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

    Neuronpedia

    INDEX
    Explanations

    references to actions, entities, and elements indicative of social interactions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     departure
    -0.14
    uge
    -0.14
    925
    -0.13
    ssf
    -0.13
     fond
    -0.13
    emm
    -0.13
     departamento
    -0.13
     xÆ°Æ¡ng
    -0.13
     Depart
    -0.13
     ((!
    -0.12
    POSITIVE LOGITS
    raquo
    0.17
    nin
    0.16
    agged
    0.15
    ingo
    0.15
    adin
    0.15
    ustos
    0.15
    reak
    0.14
    lington
    0.14
    ayo
    0.14
    olumn
    0.14
    Act Density 0.089%

    No Known Activations