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

    Neuronpedia

    INDEX
    Explanations

    web URLs

    oai_token-act-pair · gpt-3.5-turbo

    sequences of characters, particularly involving formatting and structural elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aea
    -0.82
     Haunted
    -0.80
     Melania
    -0.77
    enegger
    -0.76
     INF
    -0.76
     Machines
    -0.74
    inery
    -0.74
    ela
    -0.73
    olin
    -0.73
    EStream
    -0.73
    POSITIVE LOGITS
    Q
    1.03
     point
    1.02
     Point
    0.98
     q
    0.90
     hint
    0.90
     nod
    0.89
    q
    0.89
     Q
    0.87
     reference
    0.85
    Point
    0.84
    Act Density 0.310%

    No Known Activations