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

    Neuronpedia

    INDEX
    Explanations

    references to community and collective identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOY
    -0.17
    anik
    -0.17
    yre
    -0.17
    anten
    -0.15
    º
    -0.15
    ppers
    -0.14
    arrass
    -0.14
    akte
    -0.14
    ETO
    -0.14
    clinic
    -0.14
    POSITIVE LOGITS
     country
    0.32
     nation
    0.26
     planet
    0.25
     society
    0.25
     Nation
    0.25
     Country
    0.23
     cities
    0.23
    country
    0.23
     species
    0.23
     children
    0.22
    Act Density 0.134%

    No Known Activations