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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating the conclusion or the last part of a text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and exclamation points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ramps
    -0.67
    rafted
    -0.66
    wagen
    -0.66
    ciplinary
    -0.65
     overpower
    -0.65
    biased
    -0.62
    ulously
    -0.62
     boun
    -0.62
     hust
    -0.60
     shelling
    -0.60
    POSITIVE LOGITS
     ********************************
    1.57
     =================================================================
    1.55
     ----------------------------------------------------------------
    1.50
     =================================
    1.47
     Conclusion
    1.43
     Lastly
    1.42
    ↵Âł
    1.38
     --------------------------------
    1.36
     Finally
    1.31
     Written
    1.31
    Act Density 0.611%

    No Known Activations