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

    Neuronpedia

    INDEX
    Explanations

    references to new ideas, technologies, and innovations across various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     нового
    -0.16
     newest
    -0.16
     newly
    -0.15
     new
    -0.15
    æľĢæĸ°
    -0.15
     newfound
    -0.15
    ugar
    -0.15
    qp
    -0.14
    etics
    -0.14
    ises
    -0.14
    POSITIVE LOGITS
     ways
    0.29
     kinds
    0.26
     forms
    0.25
     parad
    0.24
     modes
    0.24
     approaches
    0.24
     ideas
    0.23
     types
    0.23
    forms
    0.23
     thinking
    0.22
    Act Density 0.071%

    No Known Activations