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

    Neuronpedia

    INDEX
    Explanations

    names of places or cities

    oai_token-act-pair · gpt-3.5-turbo

    the symbol "âĢĶ" and similar patterns, suggesting a focus on specific encoding or formatting characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.73
     assum
    -0.72
     redes
    -0.72
     appro
    -0.71
     rele
    -0.68
    course
    -0.68
     recip
    -0.68
    raq
    -0.67
     offending
    -0.67
     tack
    -0.64
    POSITIVE LOGITS
     Authorities
    1.00
     Thousands
    1.00
     Dozens
    0.92
     Hundreds
    0.90
     Latest
    0.90
     Prosecutors
    0.87
     Protesters
    0.87
     Former
    0.86
     Officials
    0.86
     Despite
    0.86
    Act Density 0.033%

    No Known Activations