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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to spatial relationships, specifically focusing on being 'adjacent' to something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geographical or spatial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.81
    GO
    -0.79
    uay
    -0.77
    odor
    -0.74
    cher
    -0.73
    roller
    -0.72
    tu
    -0.71
    ifter
    -0.70
    fare
    -0.70
    =-=-=-=-=-=-=-=-
    -0.69
    POSITIVE LOGITS
     adjacent
    0.96
     adjoining
    0.88
     thereto
    0.88
     territories
    0.75
     areas
    0.75
     spaces
    0.74
     regions
    0.71
     quarters
    0.71
     exhib
    0.69
     halls
    0.68
    Act Density 0.014%

    No Known Activations