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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndContext
    -0.77
     Administrativna
    -0.65
     IBRARY
    -0.63
     Савезне
    -0.63
    juvant
    -0.62
    راسیون
    -0.62
    ofire
    -0.61
    mazoo
    -0.61
    maar
    -0.60
    >--}}
    -0.60
    POSITIVE LOGITS
    jbl
    0.45
    RTDA
    0.43
     okuyayım
    0.42
     vrouwen
    0.41
     renovables
    0.41
     estimés
    0.39
     &
    0.38
    nador
    0.38
    asteroide
    0.38
    mappedBy
    0.37
    Act Density 0.159%

    No Known Activations