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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mar
    -0.19
    mur
    -0.16
    kowski
    -0.15
    ra
    -0.15
    434
    -0.14
    mys
    -0.14
    her
    -0.14
    ry
    -0.14
    ric
    -0.14
    illage
    -0.14
    POSITIVE LOGITS
    áty
    0.18
    utar
    0.15
     Picker
    0.15
    eyen
    0.15
    iddi
    0.14
    ãĥ³ãĤ¬
    0.14
    oola
    0.14
    ookies
    0.14
    uvw
    0.14
    wich
    0.14
    Act Density 0.003%

    No Known Activations