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

    Neuronpedia

    INDEX
    Explanations

    phrases related to vehicles

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicles and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flan
    -0.66
     butterfly
    -0.64
     frog
    -0.64
    iral
    -0.64
     1889
    -0.63
    ishing
    -0.61
     slug
    -0.60
    itton
    -0.60
     discriminating
    -0.60
     bats
    -0.59
    POSITIVE LOGITS
    veh
    3.32
    dash
    2.21
    prise
    1.64
    Veh
    1.56
     pas
    1.55
    prises
    1.16
    uds
    1.11
    pas
    1.02
    oven
    0.93
    kai
    0.92
    Act Density 0.055%

    No Known Activations