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

    Neuronpedia

    INDEX
    Explanations

    topics of discussion

    oai_token-act-pair · gpt-3.5-turbo

    references to various topics of discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignt
    -0.79
     Yates
    -0.77
    urses
    -0.75
    omers
    -0.69
    xon
    -0.67
    raphics
    -0.66
     Kats
    -0.66
    zik
    -0.64
    otted
    -0.64
    arus
    -0.64
    POSITIVE LOGITS
     topics
    0.91
     topic
    0.90
    topic
    0.89
    Topics
    0.83
    Topic
    0.83
     Topics
    0.81
    matter
    0.79
    icular
    0.77
    worm
    0.77
    forum
    0.76
    Act Density 0.023%

    No Known Activations