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

    Neuronpedia

    INDEX
    Explanations

    references to military involvement and the formation of military units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rosso
    -0.18
     chatte
    -0.16
    ائر
    -0.16
    è³¢
    -0.16
    klady
    -0.15
    anske
    -0.15
    ITTE
    -0.15
    .Atomic
    -0.14
    sanitize
    -0.14
    ød
    -0.14
    POSITIVE LOGITS
     training
    0.20
     units
    0.19
     formations
    0.18
    Training
    0.18
     Training
    0.18
    training
    0.17
    åĭŁ
    0.17
     uniform
    0.16
    -un
    0.16
     Units
    0.16
    Act Density 0.107%

    No Known Activations