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

    Neuronpedia

    INDEX
    Explanations

    significant statements or claims made by named individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     THEIR
    -0.44
     Conferencia
    -0.43
     officer
    -0.43
    лго
    -0.42
    Dit
    -0.41
    choon
    -0.41
    Their
    -0.41
    raisemb
    -0.41
     évent
    -0.40
     či
    -0.39
    POSITIVE LOGITS
     himself
    1.00
    himself
    0.78
    tagHelper
    0.76
    )";
    0.75
    StoryboardSegue
    0.73
     <=",
    0.72
    ⓧ
    0.72
    Diwedd
    0.70
    帖最后由
    0.69
     يتيمه
    0.68
    Act Density 0.418%

    No Known Activations