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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to transcripts or difficult-to-read communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oram
    -0.17
    eden
    -0.17
    brook
    -0.16
    libft
    -0.16
    iska
    -0.15
    ICC
    -0.14
    pson
    -0.14
     mktime
    -0.14
    ãĤ¿ãĥ¼
    -0.14
     Watkins
    -0.14
    POSITIVE LOGITS
     leg
    0.31
     understandable
    0.28
     readable
    0.28
     unint
    0.28
     readability
    0.26
     intellig
    0.24
     unread
    0.24
     meaning
    0.24
     unclear
    0.23
     incom
    0.23
    Act Density 0.200%

    No Known Activations