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

    Neuronpedia

    INDEX
    Explanations

    words related to decision-making processes

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

    decision making process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.66
    The
    -0.57
    *
    -0.46
     femininas
    -0.46
    <bos>
    -0.45
     wide
    -0.44
     crazy
    -0.44
    ys
    -0.43
     five
    -0.42
    Is
    -0.41
    POSITIVE LOGITS
     Decision
    1.11
     decision
    1.06
    decision
    1.04
    Decision
    1.03
     DECISION
    0.94
     Decisions
    0.91
     decisions
    0.86
    DECISION
    0.86
    Decisions
    0.83
    decisions
    0.80
    Act Density 0.013%

    No Known Activations