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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of identifying or defining concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eview
    -0.15
    ENARIO
    -0.13
    aver
    -0.13
    infeld
    -0.13
    uell
    -0.13
    اء
    -0.13
    ful
    -0.13
    aida
    -0.13
    /her
    -0.13
    ull
    -0.13
    POSITIVE LOGITS
    opoulos
    0.18
    /address
    0.15
    rael
    0.14
    UnderTest
    0.14
    ocos
    0.14
    abor
    0.14
    .scalablytyped
    0.14
    wchar
    0.14
    ipes
    0.14
    abeth
    0.14
    Act Density 0.033%

    No Known Activations