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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global issues and making the world a better place

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments regarding the world's state and its future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -1.02
    oyal
    -0.76
     omission
    -0.66
    itone
    -0.64
    ois
    -0.63
     personally
    -0.63
    ints
    -0.62
     predecessors
    -0.61
    ricular
    -0.60
     succeed
    -0.60
    POSITIVE LOGITS
    Thumbnail
    0.76
     Tsukuyomi
    0.74
     darkened
    0.71
     revolves
    0.71
    ģ«
    0.67
     tilted
    0.67
    iven
    0.66
     trillions
    0.66
    ********
    0.65
     Watergate
    0.65
    Act Density 0.618%

    No Known Activations