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

    Neuronpedia

    INDEX
    Explanations

    recent time references

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time, specifically years ago

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eq
    -0.77
    notations
    -0.64
    ums
    -0.63
    rouse
    -0.62
    lua
    -0.62
    aspx
    -0.61
    atile
    -0.61
    eps
    -0.59
    CG
    -0.59
    Applic
    -0.58
    POSITIVE LOGITS
     when
    0.76
     WHEN
    0.69
    opausal
    0.68
     Olivier
    0.67
    upon
    0.66
     ago
    0.66
    inery
    0.62
    adays
    0.62
    UFC
    0.61
     I
    0.61
    Act Density 0.032%

    No Known Activations