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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions that indicate time and duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤº
    -0.17
    \grid
    -0.17
    obra
    -0.17
    eson
    -0.16
    ãĥ¼ãĥ«ãĥī
    -0.15
    izin
    -0.15
    ãģĵãģĿ
    -0.15
    ascript
    -0.14
    911
    -0.14
    ãģĵãĤį
    -0.14
    POSITIVE LOGITS
     history
    0.18
    ialis
    0.16
     ever
    0.15
    enco
    0.15
    adas
    0.15
     nearly
    0.15
     memory
    0.14
     since
    0.14
     recorded
    0.14
     quite
    0.14
    Act Density 0.039%

    No Known Activations