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

    Neuronpedia

    INDEX
    Explanations

    terms related to software licensing and usage permissions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     typelib
    -0.63
    StoryboardSegue
    -0.59
    ########.
    -0.59
    Jîn
    -0.54
     MenuView
    -0.52
     NSCoder
    -0.51
    DotNetBar
    -0.51
     externi
    -0.50
    Diweddarwch
    -0.49
    StructEnd
    -0.49
    POSITIVE LOGITS
     للاسماء
    0.66
     بيها
    0.58
    новниш
    0.57
     Zwiebel
    0.54
    ]")]
    0.53
    ggiata
    0.51
    acterium
    0.50
     Lieder
    0.50
    ✭
    0.50
    NSON
    0.48
    Act Density 0.002%

    No Known Activations