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

    Neuronpedia

    INDEX
    Explanations

    references to betrayal and treason

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to betrayal or disloyalty

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gor
    -0.75
    EVA
    -0.72
    Electric
    -0.71
    Roll
    -0.70
    Morning
    -0.68
     Cancel
    -0.68
    Environment
    -0.67
    Delivery
    -0.65
    Sample
    -0.65
    arel
    -0.64
    POSITIVE LOGITS
     traitor
    0.96
     treason
    0.94
     sympath
    0.93
     plotting
    0.90
     guiActiveUn
    0.86
     plot
    0.82
    uous
    0.81
     subversive
    0.81
     plotted
    0.81
     salute
    0.79
    Act Density 0.025%

    No Known Activations