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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific term ("Hyatt")

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific placeholders or tags in a structured document format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IFIED
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.72
    DERR
    -0.70
    Ø©
    -0.67
    emouth
    -0.66
    女
    -0.66
    Adds
    -0.65
    س
    -0.61
    ãĤ´ãĥ³
    -0.61
    iants
    -0.60
    POSITIVE LOGITS
    brid
    1.21
    brids
    1.20
    giene
    1.18
    undai
    1.10
    annis
    1.06
    rule
    1.05
    atts
    1.00
    bris
    0.92
    ster
    0.86
    tro
    0.86
    Act Density 0.032%

    No Known Activations