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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with unspecified attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \}\\
    -0.76
     '/';
    -0.71
    ++++++++++++++++
    -0.70
    EDR
    -0.69
    ]]]
    -0.69
    ::::::::::::::::
    -0.68
    ®:
    -0.67
    колеп
    -0.67
    branche
    -0.66
    amiento
    -0.65
    POSITIVE LOGITS
     nums
    1.07
    Num
    1.05
     Num
    1.04
     num
    1.02
    num
    1.00
    Nums
    0.92
    nums
    0.91
    DockStyle
    0.88
    numRows
    0.87
     Curran
    0.86
    Act Density 0.084%

    No Known Activations