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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate measurements or rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĥÏĩ
    -0.17
    unger
    -0.16
    yard
    -0.15
    routine
    -0.14
    us
    -0.14
    erties
    -0.14
    eg
    -0.14
    们
    -0.14
    info
    -0.13
    jen
    -0.13
    POSITIVE LOGITS
     annum
    0.19
    isposable
    0.15
    fter
    0.15
    iphery
    0.15
    ipherals
    0.15
    ipher
    0.15
    pend
    0.15
    legate
    0.14
    .Tx
    0.14
     keer
    0.14
    Act Density 0.024%

    No Known Activations