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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to size, quantity, or measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     simplu
    -0.66
     Persönlichkeit
    -0.66
    סים
    -0.63
     său
    -0.63
    InitVars
    -0.57
     bague
    -0.57
     centavos
    -0.56
    гда
    -0.56
     simplicité
    -0.56
     faune
    -0.55
    POSITIVE LOGITS
    annica
    0.91
     herself
    0.88
     تضيفلها
    0.88
     BeautifulSoup
    0.81
     shes
    0.81
     dAtA
    0.80
     stringBuilder
    0.80
     která
    0.80
    nouvelle
    0.79
     Latina
    0.78
    Act Density 0.090%

    No Known Activations