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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and possessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /*++
    -0.51
    centr
    -0.48
     pres
    -0.48
     Pres
    -0.45
    pres
    -0.45
     adulte
    -0.44
    ItemCount
    -0.44
    ارم
    -0.43
    來看
    -0.42
     Tanner
    -0.42
    POSITIVE LOGITS
     Himself
    0.75
    +#+#
    0.73
    sizeCache
    0.69
     himself
    0.68
    principalTable
    0.66
    nodoc
    0.65
    principalColumn
    0.64
     thier
    0.64
     dirinya
    0.63
     THEIR
    0.62
    Act Density 0.550%

    No Known Activations