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

    Neuronpedia

    INDEX
    Explanations

    months and dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific months or times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ym
    -0.67
     sy
    -0.65
    idine
    -0.64
     totality
    -0.61
     sync
    -0.61
     gib
    -0.60
     predec
    -0.59
     nep
    -0.59
     textual
    -0.58
     Seym
    -0.58
    POSITIVE LOGITS
    obyl
    0.73
    ghan
    0.73
     GOODMAN
    0.69
     Dill
    0.67
    WOOD
    0.65
     Keane
    0.64
    eteenth
    0.63
    OULD
    0.63
     when
    0.62
    furt
    0.62
    Act Density 0.085%

    No Known Activations