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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating relationships and connections between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĸ
    -0.15
     isNaN
    -0.14
    adm
    -0.14
    姫
    -0.14
     rem
    -0.13
     settling
    -0.13
    vens
    -0.13
    _given
    -0.13
    .googleapis
    -0.13
     given
    -0.13
    POSITIVE LOGITS
    elize
    0.15
    serter
    0.15
    IALOG
    0.15
    ãģ¿
    0.15
    çĶŁ
    0.14
    134
    0.14
     Affairs
    0.14
     Kral
    0.14
     ########################################################################
    0.14
    allon
    0.14
    Act Density 0.003%

    No Known Activations