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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bec
    -0.15
    WB
    -0.15
     ÄIJó
    -0.15
    ãĥ¼ãĥģ
    -0.15
    .Toolkit
    -0.14
    ourd
    -0.14
     pornô
    -0.14
    ÃŃt
    -0.14
    udev
    -0.14
    áv
    -0.14
    POSITIVE LOGITS
     La
    0.31
     Il
    0.29
     Ã
    0.25
    La
    0.24
     Le
    0.24
     Come
    0.23
     Second
    0.22
    Il
    0.22
     Si
    0.21
     Lo
    0.21
    Act Density 0.006%

    No Known Activations