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

    Neuronpedia

    INDEX
    Explanations

    words related to founders or founding of organizations and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.80
     Theſe
    -0.77
     ſtate
    -0.72
     pleaſure
    -0.71
     ſever
    -0.70
     faſt
    -0.68
     perfons
    -0.68
     uſed
    -0.68
     ARXIV
    -0.67
     Chriftian
    -0.67
    POSITIVE LOGITS
     founder
    0.78
     dam
    0.72
    dam
    0.68
     damn
    0.67
     Founder
    0.66
     autorytatywna
    0.65
    IntoConstraints
    0.65
     jam
    0.64
    damn
    0.60
    GOT
    0.60
    Act Density 0.095%

    No Known Activations