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

    Neuronpedia

    INDEX
    Explanations

    mentions of historical events or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rosso
    -0.17
    imbus
    -0.15
     Craw
    -0.15
    ski
    -0.15
     pros
    -0.14
    altar
    -0.14
     vending
    -0.14
    kiem
    -0.14
    illez
    -0.14
     craw
    -0.14
    POSITIVE LOGITS
     horses
    0.61
     horse
    0.59
    horse
    0.49
     Horse
    0.47
     saddle
    0.38
     riders
    0.34
     rider
    0.34
     horsepower
    0.32
     ox
    0.30
     riding
    0.30
    Act Density 0.185%

    No Known Activations