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

    Neuronpedia

    INDEX
    Explanations

    mentions of military-related terms or topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gger
    -0.90
    âĶģ
    -0.77
    apest
    -0.73
    nob
    -0.71
    ï¸
    -0.70
    esta
    -0.68
    ividual
    -0.68
    orative
    -0.68
    DAY
    -0.68
    olog
    -0.67
    POSITIVE LOGITS
     dictatorship
    1.12
     commanders
    1.09
     fatig
    1.04
     barracks
    1.00
     personnel
    0.99
     commander
    0.99
     acad
    0.96
     academy
    0.93
     buildup
    0.93
     readiness
    0.91
    Act Density 0.050%

    No Known Activations