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

    Neuronpedia

    INDEX
    Explanations

    references to specific high-performance car brands and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rist
    -0.16
    station
    -0.15
    üs
    -0.14
    mour
    -0.13
    enal
    -0.13
    ục
    -0.13
    æ¤
    -0.13
    agram
    -0.13
    gis
    -0.13
    æ¥ļ
    -0.13
    POSITIVE LOGITS
     McLaren
    0.31
     MP
    0.21
     McL
    0.21
     Formula
    0.20
     carbon
    0.19
    Carbon
    0.18
     GT
    0.18
     Carbon
    0.18
     TAG
    0.17
    COOKIE
    0.17
    Act Density 0.004%

    No Known Activations