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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific attributes or properties in a structured format, potentially related to data or file organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wich
    -0.20
    rack
    -0.19
     Eighth
    -0.18
     Rack
    -0.17
    .synthetic
    -0.16
    rak
    -0.16
     ä¸ĥ
    -0.15
     Seventh
    -0.15
     Raf
    -0.15
    RAL
    -0.15
    POSITIVE LOGITS
    9
    0.50
    ï¼Ļ
    0.32
    ९
    0.30
    Û¹
    0.30
     nine
    0.29
    -nine
    0.27
    Ù©
    0.27
    ä¹Ŀ
    0.26
     ä¹Ŀ
    0.25
    nine
    0.24
    Act Density 0.042%

    No Known Activations