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

    Neuronpedia

    INDEX
    Explanations

    questions and hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to hypothetical scenarios and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uncture
    -0.64
    inventoryQuantity
    -0.62
    resa
    -0.61
    DX
    -0.59
    racuse
    -0.56
     SX
    -0.54
    ãĤ¨
    -0.54
    FTWARE
    -0.52
     FINAL
    -0.51
    NetMessage
    -0.51
    POSITIVE LOGITS
    would
    2.21
     would
    2.12
     wouldn
    1.83
     Would
    1.77
    Would
    1.69
    'd
    1.49
     Wouldn
    1.49
    could
    1.37
     could
    1.27
    OULD
    1.27
    Act Density 1.072%

    No Known Activations