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

    Neuronpedia

    INDEX
    Explanations

    references to military actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥĩ
    -0.15
    otr
    -0.15
     wings
    -0.14
    .glide
    -0.14
     Abyss
    -0.14
     IBM
    -0.14
    erti
    -0.14
    èıĮ
    -0.14
     fleets
    -0.14
    agna
    -0.14
    POSITIVE LOGITS
     Taliban
    0.22
     Provincial
    0.20
     roadside
    0.20
     Afghan
    0.20
     coalition
    0.20
     Coalition
    0.20
     Forward
    0.18
     mortar
    0.18
    embedding
    0.18
     mort
    0.17
    Act Density 0.057%

    No Known Activations