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

    Neuronpedia

    INDEX
    Explanations

    terms associated with decision-making and related processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilden
    -0.16
    oru
    -0.14
    unami
    -0.14
    deen
    -0.14
    laus
    -0.14
    ustum
    -0.14
    infeld
    -0.14
    iges
    -0.14
    amac
    -0.14
     Gow
    -0.14
    POSITIVE LOGITS
    -making
    0.25
    naire
    0.23
     made
    0.20
    aries
    0.19
    naires
    0.19
    -makers
    0.19
    Made
    0.19
     makers
    0.18
     decision
    0.18
    made
    0.18
    Act Density 0.050%

    No Known Activations