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

    Neuronpedia

    INDEX
    Explanations

    sentences that indicate significant emotional or impactful moments

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

    incredible descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.76
    <unused47>
    -0.76
    <unused21>
    -0.76
    <unused3>
    -0.76
    <unused28>
    -0.76
    <unused40>
    -0.76
    <unused41>
    -0.76
    <unused68>
    -0.76
    [@BOS@]
    -0.75
    <unused14>
    -0.75
    POSITIVE LOGITS
     mencionó
    0.27
     cadenas
    0.27
     Muskel
    0.27
     incredible
    0.23
     Kunde
    0.22
     vokal
    0.22
     Wirk
    0.22
    Przypisy
    0.22
     increíbles
    0.22
     incríveis
    0.21
    Act Density 0.001%

    No Known Activations