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

    Neuronpedia

    INDEX
    Explanations

    words related to politics and international relations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     bere
    -0.59
     Jasper
    -0.59
     Cullen
    -0.59
    sson
    -0.58
     EntityItem
    -0.58
     Edited
    -0.57
     Prohibition
    -0.56
     incred
    -0.56
     Philips
    -0.56
     succeeding
    -0.56
    POSITIVE LOGITS
    shaped
    1.32
    series
    1.06
    dimensional
    0.98
    bomb
    0.96
    factor
    0.92
    FU
    0.92
    level
    0.91
    Unit
    0.91
    word
    0.90
    section
    0.90
    Act Density 0.040%

    No Known Activations