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

    Neuronpedia

    INDEX
    Explanations

    positive experiences and emotional expressions related to enjoyment and pleasure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.15
    anta
    -0.15
    ampa
    -0.15
    ohen
    -0.14
    aleb
    -0.14
    )(__
    -0.13
     Quiet
    -0.13
    hydro
    -0.13
    olumbia
    -0.13
    PWD
    -0.13
    POSITIVE LOGITS
    ä¸Ī
    0.15
    appen
    0.15
    wards
    0.15
    JNIEnv
    0.14
    ionage
    0.14
    berapa
    0.14
    жд
    0.14
    jvu
    0.13
    zon
    0.13
    annels
    0.13
    Act Density 0.181%

    No Known Activations