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

    Neuronpedia

    INDEX
    Explanations

    collective references to generations or age groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.34
     known
    -0.29
      
    -0.28
    </td>
    -0.28
     ever
    -0.27
    2
    -0.27
     many
    -0.26
       
    -0.25
     (
    -0.25
    const
    -0.25
    POSITIVE LOGITS
     queſta
    0.98
     nakalista
    0.97
    <unused52>
    0.95
    <unused79>
    0.95
    [@BOS@]
    0.95
    <unused14>
    0.95
    <unused16>
    0.94
    <unused8>
    0.94
    <unused68>
    0.94
    <unused28>
    0.94
    Act Density 6.505%

    No Known Activations