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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their descriptions in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.82
    parsedMessage
    -0.81
    mybatisplus
    -0.80
    "])
    -0.79
    complexContent
    -0.78
     EconPapers
    -0.76
    astéro
    -0.76
    ']],
    -0.76
     يتيمه
    -0.76
    Aholisi
    -0.75
    POSITIVE LOGITS
    8
    1.51
    9
    1.51
    6
    1.46
    7
    1.45
    4
    1.38
    5
    1.38
    0
    1.32
    3
    1.31
    2
    1.22
    1
    1.08
    Act Density 3.434%

    No Known Activations