stereotypes and their impact on communities

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

    Followed by certain prepositions or articles

    np_acts-logits-general · gemini-2.0-flash

    biases and habits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.86
    WithIOException
    -0.77
     виправивши
    -0.72
    FieldNumber
    -0.71
    Personendaten
    -0.66
    OuterClass
    -0.66
    Geplaatst
    -0.65
    SqlClient
    -0.64
     AssemblyProduct
    -0.64
    TestingModule
    -0.62
    POSITIVE LOGITS
     tendency
    0.90
     tendencies
    0.83
     habits
    0.69
     tenden
    0.68
     habit
    0.65
     biases
    0.63
     bias
    0.61
     tendance
    0.59
     pernicious
    0.58
     practices
    0.58
    Act Density 0.372%

    No Known Activations