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

    Neuronpedia

    INDEX
    Explanations

    references to military hardware and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wing
    -0.17
    cken
    -0.17
     knife
    -0.16
     Wing
    -0.15
     Lind
    -0.15
    urovision
    -0.14
     dagger
    -0.14
    unan
    -0.14
     wing
    -0.14
    reed
    -0.14
    POSITIVE LOGITS
     battery
    0.25
     batteries
    0.24
    æ¦
    0.23
     Battery
    0.23
     shells
    0.22
     Batter
    0.22
     mort
    0.21
     Art
    0.20
     shell
    0.20
    Canon
    0.20
    Act Density 0.023%

    No Known Activations