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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "from"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.90
     ſche
    -0.86
     purpoſe
    -0.76
     ſta
    -0.74
     juſ
    -0.73
     ſtate
    -0.73
     fédé
    -0.73
     ſtand
    -0.72
     ſol
    -0.71
     faſt
    -0.70
    POSITIVE LOGITS
     from
    1.41
    from
    1.33
     From
    1.27
     FROM
    1.27
    From
    1.23
    FROM
    1.14
    getFrom
    0.97
    จาก
    0.96
     dari
    0.91
     từ
    0.90
    Act Density 0.345%

    No Known Activations