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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating familiarity or awareness of past events

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.92
     مشين
    -0.90
     дописавши
    -0.88
     surla
    -0.82
     estekak
    -0.79
    Autoritní
    -0.79
    PreferredItem
    -0.78
    ThroughAttribute
    -0.77
    Tembelea
    -0.76
    VIAF
    -0.75
    POSITIVE LOGITS
     or
    0.54
     recent
    0.54
     recenti
    0.52
     hasard
    0.52
     हुए
    0.51
     Recent
    0.50
     
    0.50
     I
    0.49
     v
    0.48
    Recent
    0.47
    Act Density 0.029%

    No Known Activations