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

    Neuronpedia

    INDEX
    Explanations

    descriptions of protruding or sticking features

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.70
     Italijani
    -0.65
    AutoScale
    -0.62
     Nacionales
    -0.62
    gpl
    -0.61
     rând
    -0.61
    amentlich
    -0.60
    DatabaseError
    -0.59
     rapides
    -0.58
    SEGUIR
    -0.58
    POSITIVE LOGITS
     protr
    0.87
     protruding
    0.84
    突
    0.65
     prot
    0.62
     Aussch
    0.60
     EventEmitter
    0.59
    obut
    0.57
     promin
    0.56
    浮
    0.56
    πού
    0.54
    Act Density 0.024%

    No Known Activations