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

    Neuronpedia

    INDEX
    Explanations

    time-related cues or transitions indicating a change or shift in events

    oai_token-act-pair · gpt-3.5-turbo

    the recurring phrase "Until" indicating a condition or limitation over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    administ
    -0.67
    hazard
    -0.66
    Adds
    -0.65
    pour
    -0.64
     prov
    -0.62
    pez
    -0.61
    åĤ
    -0.61
    âĵĺ
    -0.61
    mob
    -0.61
    exp
    -0.61
    POSITIVE LOGITS
    unda
    0.67
     Ago
    0.67
    ilage
    0.66
    ndra
    0.64
    cks
    0.64
    ments
    0.64
    inka
    0.62
    cot
    0.62
    atonin
    0.61
     Adidas
    0.61
    Act Density 0.022%

    No Known Activations