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

    Neuronpedia

    INDEX
    Explanations

    topics related to historical texts and community dynamics, particularly focusing on authorship, ownership, and the role of communities in shaping literature

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

    captives or captured

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused47>
    -0.71
    <unused8>
    -0.71
    <unused16>
    -0.71
    [@BOS@]
    -0.71
    <unused28>
    -0.71
    <unused79>
    -0.71
    <unused41>
    -0.71
    <unused52>
    -0.71
    <unused43>
    -0.71
    <pad>
    -0.70
    POSITIVE LOGITS
     podían
    0.36
     often
    0.32
     honor
    0.32
     hó
    0.31
     optique
    0.29
     private
    0.28
     hú
    0.28
     honored
    0.28
     publice
    0.27
    totalPrice
    0.26
    Act Density 0.111%

    No Known Activations