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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of decision-making and agency regarding departures or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.54
    脚注の使い方
    -0.47
     actionPerformed
    -0.47
    ChildScrollView
    -0.43
    /**
    -0.42
    InjectAttribute
    -0.41
    GTCX
    -0.41
    expandindo
    -0.40
    findpost
    -0.40
    extAlignment
    -0.39
    POSITIVE LOGITS
     exit
    2.48
     departure
    2.25
     Exit
    2.23
    exit
    2.14
     exits
    2.05
    Exit
    2.03
     departing
    2.03
     exiting
    2.00
     departures
    1.91
     EXIT
    1.90
    Act Density 0.777%

    No Known Activations