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

    Neuronpedia

    INDEX
    Explanations

    references to "sides" and related descriptors, indicating a focus on dualities or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hendes
    -0.46
     quidem
    -0.45
     Reisedaten
    -0.44
     Szcz
    -0.44
     acoper
    -0.43
     Reſ
    -0.42
     extensión
    -0.42
     estrange
    -0.42
    DataSetChanged
    -0.41
     gekomen
    -0.41
    POSITIVE LOGITS
     side
    0.69
     until
    0.69
     till
    0.68
     Side
    0.67
    til
    0.67
     Til
    0.65
     sides
    0.65
    until
    0.65
     Till
    0.64
    Til
    0.64
    Act Density 1.645%

    No Known Activations