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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues or controversies

    oai_token-act-pair · gpt-3.5-turbo

    topics that present significant challenges or critical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.82
    oud
    -0.79
     tremend
    -0.71
     troubles
    -0.68
    alian
    -0.68
    fal
    -0.68
    iple
    -0.66
    plex
    -0.66
    ãĤ¡
    -0.65
    apan
    -0.65
    POSITIVE LOGITS
     namely
    1.11
     Provided
    0.90
     Stories
    0.83
     Whereas
    0.81
     Countries
    0.73
     Journals
    0.72
     Scores
    0.72
     Firstly
    0.71
     They
    0.68
    YES
    0.68
    Act Density 0.115%

    No Known Activations