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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical locations, particularly "Fr" associated with France

    oai_token-act-pair · gpt-3.5-turbo

    references to "Frisian" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ython
    -0.77
    alla
    -0.70
     enrol
    -0.69
    Ĭ
    -0.64
    anmar
    -0.63
     concurrently
    -0.63
    ²¾
    -0.63
     biomark
    -0.62
    ī
    -0.62
    otal
    -0.62
    POSITIVE LOGITS
     Fr
    3.74
    Fr
    2.69
     fr
    2.00
    fr
    1.75
     FR
    1.43
     Fra
    1.29
     Franch
    1.22
     Franc
    1.21
     Gr
    1.17
     Fraser
    1.11
    Act Density 0.016%

    No Known Activations