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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating amounts, comparisons, or significant numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .blob
    -0.15
     же
    -0.15
    anten
    -0.14
    wij
    -0.14
    çĴ°
    -0.13
    ptime
    -0.13
    Immutable
    -0.13
    ughter
    -0.13
     Sant
    -0.13
    eç
    -0.13
    POSITIVE LOGITS
     bust
    0.16
    inski
    0.15
    rens
    0.14
    yx
    0.14
    ahren
    0.14
    isher
    0.14
    iani
    0.14
    isser
    0.14
    eneg
    0.14
     Closet
    0.14
    Act Density 1.428%

    No Known Activations