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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the phrase "back-to-back" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venes
    -0.17
    quals
    -0.15
    .sg
    -0.14
    andest
    -0.14
    yssey
    -0.14
    âĸį
    -0.14
    ipar
    -0.14
    Td
    -0.13
    798
    -0.13
     sene
    -0.13
    POSITIVE LOGITS
    -to
    0.29
     consecutive
    0.26
     successive
    0.26
    -t
    0.22
    -To
    0.19
     luck
    0.19
    -back
    0.18
    strom
    0.17
    con
    0.17
    -con
    0.16
    Act Density 0.004%

    No Known Activations