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

    Neuronpedia

    INDEX
    Explanations

    punctuation and transitional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SystemService
    -0.17
    urai
    -0.16
    aska
    -0.16
    HI
    -0.16
     Norm
    -0.15
     HI
    -0.14
    addock
    -0.14
    ãģ¡ãĤĩ
    -0.14
    ãģĵãĤĵ
    -0.14
    κÏģι
    -0.14
    POSITIVE LOGITS
    以
    0.15
     hammer
    0.15
    816
    0.15
    orch
    0.15
    hoff
    0.14
    .EMPTY
    0.14
    izer
    0.14
    ÙĤات
    0.13
     Seymour
    0.13
    061
    0.13
    Act Density 0.003%

    No Known Activations