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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recent events or time periods

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "recent" along with references to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vantage
    -0.77
    hyde
    -0.74
    alach
    -0.72
    paio
    -0.71
    cius
    -0.69
    claimer
    -0.66
    ynchron
    -0.65
    pose
    -0.65
    ohm
    -0.60
    ucker
    -0.60
    POSITIVE LOGITS
     weeks
    1.13
     months
    1.06
     generations
    1.06
     days
    1.03
     years
    1.03
     evenings
    0.98
     editions
    0.98
     afternoon
    0.91
     times
    0.91
     occasions
    0.90
    Act Density 0.023%

    No Known Activations