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

    Neuronpedia

    INDEX
    Explanations

    instances of quantities and rates, particularly focusing on 'per' values indicating frequency or measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adar
    -0.16
     mornings
    -0.15
    VILLE
    -0.15
    ville
    -0.15
    lek
    -0.14
     monthly
    -0.14
     hourly
    -0.14
     ÑĤол
    -0.14
    horn
    -0.14
    STALL
    -0.14
    POSITIVE LOGITS
     year
    0.25
     week
    0.22
     day
    0.20
     month
    0.20
     ÑĢÑĸк
    0.18
     typical
    0.18
     nÄĥm
    0.17
     ÑģÑĥÑĤ
    0.16
     annum
    0.15
     годÑĥ
    0.15
    Act Density 0.027%

    No Known Activations