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

    Neuronpedia

    INDEX
    Explanations

    email-related terms

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms followed by numbers or letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.77
     Rebels
    -0.73
     Clown
    -0.73
     Primal
    -0.68
     Prest
    -0.67
     Glas
    -0.66
     Nirvana
    -0.66
     Wast
    -0.66
     Prism
    -0.65
     Heritage
    -0.64
    POSITIVE LOGITS
    ailing
    1.18
    cknowled
    1.16
    illed
    1.15
    ipping
    1.13
    ailed
    1.12
    apping
    1.09
    itting
    1.08
    asting
    1.06
    itted
    1.06
    rought
    1.05
    Act Density 0.129%

    No Known Activations