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

    Neuronpedia

    INDEX
    Explanations

    patterns representing borders or separators

    oai_token-act-pair · gpt-3.5-turbo

    sequence patterns or structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ponies
    -0.53
     rhy
    -0.53
     snipp
    -0.52
    "—
    -0.52
    stellar
    -0.52
    owship
    -0.51
     interchangeable
    -0.51
    cember
    -0.51
    bett
    -0.50
    âĢ¦
    -0.50
    POSITIVE LOGITS
     |
    3.49
    |
    2.00
     ||
    1.76
    )|
    1.62
     |--
    1.59
     >>
    1.50
     âĶĤ
    1.48
     »
    1.45
     }}
    1.44
     ·
    1.42
    Act Density 0.021%

    No Known Activations