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

    Neuronpedia

    INDEX
    Explanations

    references to capitals and administrative centers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FormControl
    -0.48
    RTGC
    -0.47
    󠁬
    -0.45
    frances
    -0.45
    tonode
    -0.45
     unknownFields
    -0.44
     Privacidade
    -0.43
     basque
    -0.43
    yelitis
    -0.43
    Personensuche
    -0.43
    POSITIVE LOGITS
     Hauptstadt
    0.64
     capital
    0.63
     capitals
    0.59
     capitale
    0.58
     Washington
    0.58
     capitol
    0.55
    Capital
    0.54
     столи
    0.53
    capital
    0.52
    Washington
    0.51
    Act Density 0.400%

    No Known Activations