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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and verbs, particularly those related to time or transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istinguish
    -0.16
    ££
    -0.16
    lland
    -0.16
    actic
    -0.15
    ÙĦات
    -0.15
    _presence
    -0.15
    grams
    -0.15
    engo
    -0.14
    isNew
    -0.14
    çĴĥ
    -0.14
    POSITIVE LOGITS
     bust
    0.15
     nat
    0.15
    unden
    0.14
    idy
    0.14
    weekday
    0.14
    .Toolkit
    0.13
    .bus
    0.13
    ansk
    0.13
    onia
    0.13
    åħ
    0.13
    Act Density 0.001%

    No Known Activations