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

    Neuronpedia

    INDEX
    Explanations

    positive expressions about various things such as watches, gifts, experiences, and more

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "awesome" expressing positive sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arenthood
    -0.71
    Mesh
    -0.69
    avis
    -0.69
     Breed
    -0.68
    ipt
    -0.66
    apers
    -0.66
    unker
    -0.66
    AUT
    -0.64
    chers
    -0.64
    PT
    -0.64
    POSITIVE LOGITS
     awesome
    0.93
     Awesome
    0.86
    ly
    0.81
     fun
    0.79
    NESS
    0.75
    ernaut
    0.73
     stuff
    0.73
     badass
    0.70
     teamwork
    0.70
     fabulous
    0.69
    Act Density 0.018%

    No Known Activations