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

    Neuronpedia

    INDEX
    Explanations

    terms related to signal loss or reduction in intensity, specifically emphasizing "attenuation."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.75
     Lacy
    -0.73
    ysk
    -0.72
     Italijani
    -0.72
    ineno
    -0.71
     Drayton
    -0.71
     FRO
    -0.69
    QRect
    -0.69
     Jof
    -0.68
     Duch
    -0.68
    POSITIVE LOGITS
    atten
    1.19
     attenuation
    1.15
     attenu
    1.06
    Atten
    1.02
     attenuated
    0.99
     Atten
    0.98
     atten
    0.95
     attent
    0.79
    ##############
    0.76
    uated
    0.73
    Act Density 0.004%

    No Known Activations