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

    Neuronpedia

    INDEX
    Explanations

    references to serialization processes and related programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pythagoras
    -0.49
    QueryBuilder
    -0.47
     RID
    -0.46
     Sasaki
    -0.46
    дования
    -0.45
    tagext
    -0.45
     שוליים
    -0.45
    GEBURTS
    -0.44
    ljeno
    -0.44
    ecuzione
    -0.43
    POSITIVE LOGITS
     freeze
    1.30
     preservation
    1.22
     Preservation
    1.16
     Freeze
    1.15
    freeze
    1.12
     frozen
    1.10
     freezes
    1.06
     Preserve
    1.04
    Freeze
    1.01
    preservation
    1.01
    Act Density 0.344%

    No Known Activations