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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political meetings or discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    afety
    -0.62
    HAM
    -0.62
    hoe
    -0.61
    hire
    -0.59
    etter
    -0.59
    letter
    -0.59
    acre
    -0.59
    SG
    -0.59
    john
    -0.57
    Magikarp
    -0.57
    POSITIVE LOGITS
     Thumbnails
    0.78
     ACTIONS
    0.75
    emort
    0.69
    thumbnails
    0.69
    romeda
    0.66
     Videos
    0.65
    osite
    0.64
     sidx
    0.63
    rosse
    0.63
     Photos
    0.60
    Act Density 0.016%

    No Known Activations