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

    Neuronpedia

    INDEX
    Explanations

    references to chocolate and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.71
    <unused43>
    -0.68
    <unused8>
    -0.68
     telefónica
    -0.67
    <unused41>
    -0.67
    <unused28>
    -0.67
    <unused42>
    -0.67
    <unused74>
    -0.67
    [@BOS@]
    -0.67
    <unused20>
    -0.67
    POSITIVE LOGITS
     chocolate
    1.23
    Chocolate
    1.15
     Chocolate
    1.13
    chocolate
    1.13
     шоколад
    0.87
     chocolates
    0.87
    OCOLATE
    0.86
     chocol
    0.83
     cioccolato
    0.81
     cocoa
    0.79
    Act Density 0.268%

    No Known Activations