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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and colons

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ÏĦικα
    -0.09
     tiener
    -0.09
    омен
    -0.09
    òi
    -0.09
    imdi
    -0.08
    .scalablytyped
    -0.08
     nack
    -0.08
     klu
    -0.08
    ÅĻád
    -0.08
    áo
    -0.08
    POSITIVE LOGITS
     de
    0.10
     or
    0.09
     j
    0.08
    <|end_of_text|>
    0.08
     re
    0.08
     ‘
    0.08
    âĢ¦↵
    0.08
     st
    0.08
    Âł
    0.08
     just
    0.08
    Act Density 0.165%

    No Known Activations