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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance evaluation and the impact on operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to user experience and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    functioning and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FieldDescriptor
    -0.54
     متعلقه
    -0.49
     שוליים
    -0.49
     Wikimédia
    -0.48
    TemporalType
    -0.47
    URLException
    -0.46
    BorderFactory
    -0.45
    rungsseite
    -0.44
    AttributeSet
    -0.44
    ::_('
    -0.44
    POSITIVE LOGITS
     functioning
    1.24
    functioning
    1.03
     success
    1.00
     workings
    0.98
     operation
    0.98
     funcionamiento
    0.97
     funzionamento
    0.96
     fonctionnement
    0.89
     succès
    0.87
     dérou
    0.86
    Act Density 0.198%

    No Known Activations