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

    Neuronpedia

    INDEX
    Explanations

    the word "and" in various contexts indicating connections or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anyl
    -0.17
    anford
    -0.17
    ãĥ«ãĥķ
    -0.17
    agram
    -0.15
    orr
    -0.15
    ilen
    -0.15
    afx
    -0.14
    ahn
    -0.14
    .WriteAll
    -0.14
    Fmt
    -0.13
    POSITIVE LOGITS
     etc
    0.18
     finally
    0.17
    alla
    0.17
     above
    0.17
    rama
    0.15
     Lastly
    0.15
     Mata
    0.15
     Halk
    0.15
    erer
    0.15
     clocks
    0.14
    Act Density 0.118%

    No Known Activations