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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    λοι
    -0.17
    lech
    -0.16
    бÑĭ
    -0.16
    urai
    -0.16
    anut
    -0.15
    achat
    -0.14
    ruh
    -0.14
    kah
    -0.14
    WidgetItem
    -0.14
    reu
    -0.13
    POSITIVE LOGITS
     Tom
    0.24
    Tom
    0.23
     Том
    0.19
     tom
    0.17
     TOM
    0.17
    Aqu
    0.15
    ç¢İ
    0.15
    .tom
    0.15
    ixo
    0.14
     Tomas
    0.14
    Act Density 0.037%

    No Known Activations