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

    Neuronpedia

    INDEX
    Explanations

    dates or times mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "for" indicating scheduling or planned events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mone
    -0.74
    ware
    -0.65
    dn
    -0.64
     beg
    -0.64
    brand
    -0.63
    arest
    -0.63
     founded
    -0.63
    MJ
    -0.62
    Shop
    -0.62
     ported
    -0.62
    POSITIVE LOGITS
    gery
    0.98
    geries
    0.91
     inclusion
    0.91
     sometime
    0.87
     eternity
    0.86
     ages
    0.83
     tomorrow
    0.82
    bidden
    0.79
     indefinite
    0.77
     awhile
    0.76
    Act Density 0.086%

    No Known Activations