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

    Neuronpedia

    INDEX
    Explanations

    references to building materials and construction components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urb
    -0.16
     Fauc
    -0.15
     Warner
    -0.14
     dripping
    -0.14
     drip
    -0.14
     vap
    -0.13
    游
    -0.13
    æĬ½
    -0.13
    æª
    -0.13
    int
    -0.13
    POSITIVE LOGITS
     sand
    0.22
     sands
    0.20
     sandbox
    0.19
     screenings
    0.19
    æ²Ļ
    0.19
     sift
    0.19
     particles
    0.18
    /loose
    0.18
     Sands
    0.18
     Loose
    0.18
    Act Density 0.111%

    No Known Activations