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

    Neuronpedia

    INDEX
    Explanations

    phrases related to invariance under transformations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    "]);
    -0.90
     ').
    -0.85
    ########.
    -0.80
     مشين
    -0.79
     estekak
    -0.77
    "],
    -0.77
    "])
    -0.75
     تضيفلها
    -0.75
    ."),
    -0.73
    "]).
    -0.73
    POSITIVE LOGITS
     membres
    0.57
     kepolisian
    0.55
     demandes
    0.54
     eorum
    0.54
     supérieures
    0.54
     immédi
    0.53
     médecins
    0.53
     faptul
    0.52
    defn
    0.52
     chimiques
    0.51
    Act Density 0.003%

    No Known Activations