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

    Neuronpedia

    INDEX
    Explanations

    references to different types of cars

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.84
     Dull
    -0.75
    tle
    -0.74
    edIn
    -0.73
    rontal
    -0.71
    emonic
    -0.67
    ãĥĥãĥĪ
    -0.66
     Birch
    -0.66
    iciary
    -0.65
    ylum
    -0.65
    POSITIVE LOGITS
    ousel
    1.31
    riages
    1.24
    penter
    1.02
     cars
    0.98
    rera
    0.96
     dealership
    0.95
     parked
    0.93
    obiles
    0.88
    cars
    0.86
    wagen
    0.83
    Act Density 0.039%

    No Known Activations