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

    Neuronpedia

    INDEX
    Explanations

    references to military branches and personnel

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Diſ
    -0.91
    ſelf
    -0.90
    ſelves
    -0.86
     Anſ
    -0.85
     ſever
    -0.84
     Conſ
    -0.83
     Perſ
    -0.83
     miſ
    -0.82
     reaſon
    -0.82
     uſ
    -0.81
    POSITIVE LOGITS
    &
    0.68
     navy
    0.62
     Navy
    0.60
    아
    0.59
     وتسجيلات
    0.55
    сени
    0.54
    Autowired
    0.52
     ver
    0.51
    íncia
    0.51
    Navy
    0.51
    Act Density 0.008%

    No Known Activations