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

    Neuronpedia

    INDEX
    Explanations

    keywords related to authority, power, and control dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.65
    resave
    -0.53
    ezers
    -0.51
    aarrggbb
    -0.48
     jedenfalls
    -0.48
    今度は
    -0.46
    multicolumn
    -0.46
    CharStream
    -0.45
     natürlich
    -0.44
     CELLS
    -0.44
    POSITIVE LOGITS
     successfully
    0.68
    ]--;
    0.67
     succeeded
    0.62
    Портал
    0.54
     jadx
    0.54
     Soccerway
    0.54
    ercises
    0.52
     Successful
    0.52
     successful
    0.52
    diğinde
    0.51
    Act Density 0.074%

    No Known Activations