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

    Neuronpedia

    INDEX
    Explanations

    references to various types of legal damages

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

    awarded damages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prêtre
    -0.40
     antemano
    -0.37
     sindic
    -0.36
    หร
    -0.35
     oreille
    -0.35
     perfección
    -0.34
     vœ
    -0.34
     prêtres
    -0.34
     viejos
    -0.33
     pouss
    -0.33
    POSITIVE LOGITS
     damages
    2.08
     Damages
    1.99
     DAMAGES
    1.82
    Dama
    1.41
     Dama
    1.00
     dama
    0.85
     damaging
    0.83
     Compensation
    0.81
    dama
    0.79
     damaged
    0.78
    Act Density 0.016%

    No Known Activations