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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social commentary and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Искәрмәләр
    -0.62
    endphp
    -0.60
    arynx
    -0.60
    Географиясе
    -0.57
    談社
    -0.56
    reportWebVitals
    -0.56
     solitario
    -0.55
    ParallelGroup
    -0.55
    melons
    -0.55
    πουργ
    -0.55
    POSITIVE LOGITS
     themselves
    1.02
     their
    0.85
    themselves
    0.74
    their
    0.68
    Their
    0.66
     Their
    0.66
     THEIR
    0.64
     kteří
    0.59
     yourselves
    0.59
     theirs
    0.52
    Act Density 1.067%

    No Known Activations