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

    Neuronpedia

    INDEX
    Explanations

    German words

    oai_token-act-pair · gpt-3.5-turbo

    words related to numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xxxxxxxx
    -0.72
     Skydragon
    -0.71
    ãĥĻ
    -0.68
    yip
    -0.64
    Redd
    -0.64
     convol
    -0.63
    caps
    -0.63
    ortment
    -0.62
    artifacts
    -0.61
    VW
    -0.61
    POSITIVE LOGITS
     Ãĸ
    0.80
    én
    0.79
    ü
    0.78
    ä
    0.77
    ön
    0.75
    inen
    0.73
    ç
    0.73
    ö
    0.72
     ni
    0.70
     Ã
    0.69
    Act Density 0.102%

    No Known Activations