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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific groups or individuals in a political or military context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific groups or individuals related to geopolitical conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Piercing
    -0.73
     Wonderland
    -0.71
     Virgin
    -0.69
     Matter
    -0.65
     USAF
    -0.65
    ++++++++++++++++
    -0.64
     Valentine
    -0.64
     Cross
    -0.64
     Blessed
    -0.63
    gger
    -0.62
    POSITIVE LOGITS
    poons
    0.89
    accompan
    0.85
     Houth
    0.84
     seiz
    0.84
    ileaks
    0.79
    ilitation
    0.78
    ipedia
    0.77
    arov
    0.77
    isi
    0.75
    oons
    0.74
    Act Density 0.002%

    No Known Activations