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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -0.61
    parsedMessage
    -0.55
    ientras
    -0.55
     propOrder
    -0.53
    CPtr
    -0.50
     NSCoder
    -0.50
    Portale
    -0.48
    mybatisplus
    -0.47
     IMEI
    -0.47
    كويكب
    -0.46
    POSITIVE LOGITS
     OMITBAD
    0.43
     or
    0.42
    natural
    0.39
    ngiliz
    0.37
    úgó
    0.36
     lumea
    0.35
     finito
    0.35
     orilla
    0.35
    cero
    0.34
    shapes
    0.34
    Act Density 0.052%

    No Known Activations