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

    Neuronpedia

    INDEX
    Explanations

    information related to dates, events, and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rys
    -0.17
    iti
    -0.15
    vars
    -0.15
    UGHT
    -0.14
     Fridays
    -0.13
     ZákladnÃŃ
    -0.13
     Tier
    -0.13
    ARS
    -0.13
    ấ
    -0.13
     precondition
    -0.13
    POSITIVE LOGITS
     July
    0.23
     February
    0.22
     March
    0.22
     June
    0.21
     May
    0.21
     December
    0.21
     October
    0.21
     September
    0.20
     November
    0.19
     August
    0.19
    Act Density 0.254%

    No Known Activations