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

    Neuronpedia

    INDEX
    Explanations

    word repetitions marked by a special symbol

    oai_token-act-pair · gpt-3.5-turbo

    instances of financial and legal terms related to governance and infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adolesc
    -0.85
     incarn
    -0.78
     adventures
    -0.77
     endeav
    -0.76
     attent
    -0.74
     endeavour
    -0.74
     enjoyment
    -0.70
    ysc
    -0.70
     outings
    -0.70
     util
    -0.70
    POSITIVE LOGITS
    WASHINGTON
    1.07
    Washington
    1.06
    Instead
    1.02
    MORE
    1.01
    Advertisement
    1.00
    Asked
    0.98
    Meanwhile
    0.98
    Iowa
    0.98
    But
    0.95
    SEE
    0.95
    Act Density 0.615%

    No Known Activations