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

    Neuronpedia

    INDEX
    Explanations

    instances of high-frequency words or phrases that indicate emotional states or significant actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edException
    -0.16
    RING
    -0.16
    uden
    -0.15
    aga
    -0.15
    ATRIX
    -0.15
    ALES
    -0.15
    ERAL
    -0.14
    atches
    -0.14
    epar
    -0.14
    Äħż
    -0.14
    POSITIVE LOGITS
    &action
    0.19
    à¥Įर
    0.15
    IT
    0.15
     Freund
    0.15
    927
    0.15
    pson
    0.14
    SD
    0.14
     Aure
    0.14
     air
    0.14
     ÙĩÙĨ
    0.14
    Act Density 0.000%

    No Known Activations