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

    Neuronpedia

    INDEX
    Explanations

    references to chocolate and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.59
     preghi
    -0.57
    CppCodeGen
    -0.47
    Dichloropropane
    -0.46
     Napier
    -0.45
     Económica
    -0.43
     RNA
    -0.42
    gebob
    -0.42
    localctx
    -0.42
    Roe
    -0.41
    POSITIVE LOGITS
     chocolate
    2.08
     Chocolate
    1.77
    chocolate
    1.73
    Chocolate
    1.68
     chocol
    1.59
     chocolates
    1.58
    🍫
    1.57
     cocoa
    1.49
     chocolat
    1.45
     cacao
    1.41
    Act Density 0.119%

    No Known Activations