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

    Neuronpedia

    INDEX
    Explanations

    names and surnames, particularly those with specific linguistic patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idad
    -0.15
    ãĤº
    -0.14
    874
    -0.14
    mente
    -0.14
    uong
    -0.13
    vette
    -0.13
    Ħìŀ¬
    -0.13
    ÌĪ
    -0.13
    ooke
    -0.13
    antal
    -0.13
    POSITIVE LOGITS
    mann
    0.17
    itsu
    0.15
    mma
    0.15
    lemen
    0.15
    OTA
    0.14
    auer
    0.14
    ocker
    0.14
    ERSHEY
    0.14
    ertz
    0.14
    -Fi
    0.14
    Act Density 0.441%

    No Known Activations