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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to universal concepts and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urdy
    -0.16
    MBProgressHUD
    -0.15
    ARIANT
    -0.14
    isma
    -0.14
    ród
    -0.14
    IFORM
    -0.14
    Ctrls
    -0.14
    .terminate
    -0.14
    ÙĬات
    -0.14
    lenmiÅŁ
    -0.14
    POSITIVE LOGITS
    acha
    0.15
     Mas
    0.15
    ovich
    0.15
     overall
    0.15
    abama
    0.14
    maz
    0.14
     Glas
    0.14
    .mas
    0.14
     Lawson
    0.14
    overall
    0.14
    Act Density 0.041%

    No Known Activations