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

    Neuronpedia

    INDEX
    Explanations

    closing brackets and other syntax-related end tokens in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enetrable
    -0.51
    }}</
    -0.44
     }</
    -0.43
     mauva
    -0.42
     penghar
    -0.42
    colgante
    -0.41
    发表于
    -0.41
     MainAxisSize
    -0.41
    rebbero
    -0.40
    ftagPool
    -0.40
    POSITIVE LOGITS
    ↵↵↵
    0.83
    ↵↵↵↵
    0.81
    ↵↵↵↵↵
    0.73
    ↵↵↵↵↵↵
    0.62
    ↵↵↵↵↵↵↵
    0.59
    ↵↵↵↵↵↵↵↵
    0.51
    ↵↵↵↵↵↵↵↵↵
    0.49
    Tembelea
    0.48
    ↵↵↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵
    0.45
    Act Density 0.209%

    No Known Activations