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

    Neuronpedia

    INDEX
    Explanations

    references to time durations expressed in weeks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     YEARS
    -0.17
    613
    -0.17
     years
    -0.16
    ythe
    -0.15
     decade
    -0.15
    Years
    -0.15
    254
    -0.15
    944
    -0.15
    ech
    -0.15
    eless
    -0.15
    POSITIVE LOGITS
    /month
    0.26
    ãĥ³ãĤº
    0.17
    ë§IJ
    0.17
    lies
    0.17
    (month
    0.16
    ends
    0.15
    month
    0.15
    enden
    0.15
     month
    0.15
    Howard
    0.15
    Act Density 0.042%

    No Known Activations