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

    Neuronpedia

    INDEX
    Explanations

    statements indicating actions or decisions made by characters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    consulté
    -0.59
    älv
    -0.59
     елның
    -0.58
    UnknownFieldSet
    -0.58
     kasarigan
    -0.56
    Dislikes
    -0.56
    enschappelijke
    -0.56
    ">'.$
    -0.56
    '],$
    -0.56
     GenerationType
    -0.55
    POSITIVE LOGITS
     two
    0.70
     Kedua
    0.68
     kedua
    0.65
    Kedua
    0.62
     twofold
    0.61
    这两个
    0.60
     pair
    0.59
     Couple
    0.57
    Two
    0.57
     both
    0.57
    Act Density 0.321%

    No Known Activations