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

    Neuronpedia

    INDEX
    Explanations

    statistics related to casualties and attacks in conflict zones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilos
    -0.16
    aben
    -0.15
    pton
    -0.15
    ÃŃf
    -0.14
    ladu
    -0.14
    assin
    -0.14
     Samp
    -0.14
    ãĥ«ãĥķ
    -0.14
    ucker
    -0.13
    .ra
    -0.13
    POSITIVE LOGITS
     sold
    0.22
    sold
    0.21
     security
    0.19
     Civ
    0.17
     lightly
    0.17
    bedo
    0.17
     guards
    0.17
     policeman
    0.17
    .security
    0.16
     SOLD
    0.16
    Act Density 0.069%

    No Known Activations