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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social progress, sustainability, and community building

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocks
    -0.15
    sam
    -0.15
    ams
    -0.14
    itone
    -0.14
     appropri
    -0.14
    ock
    -0.14
    ime
    -0.14
     busiest
    -0.14
    AVIS
    -0.14
    &view
    -0.13
    POSITIVE LOGITS
     healthy
    0.22
     prosperous
    0.21
     Secure
    0.20
     healthier
    0.20
     safe
    0.20
    thr
    0.20
     secure
    0.20
     fair
    0.20
     Vibr
    0.20
     truly
    0.20
    Act Density 0.200%

    No Known Activations