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

    Neuronpedia

    INDEX
    Explanations

    references to islands and their names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.83
     femen
    -0.72
     fale
    -0.68
     umane
    -0.67
     étoient
    -0.66
     pleaſure
    -0.66
     fémin
    -0.63
    汰
    -0.63
     Вікі
    -0.62
    oredCriteria
    -0.62
    POSITIVE LOGITS
    WebServlet
    0.76
     Island
    0.73
    island
    0.69
    GEBURTSDATUM
    0.67
     island
    0.66
     New
    0.65
    Island
    0.65
     ISLAND
    0.61
     发表于
    0.59
     Old
    0.56
    Act Density 0.111%

    No Known Activations