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

    Neuronpedia

    INDEX
    Explanations

    references to architectural projects and related details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kw
    -0.18
    icut
    -0.17
    kh
    -0.16
     kr
    -0.16
    elper
    -0.15
    orting
    -0.15
    loth
    -0.14
    turnstile
    -0.14
     kw
    -0.14
    faction
    -0.14
    POSITIVE LOGITS
     Finland
    0.49
     Finnish
    0.47
     Helsinki
    0.44
    .fi
    0.39
     Finn
    0.35
    elsinki
    0.32
     Mets
    0.31
     Nokia
    0.31
     FIN
    0.31
    Fin
    0.31
    Act Density 0.095%

    No Known Activations