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

    Neuronpedia

    INDEX
    Explanations

    terms related to applied sciences and mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppard
    -0.17
    ëŀĮ
    -0.15
    ocos
    -0.15
    lew
    -0.15
    itori
    -0.15
    atori
    -0.15
    iena
    -0.14
    eland
    -0.14
    iser
    -0.14
    ADIUS
    -0.14
    POSITIVE LOGITS
    arters
    0.17
    bach
    0.16
    298
    0.15
    zik
    0.15
    inde
    0.14
    RTL
    0.14
    anken
    0.14
    chas
    0.13
    485
    0.13
    ode
    0.13
    Act Density 0.010%

    No Known Activations