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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -1.64
     encomp
    -1.63
     increa
    -1.63
     hairc
    -1.58
     disagre
    -1.58
     intersper
    -1.57
     affor
    -1.56
     perfet
    -1.56
     shenan
    -1.56
     inev
    -1.56
    POSITIVE LOGITS
    AfterEach
    0.69
     helped
    0.68
    makedirs
    0.67
     helping
    0.67
    RemoteException
    0.63
    ComponentScan
    0.62
     himself
    0.61
    abspath
    0.61
     successfully
    0.60
     worked
    0.60
    Act Density 1.080%

    No Known Activations