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

    Neuronpedia

    INDEX
    Explanations

    references to consequences and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     everybody
    -1.05
     guys
    -1.02
    Everybody
    -1.01
     Everybody
    -0.96
     somebody
    -0.95
     stuff
    -0.90
    Somebody
    -0.88
    everybody
    -0.84
    Guys
    -0.81
    Nobody
    -0.81
    POSITIVE LOGITS
    etheless
    1.00
     CreateTagHelper
    0.94
    setVerticalGroup
    0.92
    Datuak
    0.90
     كومونز
    0.89
    FundMe
    0.89
     TestBed
    0.88
    ItemBackground
    0.88
    AxisAlignment
    0.87
    InjectAttribute
    0.87
    Act Density 1.915%

    No Known Activations