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

    Neuronpedia

    INDEX
    Explanations

    words related to decision-making or creation

    oai_token-act-pair · gpt-3.5-turbo

    references to decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sub
    -0.78
     sympath
    -0.77
     spray
    -0.75
     serv
    -0.72
     sear
    -0.72
     moderate
    -0.72
     subdiv
    -0.72
     shut
    -0.71
     die
    -0.71
     condemn
    -0.71
    POSITIVE LOGITS
     Making
    2.35
     Getting
    2.16
    Making
    2.00
     Keeping
    1.94
     Giving
    1.88
     Bringing
    1.87
     Creating
    1.84
     Putting
    1.84
     Taking
    1.83
     Changing
    1.78
    Act Density 0.067%

    No Known Activations