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

    Neuronpedia

    INDEX
    Explanations

    metrics and evaluation results related to experiments and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    γον
    -0.15
    itch
    -0.15
    zte
    -0.14
    .Assertions
    -0.14
    ูà¹Ī
    -0.14
    rewrite
    -0.14
     tob
    -0.13
    cimal
    -0.13
     çĶŁåij½åij¨æľŁ
    -0.13
    .scalablytyped
    -0.13
    POSITIVE LOGITS
     performance
    0.29
    performance
    0.23
     Performance
    0.21
    Performance
    0.20
     performances
    0.19
     results
    0.18
     PERFORMANCE
    0.18
    .performance
    0.18
     improvement
    0.17
     performan
    0.17
    Act Density 0.139%

    No Known Activations