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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "As" used to introduce comparisons or references to prior statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     мәкал
    -0.57
    Diweddarwch
    -0.53
    UserScript
    -0.51
     nakalista
    -0.50
    InjectAttribute
    -0.49
    tagHelperRunner
    -0.48
     as
    -0.47
     незавершена
    -0.47
     AssemblyCompany
    -0.44
     referenties
    -0.42
    POSITIVE LOGITS
     regards
    0.91
     was
    0.71
     explained
    0.69
    regards
    0.66
     argued
    0.66
     shown
    0.65
     compared
    0.61
     defined
    0.60
     indicated
    0.59
     pointed
    0.59
    Act Density 0.382%

    No Known Activations