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

    Neuronpedia

    INDEX
    Explanations

    phrases related to armed conflicts or militant groups

    oai_token-act-pair · gpt-3.5-turbo

    words related to guerrilla warfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.87
    ŃĶ
    -0.75
    picture
    -0.69
     Pradesh
    -0.68
     Redux
    -0.67
    quartered
    -0.66
     Cycle
    -0.64
    croft
    -0.64
     Spectrum
    -0.63
    20439
    -0.63
    POSITIVE LOGITS
    inea
    1.22
    vernment
    1.12
    cci
    1.00
    ilt
    1.00
    arding
    0.99
    ilts
    0.98
    ppy
    0.94
    aret
    0.88
    ile
    0.88
    arded
    0.86
    Act Density 0.009%

    No Known Activations