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

    Neuronpedia

    INDEX
    Explanations

    closing braces and parentheses in code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused14>
    -1.91
    <unused3>
    -1.91
    <unused16>
    -1.91
    <unused51>
    -1.91
    <unused74>
    -1.91
    [@BOS@]
    -1.91
    <unused8>
    -1.91
    <unused41>
    -1.91
    <unused79>
    -1.91
    <unused28>
    -1.91
    POSITIVE LOGITS
    }
    1.28
    ()
    1.21
    )
    1.20
    ,
    1.08
    ↵↵
    1.07
     (
    1.05
    /
    0.98
     and
    0.97
      
    0.97
    .
    0.97
    Act Density 1.172%

    No Known Activations