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

    Neuronpedia

    INDEX
    Explanations

    technical phrases in a foreign language, potentially related to medicine

    oai_token-act-pair · gpt-3.5-turbo

    non-English characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.94
    aceutical
    -0.73
    .;
    -0.72
    Western
    -0.70
    Chinese
    -0.70
    Asian
    -0.70
    usterity
    -0.70
    Atlanta
    -0.70
    Jewish
    -0.69
    bright
    -0.69
    POSITIVE LOGITS
     est
    1.13
     este
    1.10
     tu
    1.05
     que
    1.03
     Ã
    1.00
     je
    0.99
     va
    0.98
     dat
    0.97
     é
    0.96
     si
    0.95
    Act Density 0.155%

    No Known Activations