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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to mechanical specifications or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zcze
    -0.16
     fus
    -0.16
     vehicle
    -0.15
     Herrera
    -0.15
    ÙĦÙĬÙģ
    -0.15
    lus
    -0.15
    èķ
    -0.14
    emodel
    -0.14
     Vehicle
    -0.14
     Boeh
    -0.14
    POSITIVE LOGITS
     drift
    0.26
     drifting
    0.24
     lap
    0.23
     rally
    0.22
     Lap
    0.21
     Dak
    0.21
     drifted
    0.20
     rallying
    0.20
     hill
    0.20
     Rally
    0.20
    Act Density 0.016%

    No Known Activations