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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "year" and related temporal markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldom
    -0.16
     eventual
    -0.15
    ibraries
    -0.15
    æľĢè¿ij
    -0.14
     Converts
    -0.13
     aujourd
    -0.13
    (can
    -0.13
    #echo
    -0.13
     recently
    -0.13
    ãģªãĤĵãģł
    -0.13
    POSITIVE LOGITS
     marks
    0.37
     marked
    0.35
    marks
    0.31
    marked
    0.29
    Marks
    0.24
     Marks
    0.24
     marking
    0.21
     saw
    0.21
    alone
    0.20
     mark
    0.19
    Act Density 0.050%

    No Known Activations