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

    Neuronpedia

    INDEX
    Explanations

    references to events and gatherings involving groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ounty
    -0.14
    etty
    -0.14
    aucoup
    -0.14
    vez
    -0.13
    ÑĮ
    -0.13
    alion
    -0.13
    讯
    -0.13
    è¢
    -0.13
    ograms
    -0.13
    æļ
    -0.13
    POSITIVE LOGITS
     witness
    0.60
     watching
    0.59
     witnessing
    0.57
     watch
    0.56
    watch
    0.52
     Witness
    0.50
     watcher
    0.50
     observer
    0.49
     witnesses
    0.49
     spectator
    0.49
    Act Density 0.426%

    No Known Activations