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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political conflict and international relations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilts
    -0.75
    Æ
    -0.71
    ice
    -0.70
    Pac
    -0.67
    aneers
    -0.67
    itud
    -0.67
    vati
    -0.66
    oldemort
    -0.66
    ]'
    -0.65
    apo
    -0.65
    POSITIVE LOGITS
     own
    1.24
     mileage
    1.13
     favorite
    1.11
     favourite
    1.09
     imagination
    0.97
     fingertips
    0.91
    ths
    0.91
     choice
    0.90
    selves
    0.89
     browser
    0.88
    Act Density 0.107%

    No Known Activations