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

    Neuronpedia

    INDEX
    Explanations

    references to towns or town-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Warszawie
    -0.84
     Karlsruhe
    -0.81
     MediatR
    -0.78
    rungsseite
    -0.73
     furs
    -0.72
     Bélgica
    -0.72
     Phillies
    -0.72
     Réponses
    -0.72
    AddWithValue
    -0.71
    ificantly
    -0.70
    POSITIVE LOGITS
     town
    2.15
     Town
    2.00
    Town
    1.86
     TOWN
    1.84
    town
    1.79
     towns
    1.64
    TOWN
    1.59
     Towns
    1.48
    towns
    1.48
     Towne
    1.41
    Act Density 0.033%

    No Known Activations