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

    Neuronpedia

    INDEX
    Explanations

    information about researching or exploring a specific topic

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kön
    -0.84
     akus
    -0.76
     ekos
    -0.73
     kosme
    -0.72
     uefa
    -0.72
     kooper
    -0.69
     kollek
    -0.68
     kriminal
    -0.68
     minimalis
    -0.68
     akut
    -0.67
    POSITIVE LOGITS
     researching
    0.71
     search
    0.65
     googling
    0.65
     searched
    0.64
     searching
    0.64
     online
    0.63
     googled
    0.62
     google
    0.60
     researched
    0.57
    onnaissance
    0.56
    Act Density 0.261%

    No Known Activations