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

    Neuronpedia

    INDEX
    Explanations

    names of individuals involved in political disputes

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

    political parties and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.30
    ,
    -0.30
    Con
    -0.29
     n
    -0.29
    .
    -0.28
    (
    -0.28
     “
    -0.28
    }
    -0.27
    len
    -0.27
     len
    -0.27
    POSITIVE LOGITS
     propOrder
    1.06
    <unused16>
    1.00
    <unused74>
    0.99
    <unused28>
    0.99
    ValueStyle
    0.99
     Weiſe
    0.99
    <unused17>
    0.99
    <unused3>
    0.99
    [@BOS@]
    0.99
    <pad>
    0.99
    Act Density 0.147%

    No Known Activations