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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structures indicative of dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñīин
    -0.15
    okt
    -0.15
     –↵↵
    -0.15
    éģķãģĦ
    -0.14
     Together
    -0.13
     Äijạo
    -0.13
    پس
    -0.13
    Besides
    -0.13
    .TODO
    -0.13
    incipal
    -0.13
    POSITIVE LOGITS
     Number
    0.15
    htdocs
    0.15
    again
    0.15
    ÙĤب
    0.15
     And
    0.15
    achuset
    0.15
    Number
    0.14
     again
    0.14
     lại
    0.14
    azio
    0.14
    Act Density 0.155%

    No Known Activations