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

    Neuronpedia

    INDEX
    Explanations

    words related to the integrity and movement of rolling components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.55
     архивлан
    -0.52
     himo
    -0.49
    衬
    -0.48
    他说
    -0.48
     发表于
    -0.47
    enumeration
    -0.47
     незавершена
    -0.47
    mahaman
    -0.47
    NUMX
    -0.46
    POSITIVE LOGITS
    rolling
    0.74
     réfugiés
    0.67
     démocr
    0.66
    Παραπομπές
    0.65
     rolled
    0.65
     rolling
    0.64
    rolled
    0.64
    Spill
    0.64
     disambiguazione
    0.64
    romptu
    0.61
    Act Density 2.777%

    No Known Activations