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

    Neuronpedia

    INDEX
    Explanations

    references to combinatorial functions, specifically related to choosing or selecting elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.88
     insuffisamment
    -0.84
     GenerationType
    -0.76
    expandindo
    -0.74
    tagHelperRunner
    -0.71
    __':
    -0.71
    principalColumn
    -0.71
    MessageTagHelper
    -0.69
    contentLoaded
    -0.69
    rungsseite
    -0.66
    POSITIVE LOGITS
      
    0.56
     oud
    0.52
     DNA
    0.46
     out
    0.44
    ↵↵↵
    0.43
    ándolos
    0.43
    例文帳に追加
    0.43
     op
    0.43
       
    0.42
    を出
    0.41
    Act Density 0.001%

    No Known Activations