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

    Neuronpedia

    INDEX
    Explanations

    mentions of phone calls, especially those discussing requests or complaints

    oai_token-act-pair · gpt-3.5-turbo

    instances of communication or requests being made

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ema
    -0.68
     presidency
    -0.67
     predecessor
    -0.67
     Compass
    -0.66
    onom
    -0.65
     Means
    -0.61
     Govern
    -0.61
     successor
    -0.61
     lender
    -0.60
    ursion
    -0.60
    POSITIVE LOGITS
     frantically
    0.93
     piles
    0.92
     endlessly
    0.89
     dinners
    0.88
     snippets
    0.86
    iddles
    0.84
     tons
    0.84
     pots
    0.83
     stuff
    0.83
     rows
    0.82
    Act Density 0.973%

    No Known Activations