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

    Neuronpedia

    INDEX
    Explanations

    terms associated with variability and change over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cÃłng
    -0.16
    átka
    -0.15
    anst
    -0.15
    worm
    -0.14
    divide
    -0.14
     Ø®ÙĦÙģ
    -0.14
    echan
    -0.14
    .dm
    -0.14
     æ¡
    -0.14
    quet
    -0.13
    POSITIVE LOGITS
    zin
    0.15
     cav
    0.15
    380
    0.15
    587
    0.14
    iable
    0.14
    iability
    0.14
    ldb
    0.14
     Fairfield
    0.14
     subclass
    0.14
    162
    0.14
    Act Density 0.114%

    No Known Activations