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

    Neuronpedia

    INDEX
    Explanations

    references to periods of time or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antu
    -0.16
    ãĥªãĥ¼ãĤº
    -0.14
     Batch
    -0.14
    aro
    -0.14
    ÑĤим
    -0.14
    abox
    -0.14
    ovat
    -0.14
    Batch
    -0.14
     toho
    -0.14
     hrom
    -0.13
    POSITIVE LOGITS
     period
    0.26
     course
    0.23
     periods
    0.22
     tenure
    0.21
     reign
    0.20
     height
    0.19
    period
    0.19
     péri
    0.18
     hey
    0.18
     periodo
    0.18
    Act Density 0.112%

    No Known Activations