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

    source or origin indicator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.79
     ſche
    -0.68
     ſtate
    -0.65
     bookId
    -0.61
     ſte
    -0.60
     ſta
    -0.59
     purpoſe
    -0.59
     juſ
    -0.57
     paſſ
    -0.57
     Majefty
    -0.56
    POSITIVE LOGITS
    from
    2.30
    FROM
    1.48
     FROM
    1.34
     from
    1.34
    From
    1.24
     From
    1.18
    getFrom
    1.02
     từ
    1.02
    จาก
    1.00
     från
    0.98
    Act Density 0.007%

    No Known Activations