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

    Neuronpedia

    INDEX
    Explanations

    locations or positions within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.73
    deen
    -0.72
    RAW
    -0.66
     Thousand
    -0.66
    IELD
    -0.66
    graduate
    -0.64
     Ended
    -0.63
    FactoryReloaded
    -0.63
    PDATE
    -0.63
    Ô
    -0.62
    POSITIVE LOGITS
     loc
    1.25
    ator
    1.13
    ators
    1.02
    itud
    0.92
    iously
    0.87
    us
    0.87
    ational
    0.87
    uating
    0.81
    inia
    0.79
    ger
    0.79
    Act Density 0.010%

    No Known Activations