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

    Neuronpedia

    INDEX
    Explanations

    decisions or choice-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithMany
    -0.50
     Réponses
    -0.45
    Ehrungen
    -0.43
     paraître
    -0.42
     disponibilités
    -0.42
     Attractive
    -0.38
     MainAxisSize
    -0.37
     bağlantılar
    -0.37
    Ecotoxicity
    -0.36
     תר
    -0.36
    POSITIVE LOGITS
     decision
    1.21
     decides
    1.20
     decide
    1.09
     decided
    1.06
     deciding
    1.02
    decision
    1.01
    decide
    0.99
    决定
    0.97
    Decision
    0.97
     DECISION
    0.96
    Act Density 0.293%

    No Known Activations