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

    Neuronpedia

    INDEX
    Explanations

    terms related to quantitative analysis and Euro-centric topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.63
     
    -0.60
    ↵
    -0.56
    ,
    -0.56
    .
    -0.56
     "
    -0.55
     Jackson
    -0.53
    ↵↵
    -0.53
     rock
    -0.52
    '
    -0.52
    POSITIVE LOGITS
    <unused79>
    1.07
    <unused14>
    1.07
    <unused8>
    1.07
    [@BOS@]
    1.06
    <unused52>
    1.06
    <unused23>
    1.06
    <unused41>
    1.06
    <unused28>
    1.06
    <unused3>
    1.06
    <unused16>
    1.06
    Act Density 0.233%

    No Known Activations