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

    Neuronpedia

    INDEX
    Explanations

    uppercase instances of the word "from"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.73
    expandindo
    -0.69
    lichter
    -0.68
    Хьажоргаш
    -0.66
     Lohan
    -0.63
     vtk
    -0.62
     Warszawie
    -0.61
    وظ
    -0.61
    geois
    -0.60
     okhttp
    -0.59
    POSITIVE LOGITS
     FROM
    2.19
     from
    2.13
    FROM
    2.06
    from
    2.04
     From
    1.89
    From
    1.86
     từ
    1.66
     från
    1.63
    desde
    1.53
     desde
    1.53
    Act Density 0.251%

    No Known Activations