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

    Neuronpedia

    INDEX
    Explanations

    specific forms or documents mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to forms or paperwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     railing
    -0.70
    >>\
    -0.65
     bark
    -0.63
     spree
    -0.62
    mins
    -0.61
    EStreamFrame
    -0.61
    wcs
    -0.60
    £ı
    -0.59
     Hots
    -0.59
     Seas
    -0.59
    POSITIVE LOGITS
    aldehyde
    1.40
    idable
    1.30
    atted
    1.27
    atter
    1.22
    ulas
    1.12
    ula
    1.11
    ulations
    1.01
    ulating
    0.99
    ulators
    0.96
    ats
    0.94
    Act Density 0.032%

    No Known Activations