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

    Neuronpedia

    INDEX
    Explanations

    proper nouns that denote locations or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lest
    -0.16
    lessly
    -0.16
    udad
    -0.15
    olation
    -0.15
    holding
    -0.15
     olan
    -0.15
    .UIManager
    -0.14
    horse
    -0.14
    ELLOW
    -0.14
    LES
    -0.14
    POSITIVE LOGITS
    neau
    0.20
    shire
    0.18
    lu
    0.17
    essa
    0.17
    ormal
    0.16
    werp
    0.16
    these
    0.16
    ract
    0.15
    ucle
    0.15
    aires
    0.15
    Act Density 0.084%

    No Known Activations