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

    Neuronpedia

    INDEX
    Explanations

    electric signals or computer code

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that appear frequently, indicating possible formatting or coding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mate
    -0.67
     Voyager
    -0.67
     dispers
    -0.66
     Belg
    -0.66
     polyg
    -0.65
     interf
    -0.63
     Jem
    -0.62
     handshake
    -0.60
     concentrate
    -0.59
     technique
    -0.59
    POSITIVE LOGITS
    ª
    1.44
    ¡
    1.29
    ¹
    1.26
    Ļ
    1.23
    Į
    1.22
    Ŀ
    1.21
    ¤
    1.21
    ı
    1.20
    Ń
    1.18
    ¬
    1.18
    Act Density 0.109%

    No Known Activations