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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    buster
    -0.71
     ante
    -0.66
     Accessed
    -0.65
    nam
    -0.62
    venant
    -0.62
     Donation
    -0.62
    cheon
    -0.61
    breaks
    -0.59
    querque
    -0.59
     articulated
    -0.58
    POSITIVE LOGITS
     us
    1.11
     passers
    1.03
     superiors
    1.00
     him
    0.98
     listeners
    0.98
     outsiders
    0.95
     viewers
    0.95
     me
    0.95
     everyone
    0.92
     readers
    0.91
    Act Density 1.342%

    No Known Activations