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

    Neuronpedia

    INDEX
    Explanations

    the use of numerical data or statistics in discussing various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.27
     ••
    -0.26
     ⚫
    -0.25
     ❖
    -0.23
     
    -0.23
    !*\
    -0.22
     🔥🔥
    -0.22
     ‫
    -0.22
     
    -0.21
     
    -0.21
    POSITIVE LOGITS
    source
    0.87
    read
    0.86
    Read
    0.81
    Source
    0.81
     Read
    0.80
     queſta
    0.80
     Source
    0.79
    posted
    0.78
    view
    0.76
    Advertisement
    0.76
    Act Density 0.641%

    No Known Activations