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

    Neuronpedia

    INDEX
    Explanations

    formatting elements and punctuation, particularly in relation to structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    occo
    -0.17
    ijo
    -0.16
     Dou
    -0.16
    aison
    -0.15
    anson
    -0.15
    retty
    -0.15
    ocked
    -0.15
    parsers
    -0.15
     Doub
    -0.15
    astle
    -0.15
    POSITIVE LOGITS
    64
    0.45
    064
    0.41
     memory
    0.40
    604
    0.35
     Memory
    0.35
    104
    0.35
    Memory
    0.32
     APR
    0.31
    964
    0.31
     apr
    0.31
    Act Density 0.040%

    No Known Activations