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

    Neuronpedia

    INDEX
    Explanations

    words related to large amounts, intensity, or significance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.91
    crow
    -0.87
    acus
    -0.78
    ades
    -0.77
    ramid
    -0.77
    arij
    -0.76
    ney
    -0.75
    illet
    -0.73
    arers
    -0.72
    EA
    -0.72
    POSITIVE LOGITS
     amount
    1.13
     importance
    1.12
     amounts
    1.09
     wealth
    1.04
     hardship
    1.02
     pleasure
    0.96
     riches
    0.95
     gratitude
    0.94
     quantities
    0.93
     hardships
    0.92
    Act Density 0.056%

    No Known Activations