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

    Neuronpedia

    INDEX
    Explanations

    words related to entities and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illez
    -0.16
    astes
    -0.16
    obraz
    -0.15
    ĪæĿĥ
    -0.15
     Prelude
    -0.15
    @admin
    -0.14
    losures
    -0.14
    cente
    -0.14
    YM
    -0.14
    vae
    -0.14
    POSITIVE LOGITS
    лÑĥг
    0.18
    ioni
    0.16
    erner
    0.15
    fully
    0.14
    asco
    0.14
    istrovstvÃŃ
    0.14
     Feinstein
    0.14
    BAD
    0.14
    宿
    0.14
    itter
    0.14
    Act Density 0.000%

    No Known Activations