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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and concepts related to geometry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forgiven
    -0.16
    \Modules
    -0.15
     Cougar
    -0.15
    ï¼ł
    -0.15
     Carlton
    -0.15
    anza
    -0.14
    lama
    -0.14
    headed
    -0.14
     longitud
    -0.14
    ampo
    -0.14
    POSITIVE LOGITS
     poly
    0.30
     Poly
    0.26
    conv
    0.25
     faces
    0.25
     Conv
    0.25
     Faces
    0.25
    poly
    0.24
    Conv
    0.23
     simp
    0.23
    Faces
    0.23
    Act Density 0.029%

    No Known Activations