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

    Neuronpedia

    INDEX
    Explanations

    references to cities and urban environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ɓ
    -0.47
     lentes
    -0.41
    niczka
    -0.40
     master
    -0.40
     ब्रेकडाउन
    -0.38
     organiser
    -0.37
    orientation
    -0.37
     noten
    -0.37
    unca
    -0.37
     organizer
    -0.36
    POSITIVE LOGITS
     cities
    1.77
     towns
    1.60
     Cities
    1.45
    Cities
    1.37
     ciudades
    1.35
    cities
    1.33
     communities
    1.29
     CITIES
    1.28
     neighborhoods
    1.25
     cidades
    1.25
    Act Density 0.155%

    No Known Activations