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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong opinions or evaluations about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Earth
    -0.15
     Scalars
    -0.14
    ãĤ¹ãĤ¯
    -0.14
    swick
    -0.14
    Ùģر
    -0.14
     hind
    -0.14
    éļİ
    -0.13
    507
    -0.13
    lip
    -0.13
     Helm
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.18
     Nez
    0.15
    .VK
    0.15
    luet
    0.14
    adge
    0.14
    Ïģι
    0.14
     знаком
    0.14
    eger
    0.14
    _IOCTL
    0.14
    akedirs
    0.14
    Act Density 0.190%

    No Known Activations