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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being imprisoned or held captive

    oai_token-act-pair · gpt-3.5-turbo

    references to prisoners of war

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Boll
    -0.78
    orp
    -0.73
    OPA
    -0.71
     Remastered
    -0.71
    orie
    -0.68
    lag
    -0.67
     Ples
    -0.65
    wig
    -0.65
    amera
    -0.64
     Blizz
    -0.64
    POSITIVE LOGITS
     prisoners
    1.01
     prisoner
    0.89
     inmates
    0.89
     captives
    0.89
     sentenced
    0.87
     detainees
    0.81
     incarcerated
    0.80
    prison
    0.78
     jailed
    0.76
     inmate
    0.76
    Act Density 0.032%

    No Known Activations