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

    Neuronpedia

    INDEX
    Explanations

    quantitative references to measurement such as distances, heights, and statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspeak
    -1.02
     intersper
    -1.02
     increa
    -1.01
     affor
    -0.97
     reluct
    -0.97
     impra
    -0.96
     encomp
    -0.96
     indescri
    -0.94
     Bartholo
    -0.94
     Rine
    -0.89
    POSITIVE LOGITS
     amount
    1.17
    amount
    1.09
     amounts
    1.08
    Amount
    1.03
     Amount
    1.00
     AMOUNT
    0.92
    tamount
    0.84
    AMOUNT
    0.84
    amounts
    0.81
     cantidad
    0.75
    Act Density 0.092%

    No Known Activations