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

    Neuronpedia

    INDEX
    Explanations

    elements related to structure or organization in a narrative context

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

    ChangeInserta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     then
    -0.35
    also
    -0.30
     tambin
    -0.30
    zugehen
    -0.30
     entonces
    -0.29
     następnie
    -0.29
    Kemudian
    -0.28
     also
    -0.27
     kiin
    -0.27
     тогда
    -0.27
    POSITIVE LOGITS
    RegressionTest
    0.77
    <unused3>
    0.77
    <unused41>
    0.77
    <unused79>
    0.77
    <unused8>
    0.77
    [@BOS@]
    0.77
    <unused28>
    0.77
    <unused42>
    0.77
    <unused16>
    0.77
    <unused43>
    0.77
    Act Density 0.014%

    No Known Activations