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

    Neuronpedia

    INDEX
    Explanations

    references to user policy validation scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neck
    -0.16
    ASY
    -0.14
    /MPL
    -0.13
    asy
    -0.13
    оваÑĢи
    -0.13
     Haley
    -0.13
    άλ
    -0.13
    nek
    -0.13
    unes
    -0.13
     Smithsonian
    -0.12
    POSITIVE LOGITS
    linkplain
    0.14
    arness
    0.14
    Ïģον
    0.14
    ÑĥлÑı
    0.14
    .va
    0.14
    .onView
    0.14
    PING
    0.13
    uien
    0.13
    ublic
    0.13
    erval
    0.13
    Act Density 0.071%

    No Known Activations