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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to spirals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    echa
    -0.16
    shima
    -0.15
    ajor
    -0.15
    emez
    -0.15
    رÙĩ
    -0.14
    ignant
    -0.14
    ickness
    -0.14
    né
    -0.14
    缼
    -0.14
    enda
    -0.14
    POSITIVE LOGITS
    aling
    0.20
    alling
    0.19
    als
    0.19
    idon
    0.17
    ited
    0.17
    aea
    0.17
    ero
    0.16
    aled
    0.15
     chute
    0.15
    itu
    0.15
    Act Density 0.009%

    No Known Activations