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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alice
    -0.17
    azu
    -0.16
    bourg
    -0.15
    ç
    -0.15
    raz
    -0.15
    enheim
    -0.15
    ales
    -0.15
    Bomb
    -0.14
    ellen
    -0.14
     Cunning
    -0.14
    POSITIVE LOGITS
    esso
    0.15
    aviours
    0.15
    ssp
    0.15
    _GC
    0.14
    esModule
    0.14
     ÑĤÑĢа
    0.14
    nets
    0.14
    naÄį
    0.14
    .Diff
    0.14
    rador
    0.14
    Act Density 0.086%

    No Known Activations