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

    Neuronpedia

    INDEX
    Explanations

    references to data manipulation and calculation in tables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄĻ
    -0.16
    oman
    -0.16
    iddet
    -0.15
    å¹²
    -0.15
     Cv
    -0.15
     ec
    -0.14
    ãĤ¦ãĥĪ
    -0.14
     Garland
    -0.14
    ccak
    -0.14
    parator
    -0.14
    POSITIVE LOGITS
     BI
    0.31
    BI
    0.28
     cubes
    0.24
     OL
    0.22
     Power
    0.22
     dash
    0.21
     cube
    0.21
    .dashboard
    0.20
    qli
    0.19
     Cube
    0.19
    Act Density 0.028%

    No Known Activations