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

    Neuronpedia

    INDEX
    Explanations

    phrases related to moral or ethical judgments

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

    preceding statements or questions

    np_acts-logits-general · gemini-2.0-flash

    doing justice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -1.20
    parsedMessage
    -1.07
    GEBURTSDATUM
    -1.05
     Monfieur
    -1.05
     Theſe
    -1.04
     becauſe
    -1.03
     estekak
    -1.02
     purpoſe
    -1.01
    __":
    -1.01
    StructEnd
    -0.99
    POSITIVE LOGITS
     justice
    1.51
    justice
    1.14
     Justice
    1.09
     JUSTICE
    1.03
    Justice
    1.02
     justicia
    0.98
     fairness
    0.93
     credit
    0.85
     giustizia
    0.83
     fair
    0.81
    Act Density 0.109%

    No Known Activations