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

    Neuronpedia

    INDEX
    Explanations

    phrases related to long periods of time

    oai_token-act-pair · gpt-3.5-turbo

    mentions of extended time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egu
    -0.71
    amina
    -0.68
    isy
    -0.68
    cheat
    -0.68
    iqu
    -0.67
    Plug
    -0.66
    rium
    -0.65
    hao
    -0.64
    hod
    -0.63
    asty
    -0.61
    POSITIVE LOGITS
     ago
    1.12
     Ago
    0.90
     sake
    0.80
     thereafter
    0.76
     consecut
    0.75
     olds
    0.70
    olson
    0.68
     apiece
    0.68
     spanning
    0.68
     ILCS
    0.67
    Act Density 0.073%

    No Known Activations