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

    Neuronpedia

    INDEX
    Explanations

    mentions of universities or educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "UN"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussen
    -0.77
    chnology
    -0.71
    iris
    -0.69
    toe
    -0.67
     Noir
    -0.66
    ãĤ¼
    -0.64
    antine
    -0.64
    igne
    -0.64
     Teg
    -0.64
     Malfoy
    -0.63
    POSITIVE LOGITS
    KNOWN
    1.30
    IVERS
    1.27
    TING
    1.12
    ESCO
    1.10
    HCR
    1.09
    DER
    1.08
    ITED
    1.01
    DAY
    0.99
    ISON
    0.99
    ION
    0.95
    Act Density 0.012%

    No Known Activations