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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making choices and selections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.77
     Barclay
    -0.77
     nakalista
    -0.71
     assistenza
    -0.70
    แดง
    -0.67
     sympy
    -0.67
    ้อมูล
    -0.66
     dumne
    -0.66
     fapt
    -0.66
     Manley
    -0.65
    POSITIVE LOGITS
     choices
    1.60
     Choices
    1.53
    choose
    1.50
     chooses
    1.47
     choose
    1.47
     CHOOSE
    1.46
     Choose
    1.44
    Choose
    1.43
    choosing
    1.43
     choice
    1.41
    Act Density 0.062%

    No Known Activations