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

    Neuronpedia

    INDEX
    Explanations

    terms related to awards and prizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulemon
    -0.51
    Tug
    -0.50
    OLEAN
    -0.49
    GEBURTSDATUM
    -0.49
     vuitton
    -0.48
    thentic
    -0.48
    şiv
    -0.47
     creed
    -0.47
     ortho
    -0.46
    tyard
    -0.46
    POSITIVE LOGITS
    messages
    0.68
     zprávy
    0.65
    Messages
    0.65
     remembered
    0.64
     reports
    0.58
     stories
    0.57
     histórias
    0.52
     verhalen
    0.52
     Geschichten
    0.52
     Messages
    0.52
    Act Density 0.238%

    No Known Activations