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

    Neuronpedia

    INDEX
    Explanations

    various numeric patterns and symbols, indicating it is likely focused on data formatting or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Warum
    -0.49
     varones
    -0.48
     why
    -0.47
    ScopeManager
    -0.46
    Warum
    -0.45
    Хьажоргаш
    -0.43
    Categoría
    -0.42
    hombres
    -0.42
    why
    -0.41
     Pourquoi
    -0.41
    POSITIVE LOGITS
     endforeach
    0.43
     Савезне
    0.42
     uParam
    0.42
    itinéraire
    0.42
     GenerationType
    0.41
     unterkunft
    0.40
     localObject
    0.39
     >=",
    0.37
     uLocal
    0.36
     bParam
    0.35
    Act Density 0.551%

    No Known Activations