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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to societal observations and criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     teda
    -0.44
    WebVitals
    -0.43
     mitään
    -0.41
     nadzieję
    -0.40
     صوتيه
    -0.40
     būs
    -0.40
    kolwiek
    -0.39
     persönlichen
    -0.39
    endpush
    -0.39
    zbęd
    -0.38
    POSITIVE LOGITS
     look
    1.94
     Look
    1.77
    Look
    1.68
    look
    1.66
     LOOK
    1.45
     remember
    1.42
     imagine
    1.41
     think
    1.33
     consider
    1.31
     notice
    1.30
    Act Density 0.603%

    No Known Activations