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

    Neuronpedia

    INDEX
    Explanations

    references to significant proportions or majorities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sometimes
    -0.17
     slightest
    -0.16
     sometimes
    -0.16
     occasionally
    -0.16
     smallest
    -0.15
     Sometimes
    -0.14
    uy
    -0.13
    enet
    -0.13
    XL
    -0.13
    icks
    -0.13
    POSITIVE LOGITS
     majority
    0.93
     Majority
    0.68
     болÑĮÑĪин
    0.61
     ëĮĢë¶Ģë¶Ħ
    0.60
     most
    0.59
     meisten
    0.59
     vÄĽtÅ¡
    0.57
     mostly
    0.54
     mayorÃŃa
    0.52
    mostly
    0.47
    Act Density 0.719%

    No Known Activations