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

    Neuronpedia

    INDEX
    Explanations

    automotive maintenance and parts-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     batter
    -0.17
    rawer
    -0.16
    aleur
    -0.15
    788
    -0.15
    ileo
    -0.15
    978
    -0.15
    volt
    -0.15
    麻
    -0.14
    opsy
    -0.14
    rients
    -0.14
    POSITIVE LOGITS
     brakes
    0.37
     brake
    0.35
     braking
    0.30
     Brake
    0.30
     stopping
    0.29
     Br
    0.24
     stop
    0.24
    stop
    0.23
    Br
    0.22
    Stop
    0.22
    Act Density 0.049%

    No Known Activations