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

    Neuronpedia

    INDEX
    Explanations

    specific behaviors deemed unacceptable in a professional setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    {
    -0.46
    [
    -0.45
     
    -0.43
    Opening
    -0.42
    '
    -0.42
     {;
    -0.42
    全文
    -0.42
    st
    -0.41
    $
    -0.40
    余
    -0.40
    POSITIVE LOGITS
     виправивши
    0.79
     дописавши
    0.77
     perfons
    0.71
     beginnetje
    0.71
     myſelf
    0.71
     Efq
    0.71
    Bibliograf
    0.69
     purpoſe
    0.69
    MessageTagHelper
    0.69
    MethodManager
    0.68
    Act Density 0.700%

    No Known Activations