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

    Neuronpedia

    INDEX
    Explanations

    quantitative data related to percentages and statistical results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -1.22
     betweenstory
    -1.15
     kaarangay
    -1.12
    principalTable
    -0.96
    ThroughAttribute
    -0.92
    Geplaatst
    -0.92
    ьаж
    -0.91
    ]--;
    -0.90
     lenker
    -0.89
    Билгалдахарш
    -0.88
    POSITIVE LOGITS
    ,
    0.68
    .
    0.56
     in
    0.54
     for
    0.53
     of
    0.52
      
    0.52
     at
    0.50
     to
    0.44
     ,
    0.44
     from
    0.43
    Act Density 0.897%

    No Known Activations