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

    Neuronpedia

    INDEX
    Explanations

    references to studies or citations in research papers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    le
    -0.58
     مشين
    -0.58
    k
    -0.58
    shafen
    -0.56
     createState
    -0.54
    p
    -0.54
    Without
    -0.53
    tisgarh
    -0.52
    ith
    -0.50
     beans
    -0.50
    POSITIVE LOGITS
     تضيفلها
    0.79
    InputBorder
    0.76
     telefónica
    0.73
    Extinguishing
    0.69
    OMI
    0.67
     Económica
    0.66
    ercises
    0.65
    ctional
    0.64
     autorytatywna
    0.64
     Anſ
    0.64
    Act Density 0.008%

    No Known Activations