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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuity or persistence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to persistence or ongoing existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buster
    -0.62
    strip
    -0.58
     pounded
    -0.56
     |--
    -0.55
    achi
    -0.55
    hower
    -0.54
    icles
    -0.54
     chast
    -0.54
     closely
    -0.54
     princip
    -0.53
    POSITIVE LOGITS
     plenty
    1.00
     ample
    0.83
     lots
    0.80
    omething
    0.77
     unanim
    0.75
    umption
    0.74
     alot
    0.70
     precedent
    0.70
    enough
    0.70
     enough
    0.69
    Act Density 0.104%

    No Known Activations