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

    Neuronpedia

    INDEX
    Explanations

    descriptions of automotive design features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gib
    -0.16
    Ñĸб
    -0.16
    enburg
    -0.15
    å¼¹
    -0.15
    chalk
    -0.14
    ench
    -0.14
    reib
    -0.14
    pink
    -0.14
     mekan
    -0.14
    chant
    -0.13
    POSITIVE LOGITS
     grille
    0.25
     spoiler
    0.23
     grill
    0.21
     aer
    0.20
     Grill
    0.19
     hood
    0.18
     aggressive
    0.18
     LEDs
    0.17
     spoilers
    0.17
     fasc
    0.17
    Act Density 0.046%

    No Known Activations