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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of time

    oai_token-act-pair · gpt-3.5-turbo

    references to "times" indicating changes, current events, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceous
    -0.83
    Ô
    -0.77
     Flavoring
    -0.74
    RD
    -0.70
     UCH
    -0.70
    andan
    -0.69
    ged
    -0.68
    GY
    -0.67
    =]
    -0.66
    ITAL
    -0.64
    POSITIVE LOGITS
    cale
    1.53
    hare
    1.11
    cape
    1.07
    hower
    0.98
    pring
    0.96
    eries
    0.94
    pan
    0.94
    lot
    0.88
    heet
    0.88
    bos
    0.88
    Act Density 0.028%

    No Known Activations