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

    Neuronpedia

    INDEX
    Explanations

    references to auxiliary elements or concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.57
    .
    -0.56
     (
    -0.55
     part
    -0.54
     per
    -0.53
    '
    -0.53
     
    -0.52
    pu
    -0.52
    가
    -0.51
    0
    -0.50
    POSITIVE LOGITS
    )";
    1.22
    .";
    1.15
    ";}
    1.10
    ]";
    1.07
    "];
    1.06
    "]
    1.04
    ++
    1.03
     Jefus
    1.03
    rungsseite
    1.02
     Aux
    1.02
    Act Density 0.536%

    No Known Activations