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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives and their relations to the subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erap
    -0.15
    аниÑĨ
    -0.14
    afen
    -0.14
    interop
    -0.14
    rer
    -0.14
    ropa
    -0.13
    ESIS
    -0.13
    ÙĦÛĮÙħ
    -0.13
    éļ
    -0.13
     destinationViewController
    -0.13
    POSITIVE LOGITS
    ippers
    0.16
     contain
    0.15
    rani
    0.15
     contains
    0.14
    anes
    0.13
    essen
    0.13
     verg
    0.13
     resource
    0.13
    assel
    0.13
    egr
    0.13
    Act Density 0.300%

    No Known Activations