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

    Neuronpedia

    INDEX
    Explanations

    terms related to decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    virons
    -0.80
     alia
    -0.76
     Rosenberg
    -0.72
    ervations
    -0.68
    rouge
    -0.67
     учета
    -0.66
    værk
    -0.65
    promote
    -0.65
     ricev
    -0.64
    quista
    -0.64
    POSITIVE LOGITS
     decision
    1.67
     decisions
    1.63
     Decisions
    1.58
     Decision
    1.57
    Decisions
    1.54
     DECISION
    1.53
    Decision
    1.44
    decision
    1.34
    DECISION
    1.29
     Decide
    1.24
    Act Density 0.058%

    No Known Activations