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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rumors and misinformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.81
    ViewFeatures
    -0.80
    TestingModule
    -0.72
    +#+
    -0.64
    ChromeDriver
    -0.64
    rrggbb
    -0.61
    archiviato
    -0.58
    GEBURTSDATUM
    -0.58
    makeConstraints
    -0.58
    WithIOException
    -0.58
    POSITIVE LOGITS
     rumors
    1.31
     rumor
    1.28
     rumour
    1.27
     rumours
    1.25
     Rumors
    1.05
     rumores
    1.05
    Rumors
    1.03
     gossip
    1.00
     rumored
    0.94
     circulated
    0.93
    Act Density 0.262%

    No Known Activations