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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'then'

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "then" in various contexts, typically related to people or events associated with specific points in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toe
    -0.79
    chy
    -0.76
    ters
    -0.70
    icles
    -0.69
     stalls
    -0.69
    halla
    -0.68
    bage
    -0.67
    mson
    -0.67
    orum
    -0.66
    asso
    -0.65
    POSITIVE LOGITS
     unpublished
    0.69
    ħĭ
    0.68
    ãĥĥãĥī
    0.68
     Yugoslav
    0.65
     prime
    0.65
     remembered
    0.64
    oslov
    0.64
     Clim
    0.63
    -'
    0.63
     Yugoslavia
    0.62
    Act Density 0.043%

    No Known Activations