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

    Neuronpedia

    INDEX
    Explanations

    elements related to choices and options in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Taktlose
    -0.43
    adaptiveStyles
    -0.42
    Життєпис
    -0.38
    Становништво
    -0.36
    medriver
    -0.34
    EndGlobalSection
    -0.33
    richTextPanel
    -0.32
    RefreshLayout
    -0.32
     bekämp
    -0.31
    requently
    -0.31
    POSITIVE LOGITS
     choose
    3.36
     choice
    3.36
     choosing
    3.34
     chooses
    3.17
    choose
    3.05
     chose
    3.00
     chosen
    2.98
     Choose
    2.97
    Choose
    2.92
     Choosing
    2.92
    Act Density 2.743%

    No Known Activations