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

    Neuronpedia

    INDEX
    Explanations

    sudden or unexpected events or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of abrupt changes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orers
    -0.71
    adata
    -0.70
    ictionary
    -0.67
    ropolitan
    -0.66
    apixel
    -0.64
     SEO
    -0.64
    igans
    -0.63
    rooms
    -0.63
    emark
    -0.62
    erb
    -0.62
    POSITIVE LOGITS
     abruptly
    1.17
     halted
    0.96
     discontin
    0.94
     abrupt
    0.83
     cessation
    0.82
    kson
    0.80
     halt
    0.78
     pauses
    0.77
     departures
    0.77
    tle
    0.74
    Act Density 0.014%

    No Known Activations