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

    Neuronpedia

    INDEX
    Explanations

    discussions about societal values and personal beliefs surrounding power dynamics and autonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     --
    -1.45
     ---
    -1.27
     ‘’
    -1.26
    ......”
    -1.18
     ----
    -1.17
     ......
    -1.12
     -----
    -1.08
     .....
    -1.04
     ―
    -1.00
     ------
    -0.98
    POSITIVE LOGITS
    –
    2.63
    )–
    1.66
    .–
    1.49
    ,–
    1.30
    –)
    1.21
    ・
    1.18
    –¿
    1.06
    −
    1.05
    \_
    1.04
    ––
    1.02
    Act Density 1.041%

    No Known Activations