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

    Neuronpedia

    INDEX
    Explanations

    short, concise statements or summaries

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate brief summaries or tips

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammed
    -0.77
    existent
    -0.71
    eworld
    -0.70
    oise
    -0.69
    ceans
    -0.69
    utm
    -0.69
    "},"
    -0.68
    hire
    -0.68
    ardless
    -0.68
    aden
    -0.67
    POSITIVE LOGITS
     disclaimer
    1.31
     note
    1.29
     caveat
    1.28
     caveats
    1.24
     recap
    1.18
     refres
    1.15
     reminder
    1.11
     clarification
    1.05
     Note
    1.03
     parting
    0.98
    Act Density 0.208%

    No Known Activations