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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific professions or areas of expertise, like "Buddhist monk," "processed meats," and "Agricultural Center for Excellence."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDER
    -0.79
     Sins
    -0.75
     Izan
    -0.75
    ider
    -0.73
     Invisible
    -0.71
     Sever
    -0.70
    332
    -0.69
     Stranger
    -0.69
     332
    -0.68
    ido
    -0.68
    POSITIVE LOGITS
    ham
    0.92
    arat
    0.79
    acs
    0.78
    705
    0.77
    70
    0.76
    hops
    0.73
    anamo
    0.73
    aches
    0.70
    pal
    0.70
    709
    0.68
    Act Density 0.212%

    No Known Activations