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

    Neuronpedia

    INDEX
    Explanations

    different types of hats and roofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    invokeLater
    -0.64
     vân
    -0.62
     Jep
    -0.62
    yně
    -0.62
    PECT
    -0.62
     Carne
    -0.61
    mgang
    -0.61
     dvs
    -0.61
     dịch
    -0.61
     Weston
    -0.59
    POSITIVE LOGITS
     hats
    1.35
     hat
    1.20
     roof
    1.18
     Hats
    1.17
     roofs
    1.16
    Hat
    1.15
    Hats
    1.13
     Hat
    1.10
     HAT
    1.05
     caps
    1.02
    Act Density 0.248%

    No Known Activations