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

    Neuronpedia

    INDEX
    Explanations

    locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    --+
    -0.84
    thood
    -0.78
    wagen
    -0.74
    bs
    -0.71
    andr
    -0.71
    ass
    -0.71
    wcsstore
    -0.69
    nit
    -0.68
    Ign
    -0.68
    oly
    -0.68
    POSITIVE LOGITS
     southwest
    0.81
     southeast
    0.80
     Corridor
    0.73
     northwest
    0.73
     Regional
    0.72
    使
    0.71
     corner
    0.70
     bloc
    0.69
     northeast
    0.68
     Kazakhstan
    0.68
    Act Density 0.010%

    No Known Activations