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

    Neuronpedia

    INDEX
    Explanations

    words related to spatial proximity or adjacency

    oai_token-act-pair · gpt-3.5-turbo

    words related to proximity and relationship between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GO
    -0.79
    tu
    -0.74
     Bild
    -0.71
    oiler
    -0.71
    ILLE
    -0.71
    soDeliveryDate
    -0.68
    Doctors
    -0.67
    uay
    -0.64
    odor
    -0.64
    ifter
    -0.62
    POSITIVE LOGITS
     adjacent
    1.13
     thereto
    0.97
     adjoining
    0.95
    ļéĨĴ
    0.77
     neighb
    0.76
    stairs
    0.73
    opol
    0.73
    rils
    0.71
     contiguous
    0.71
    ĸļ
    0.71
    Act Density 0.007%

    No Known Activations