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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the voluntariness and admissibility of confessions

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

    voluntarily given or freely made

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BAB
    -0.41
     parseFrom
    -0.40
    picks
    -0.40
    uploads
    -0.39
     permiten
    -0.38
    Upload
    -0.38
    vima
    -0.38
     الاح
    -0.37
    原始内容存档
    -0.37
    Permutation
    -0.37
    POSITIVE LOGITS
     pemberian
    0.87
     giver
    0.85
     freely
    0.85
    Giving
    0.85
     given
    0.82
     Giving
    0.82
    giving
    0.82
     giving
    0.81
     giv
    0.80
    give
    0.77
    Act Density 0.136%

    No Known Activations