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

    Neuronpedia

    INDEX
    Explanations

    actions related to processing and delivering mail services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unn
    -0.17
    nor
    -0.16
     particularly
    -0.16
     ÙħÙĨØ°
    -0.15
     despite
    -0.15
    аÑĢÑĮ
    -0.14
     beyond
    -0.14
     since
    -0.14
    ç«Ł
    -0.14
    early
    -0.14
    POSITIVE LOGITS
     accordingly
    0.26
     usually
    0.24
     either
    0.23
     then
    0.20
    either
    0.19
     ready
    0.19
     THEN
    0.18
    usually
    0.18
     Either
    0.18
     exactly
    0.18
    Act Density 0.305%

    No Known Activations