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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quantifiable subsets or examples within a larger context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etti
    -0.16
    iid
    -0.15
    rico
    -0.15
    .localized
    -0.14
    mund
    -0.13
    adro
    -0.13
    yk
    -0.13
    midt
    -0.13
     Percy
    -0.13
    idable
    -0.13
    POSITIVE LOGITS
    olon
    0.18
    же
    0.15
    á»ķ
    0.15
    olta
    0.14
    à¹ģล
    0.14
     Cable
    0.14
    quet
    0.14
    iskey
    0.14
    ashboard
    0.13
    JI
    0.13
    Act Density 0.105%

    No Known Activations