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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that indicate conditional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grüsse
    -0.55
    plaatst
    -0.46
     gewöhnlich
    -0.45
    ufnahme
    -0.45
    esistenza
    -0.44
    enumi
    -0.43
    område
    -0.42
     aislada
    -0.41
     využ
    -0.41
     ditangkap
    -0.41
    POSITIVE LOGITS
    RenderAtEndOf
    0.78
    AddTagHelper
    0.57
    脚注の使い方
    0.56
     Brookings
    0.54
    getOr
    0.53
    ۗ
    0.53
    ?";
    0.48
     Gan
    0.47
    +:+
    0.47
     testGet
    0.47
    Act Density 0.444%

    No Known Activations