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

    Neuronpedia

    INDEX
    Explanations

    variants of the word "the" and related pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.58
    넷
    -0.55
    ,
    -0.53
    ;
    -0.52
    "
    -0.44
     assuming
    -0.43
    -
    -0.42
    )
    -0.42
    ..
    -0.41
    :
    -0.41
    POSITIVE LOGITS
     disambiguazione
    1.03
     дописавши
    0.97
     للمعارف
    0.95
    styleable
    0.94
     surla
    0.92
     مُعرِّف
    0.88
    tvguidetime
    0.87
     MainAxisSize
    0.87
    الإنجليزية
    0.87
    providedIn
    0.86
    Act Density 0.909%

    No Known Activations