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

    Neuronpedia

    INDEX
    Explanations

    terms related to pardons and amnesty

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

    pardon, Amnesty, parm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    U
    -0.47
    He
    -0.46
    zzleHttp
    -0.44
    Ria
    -0.43
     he
    -0.43
    Li
    -0.42
    Things
    -0.42
    HS
    -0.42
    MC
    -0.41
    Louisa
    -0.41
    POSITIVE LOGITS
     pardon
    1.98
     Pardon
    1.85
    Pardon
    1.66
    pardon
    1.61
     pardoned
    1.45
     pard
    1.42
     Pard
    1.27
     perdón
    0.96
    pard
    0.93
     perdon
    0.90
    Act Density 0.004%

    No Known Activations