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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of 'origin'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </i>
    -0.81
    </b>
    -0.80
    dymyr
    -0.71
     Monza
    -0.67
    Samoa
    -0.67
     Waw
    -0.65
    owulf
    -0.65
    <b>
    -0.63
    Chham
    -0.62
    s
    -0.62
    POSITIVE LOGITS
     Origin
    2.06
     origin
    2.03
    Origin
    2.00
    origin
    2.00
     ORIGIN
    1.78
     Origins
    1.77
     origins
    1.76
    ORIGIN
    1.66
    Origins
    1.66
    origins
    1.60
    Act Density 0.068%

    No Known Activations