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

    Neuronpedia

    INDEX
    Explanations

    terms related to data types or measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.70
    ThroughAttribute
    -0.69
     Hadd
    -0.66
    wój
    -0.65
    Ching
    -0.63
     Borden
    -0.61
     spade
    -0.59
    stranded
    -0.59
     ComVisible
    -0.58
     Pears
    -0.58
    POSITIVE LOGITS
     DT
    1.47
     dt
    1.38
    dt
    1.36
    DT
    1.34
     Dt
    1.11
    Dt
    1.02
    nastics
    0.88
    dts
    0.87
    dataTable
    0.81
     Holtz
    0.81
    Act Density 0.016%

    No Known Activations