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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time or temporal actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.65
     Tayyip
    -0.63
    manship
    -0.61
    bis
    -0.60
    greg
    -0.60
    git
    -0.60
    itative
    -0.60
    ional
    -0.60
    folios
    -0.59
    phabet
    -0.59
    POSITIVE LOGITS
     outset
    1.38
     behest
    1.30
     expense
    1.29
     seams
    1.10
     end
    1.07
     mercy
    1.04
     discretion
    1.04
     beginning
    1.02
     altar
    1.00
     moment
    1.00
    Act Density 0.116%

    No Known Activations