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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ographically
    -0.69
    igans
    -0.69
    fy
    -0.68
    coins
    -0.66
    ographers
    -0.66
    alties
    -0.66
    eers
    -0.66
    aylor
    -0.64
    quit
    -0.63
    azz
    -0.63
    POSITIVE LOGITS
     entirety
    1.09
     holidays
    1.02
     latter
    1.02
     midst
    0.95
     period
    0.91
     same
    0.91
     darkest
    0.90
     course
    0.90
     remainder
    0.89
     weekend
    0.88
    Act Density 0.106%

    No Known Activations