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

    Neuronpedia

    INDEX
    Explanations

    references to windows and light features in architectural descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cherchés
    -0.72
    AddTagHelper
    -0.66
    ThroughAttribute
    -0.64
     Cæsar
    -0.59
     chariots
    -0.59
    esserung
    -0.58
    Autoritní
    -0.58
     polyg
    -0.57
     hardening
    -0.56
     epit
    -0.56
    POSITIVE LOGITS
     jendela
    0.58
     finestra
    0.56
    fenster
    0.50
     janela
    0.49
    AutoScaleMode
    0.48
    isler
    0.47
     fenêtres
    0.46
     cedera
    0.46
     ibunya
    0.44
     窗
    0.43
    Act Density 0.055%

    No Known Activations