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

    Neuronpedia

    INDEX
    Explanations

    times or events indicated by phrases like "by then" or "by the time"

    oai_token-act-pair · gpt-3.5-turbo

    references to developmental stages or points in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bol
    -0.70
     externalToEVAOnly
    -0.62
    nesday
    -0.62
     honour
    -0.62
     ransom
    -0.61
     prov
    -0.60
     purposes
    -0.60
     Bought
    -0.60
     investigates
    -0.59
     suggestion
    -0.58
    POSITIVE LOGITS
     exhausted
    0.84
     already
    0.84
    Already
    0.73
    ©¶æ¥µ
    0.70
     outnumbered
    0.70
    apsed
    0.70
     Already
    0.68
    ÃįÃį
    0.68
    >>>>>>>>
    0.67
     surpassed
    0.65
    Act Density 0.365%

    No Known Activations