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

    Neuronpedia

    INDEX
    Explanations

    terms related to "density" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Swin
    -0.77
    serviceWorker
    -0.74
     Alvar
    -0.68
    toPromise
    -0.65
     Vai
    -0.64
     Olli
    -0.63
    Cog
    -0.62
     falcon
    -0.61
     elm
    -0.60
     Caspian
    -0.58
    POSITIVE LOGITS
     densities
    1.47
     density
    1.47
     Density
    1.44
    density
    1.38
    Density
    1.35
     DENSITY
    1.33
     denso
    1.21
    密度
    1.19
     DEN
    1.19
     ρ
    1.18
    Act Density 0.216%

    No Known Activations