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

    Neuronpedia

    INDEX
    Explanations

    terms related to spiral shapes or patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oose
    -0.18
    emez
    -0.15
    ajor
    -0.15
    ãĥ³ãĥĨãĤ£
    -0.15
    缼
    -0.15
    ustry
    -0.14
    opher
    -0.14
    844
    -0.14
    CLUDE
    -0.14
    shima
    -0.14
    POSITIVE LOGITS
    aling
    0.17
    aea
    0.17
     chute
    0.16
     spir
    0.16
    alling
    0.16
    als
    0.15
    ero
    0.15
    wind
    0.15
    pery
    0.14
    aled
    0.14
    Act Density 0.010%

    No Known Activations