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

    Neuronpedia

    INDEX
    Explanations

    the possessive form of words, specifically '"s' indicating ownership or association

    oai_token-act-pair · gpt-3.5-turbo

    the word "is"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prior
    -0.68
     Brune
    -0.62
     precinct
    -0.61
     Murd
    -0.60
     Spani
    -0.59
     Britons
    -0.57
     Remain
    -0.56
     Moff
    -0.55
    apixel
    -0.53
     Reef
    -0.53
    POSITIVE LOGITS
    ELF
    0.83
    pecially
    0.75
    por
    0.75
    ustainable
    0.73
    entin
    0.71
    etsk
    0.71
    orno
    0.71
     abundantly
    0.71
    selves
    0.69
    eros
    0.69
    Act Density 0.138%

    No Known Activations