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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to causation and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yš
    -0.17
    ĶĦ
    -0.17
    ibold
    -0.16
    олоÑģ
    -0.15
     Söz
    -0.15
    cord
    -0.15
    ÑĢава
    -0.15
     Lone
    -0.15
    ÙĥÙĬ
    -0.14
    ONTAL
    -0.14
    POSITIVE LOGITS
     Revolution
    0.15
    ctl
    0.15
     Dul
    0.14
    벨
    0.14
     FLAGS
    0.14
     Ton
    0.14
     Mobil
    0.14
    AGO
    0.14
    ZE
    0.14
     Ze
    0.14
    Act Density 0.018%

    No Known Activations