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

    Neuronpedia

    INDEX
    Explanations

    the word "from" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.69
    lichter
    -0.63
    geois
    -0.62
    ucchini
    -0.61
    وظ
    -0.59
     okhttp
    -0.59
     itſelf
    -0.56
    expandindo
    -0.55
    paksa
    -0.54
    lexikon
    -0.54
    POSITIVE LOGITS
     FROM
    2.12
     from
    2.07
    FROM
    1.98
    from
    1.94
     From
    1.81
    From
    1.77
     från
    1.68
     từ
    1.63
     desde
    1.50
    desde
    1.47
    Act Density 0.343%

    No Known Activations