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

    Neuronpedia

    INDEX
    Explanations

    names or terms with "ul" as a suffix, potentially related to names or places

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific suffix or ending in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĢIJ
    -0.69
     Hitman
    -0.69
     Tables
    -0.62
     Skydragon
    -0.62
     Picture
    -0.62
     Citation
    -0.60
     Collider
    -0.60
     Chest
    -0.60
    ãĤ¤ãĥĪ
    -0.60
     Mickey
    -0.59
    POSITIVE LOGITS
    monary
    1.12
    terior
    1.00
    otine
    0.87
    gins
    0.85
    gence
    0.85
    ibrary
    0.84
    iple
    0.84
    ums
    0.83
    anguage
    0.80
    esc
    0.80
    Act Density 0.039%

    No Known Activations