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

    Neuronpedia

    INDEX
    Explanations

    references to rows and their indices in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.88
     fubject
    -0.85
     Theſe
    -0.85
    DispatchToProps
    -0.82
     Giuliano
    -0.78
     &___
    -0.77
     ſtill
    -0.76
     majeur
    -0.76
     pleaſure
    -0.76
     Harz
    -0.76
    POSITIVE LOGITS
     row
    3.32
     Row
    3.10
     rows
    2.79
    Row
    2.77
    row
    2.66
     ROW
    2.51
     Rows
    2.32
    ROW
    2.22
    rows
    2.20
    Rows
    2.02
    Act Density 0.044%

    No Known Activations