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

    Neuronpedia

    INDEX
    Explanations

    capital cities of countries

    oai_token-act-pair · gpt-3.5-turbo

    names of major cities and countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.58
    eatures
    -0.51
    IBLE
    -0.48
    forward
    -0.47
    compl
    -0.46
     experien
    -0.46
     Pixie
    -0.45
    endum
    -0.45
     Warranty
    -0.45
    ãĤ¨ãĥ«
    -0.45
    POSITIVE LOGITS
     etc
    0.58
     respectively
    0.56
    ;
    0.47
     ..........
    0.47
    .>>
    0.47
    ,[
    0.46
    ),
    0.46
    BSD
    0.44
    /
    0.44
    *.
    0.44
    Act Density 0.892%

    No Known Activations