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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate perception or classification of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.81
     itſelf
    -0.81
     uſed
    -0.78
    knecht
    -0.76
    出版年
    -0.75
    SPATH
    -0.75
     saveiro
    -0.74
     purpoſe
    -0.73
     Majefty
    -0.71
     Efq
    -0.71
    POSITIVE LOGITS
     “
    0.84
     a
    0.79
     ‘
    0.71
    writerow
    0.68
     "
    0.68
     being
    0.66
    是一種
    0.63
     be
    0.62
     «
    0.61
     part
    0.61
    Act Density 0.373%

    No Known Activations