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

    Neuronpedia

    INDEX
    Explanations

    geographical names and locations related to specific countries and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſmall
    -0.91
     itſelf
    -0.89
     myſelf
    -0.87
     purpoſe
    -0.86
     greateſt
    -0.84
     ſtate
    -0.83
     ſeveral
    -0.83
     Efq
    -0.78
     reaſon
    -0.78
     Theſe
    -0.77
    POSITIVE LOGITS
     border
    0.49
    Билгалдахарш
    0.46
     Borders
    0.43
     neighboring
    0.42
    Borders
    0.42
     trans
    0.42
    border
    0.42
    trans
    0.41
    sist
    0.41
     and
    0.40
    Act Density 0.229%

    No Known Activations