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

    Neuronpedia

    INDEX
    Explanations

    references to the United Kingdom (UK)

    oai_token-act-pair · gpt-3.5-turbo

    references to the United Kingdom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciplinary
    -0.68
     mc
    -0.67
     cort
    -0.67
    tons
    -0.67
    block
    -0.66
    chin
    -0.62
    cler
    -0.61
    practice
    -0.61
     saturated
    -0.61
    clud
    -0.61
    POSITIVE LOGITS
     UKIP
    1.11
    UK
    1.09
    JV
    0.98
    MAP
    0.93
    RA
    0.90
    CAN
    0.89
    tarian
    0.88
    UGE
    0.88
    AIN
    0.87
    ION
    0.86
    Act Density 0.007%

    No Known Activations