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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attribution and responsibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.70
    esez
    -0.68
     ioutil
    -0.68
    XMLSchema
    -0.66
    ViewChild
    -0.64
    PhysRev
    -0.63
    ########.
    -0.62
    GEBURTS
    -0.62
     OFDb
    -0.61
    ModelSerializer
    -0.61
    POSITIVE LOGITS
     attributed
    1.29
     attribution
    1.23
     atribu
    1.17
     blame
    1.15
     Attribution
    1.14
    Attribution
    1.14
    attribution
    0.97
     attribué
    0.96
     blames
    0.96
     blamed
    0.94
    Act Density 0.383%

    No Known Activations