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

    Neuronpedia

    INDEX
    Explanations

    the word "awesome" with various intensities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement or positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avis
    -0.74
    arenthood
    -0.70
     Breed
    -0.70
    AUT
    -0.68
    Downloadha
    -0.68
    PT
    -0.68
     Clin
    -0.67
    eper
    -0.66
    unker
    -0.66
    arians
    -0.65
    POSITIVE LOGITS
     awesome
    0.92
     Awesome
    0.85
    NESS
    0.84
     fun
    0.83
    ly
    0.82
     stuff
    0.79
     thing
    0.77
     teamwork
    0.76
     synergy
    0.74
     idea
    0.72
    Act Density 0.019%

    No Known Activations