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

    Neuronpedia

    INDEX
    Explanations

    words related to scientific research and medical development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wierd
    -0.86
     somebody
    -0.83
     Надо
    -0.83
     Somebody
    -0.79
     stuff
    -0.77
     colère
    -0.77
     stupid
    -0.77
     Jefus
    -0.76
     honte
    -0.76
    Somebody
    -0.76
    POSITIVE LOGITS
     welcher
    0.77
     אשר
    0.74
     prior
    0.70
    uxta
    0.70
     welchem
    0.69
     showcased
    0.69
     utilizing
    0.67
     advancements
    0.66
     showcasing
    0.64
    唯有
    0.64
    Act Density 2.146%

    No Known Activations