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

    Neuronpedia

    INDEX
    Explanations

    terms related to diplomatic or bilateral relations between entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "relations," particularly in a political or diplomatic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \\\\\\\\\\\\\\\\
    -0.74
    Sky
    -0.73
    iary
    -0.73
    orage
    -0.71
    strap
    -0.71
    astic
    -0.71
    otos
    -0.71
    idth
    -0.71
    ARK
    -0.71
    OWN
    -0.71
    POSITIVE LOGITS
    hips
    1.55
    hip
    1.01
     relations
    0.92
    pring
    0.86
     relation
    0.70
    hops
    0.70
    ystem
    0.68
    ually
    0.67
     between
    0.67
     ties
    0.66
    Act Density 0.025%

    No Known Activations