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

    Neuronpedia

    INDEX
    Explanations

    foreign characters related to specific languages

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     rake
    -0.74
    Downloadha
    -0.66
    ilater
    -0.65
     disenfranch
    -0.63
     Derby
    -0.62
     Sussex
    -0.62
     chau
    -0.62
     DRAG
    -0.61
    bda
    -0.61
     birthplace
    -0.61
    POSITIVE LOGITS
    ħ
    1.17
    Į
    1.05
    к
    1.04
    ÑĤ
    0.96
    İ
    0.94
    Ð
    0.93
    obar
    0.92
    Û
    0.91
    ĭ
    0.89
    à¨
    0.89
    Act Density 0.009%

    No Known Activations