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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate statistical references or generalizations about populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inine
    -0.18
    ero
    -0.16
    اکÛĮ
    -0.16
    umen
    -0.15
    yle
    -0.14
    elines
    -0.14
    hen
    -0.14
    pes
    -0.14
    Ïĥαν
    -0.14
    ORS
    -0.14
    POSITIVE LOGITS
     note
    0.33
    note
    0.27
     Note
    0.23
     course
    0.23
    Note
    0.20
     NOTE
    0.19
    osu
    0.19
     notice
    0.19
     those
    0.19
    sted
    0.19
    Act Density 0.016%

    No Known Activations