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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases or transitional elements in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MenuView
    -0.61
    awtextra
    -0.59
    liken
    -0.58
     Monfieur
    -0.58
     meridian
    -0.57
     Domes
    -0.57
     Jefus
    -0.56
    ſelf
    -0.56
     sandero
    -0.55
    felves
    -0.55
    POSITIVE LOGITS
    原始内容存档于
    0.53
     кӀ
    0.52
     että
    0.50
    /
    0.50
    ,
    0.50
     насеље
    0.49
    日閲覧
    0.48
    :
    0.47
    ніципа
    0.47
    Contours
    0.47
    Act Density 0.091%

    No Known Activations