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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating a comparison or categorization

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing a sense of categorization or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nut
    -0.75
    DS
    -0.75
    LAN
    -0.69
    BLE
    -0.69
     VIDEOS
    -0.66
    database
    -0.65
    league
    -0.64
    yer
    -0.64
    USA
    -0.64
    interrupted
    -0.64
    POSITIVE LOGITS
    sort
    0.86
     sort
    0.85
    ãĤ¦ãĤ¹
    0.84
    ilege
    0.77
    Sort
    0.74
     Sort
    0.73
    unia
    0.70
     sorting
    0.69
    atism
    0.69
    entially
    0.68
    Act Density 0.018%

    No Known Activations