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

    Neuronpedia

    INDEX
    Explanations

    references to rhinos

    oai_token-act-pair · gpt-3.5-turbo

    references to rhinoceroses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARE
    -0.75
    HUD
    -0.74
    flies
    -0.70
     Shift
    -0.70
    hare
    -0.69
    ãĥ¼ãĥĨ
    -0.69
     Telegram
    -0.69
     Whale
    -0.67
    boat
    -0.67
    Fra
    -0.66
    POSITIVE LOGITS
    actic
    0.85
    iggs
    0.81
    itability
    0.80
    inary
    0.79
     rh
    0.78
    iles
    0.76
    atl
    0.76
    ile
    0.76
    inn
    0.76
    outed
    0.76
    Act Density 0.038%

    No Known Activations