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

    Neuronpedia

    INDEX
    Explanations

    words related to decision-making

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -0.71
    Anti
    -0.66
    Legend
    -0.66
    gel
    -0.65
     maiden
    -0.64
    NES
    -0.64
    waters
    -0.64
    Versions
    -0.63
    ppo
    -0.63
    anti
    -0.62
    POSITIVE LOGITS
     regarding
    1.16
     decisions
    1.11
     affecting
    1.08
     based
    1.02
     concerning
    1.01
     about
    0.94
     involving
    0.91
     democratically
    0.90
     impacting
    0.88
     accordingly
    0.88
    Act Density 0.069%

    No Known Activations