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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making choices or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Svet
    -0.52
    /**
    -0.48
    Rptr
    -0.47
    unkel
    -0.47
     Grossman
    -0.47
    oldt
    -0.46
    RefreshLayout
    -0.45
     argint
    -0.44
    llary
    -0.44
     Harman
    -0.44
    POSITIVE LOGITS
     choice
    1.51
     Choice
    1.39
    choice
    1.38
    Choice
    1.32
     choose
    1.32
    choose
    1.30
     choices
    1.29
     Choose
    1.27
    Choose
    1.26
     CHOICE
    1.25
    Act Density 0.123%

    No Known Activations