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

    Neuronpedia

    INDEX
    Explanations

    descriptions of uniqueness and unmatched qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    новништво
    -0.47
     intStringLen
    -0.43
     cumpli
    -0.43
    middels
    -0.42
     polizia
    -0.42
    DeleteBehavior
    -0.42
    hbase
    -0.41
    น่า
    -0.41
     cumplen
    -0.40
    janya
    -0.40
    POSITIVE LOGITS
     unique
    1.03
     unparalleled
    0.91
     Unique
    0.88
     UNIQUE
    0.86
     unieke
    0.86
     uniquely
    0.83
    unique
    0.82
     incomparable
    0.81
     einzigartigen
    0.79
    Unique
    0.79
    Act Density 0.208%

    No Known Activations