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

    Neuronpedia

    INDEX
    Explanations

    specific variables or identifiers in code or mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ***!
    -0.62
    SequentialGroup
    -0.59
     unknownFields
    -0.54
    PropertyChanging
    -0.53
    mtrl
    -0.50
     крае
    -0.50
    جوايز
    -0.49
     estekak
    -0.48
    weiß
    -0.47
    setVerticalGroup
    -0.46
    POSITIVE LOGITS
     Meksiku
    0.57
    IBOutlet
    0.56
     thème
    0.55
    titura
    0.54
     fédé
    0.53
     estimés
    0.52
     Standardi
    0.51
    tichetta
    0.51
     quelcon
    0.50
    تیاز
    0.50
    Act Density 0.149%

    No Known Activations