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

    Neuronpedia

    INDEX
    Explanations

    references to timeframes and deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thurs
    -0.15
    Thu
    -0.15
     Fridays
    -0.14
     Tues
    -0.14
    arken
    -0.14
    iene
    -0.14
    amente
    -0.14
    ovel
    -0.14
    abol
    -0.14
    uft
    -0.14
    POSITIVE LOGITS
    acle
    0.19
     May
    0.17
     March
    0.17
     early
    0.17
     June
    0.16
    LOAT
    0.16
     February
    0.15
     late
    0.15
     July
    0.15
     August
    0.15
    Act Density 0.183%

    No Known Activations