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

    Neuronpedia

    INDEX
    Explanations

    terms related to tangents and their mathematical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McIl
    -0.79
    花板
    -0.78
     "..\..\..\
    -0.77
     Winslow
    -0.73
     Stowe
    -0.69
     isolado
    -0.69
     BIS
    -0.69
    colta
    -0.66
     Melton
    -0.66
     Hoon
    -0.65
    POSITIVE LOGITS
     Tang
    1.70
     TANG
    1.68
    tang
    1.59
    Tang
    1.57
     tang
    1.52
     Tanger
    1.16
     Tango
    1.04
     tanga
    1.00
     tango
    0.95
    atang
    0.93
    Act Density 0.010%

    No Known Activations