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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions that indicate the word "from."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.96
     Houſe
    -0.82
     Reſ
    -0.80
     Maori
    -0.77
     CMY
    -0.77
     cartier
    -0.76
     Danzig
    -0.75
     Bastille
    -0.75
     Majefty
    -0.75
     IMEI
    -0.74
    POSITIVE LOGITS
     FROM
    1.68
    FROM
    1.59
     From
    1.45
     from
    1.38
    from
    1.26
    From
    1.25
    Từ
    1.24
    getFrom
    1.18
     Từ
    1.17
     từ
    1.08
    Act Density 0.252%

    No Known Activations