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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by proper nouns or specific locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.85
    jud
    -0.71
    ealous
    -0.69
    matical
    -0.65
    asing
    -0.64
    Downloadha
    -0.63
    hran
    -0.62
    venants
    -0.62
    Publisher
    -0.61
    osph
    -0.61
    POSITIVE LOGITS
     choice
    0.94
     excellence
    0.76
     tomorrow
    0.72
     mankind
    0.69
     whichever
    0.69
     salvation
    0.68
     Scandinav
    0.68
     humankind
    0.67
     sorts
    0.67
     heaven
    0.66
    Act Density 0.166%

    No Known Activations