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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dete
    -0.17
    ÂĿ
    -0.14
     ↵↵
    -0.14
    âce
    -0.14
    ноÑĪ
    -0.14
    PÅĻÃŃ
    -0.14
    chedulers
    -0.13
    ""
    -0.13
    ataires
    -0.13
    ↵↵
    -0.13
    POSITIVE LOGITS
    00
    0.52
    000
    0.45
    0
    0.44
    02
    0.44
    05
    0.43
    01
    0.43
    03
    0.42
    06
    0.41
    04
    0.41
    08
    0.40
    Act Density 0.483%

    No Known Activations