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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and statistical analysis related to study results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.81
     seperate
    -0.65
     gibts
    -0.59
     recieve
    -0.58
     ."
    -0.58
     isn
    -0.57
     doesn
    -0.56
     alot
    -0.55
     seper
    -0.55
     !"
    -0.54
    POSITIVE LOGITS
     (−
    0.94
     ∼
    0.93
     < 
    0.86
     = 
    0.81
     × 
    0.77
     + 
    0.73
    ∼
    0.73
    /−
    0.73
     Table
    0.71
    = 
    0.70
    Act Density 7.559%

    No Known Activations