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

    Neuronpedia

    INDEX
    Explanations

    phrases that contrast or emphasize a difference

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating cause and effect relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Heath
    -0.64
    Python
    -0.63
    ory
    -0.61
     Scene
    -0.57
    oft
    -0.56
    ct
    -0.55
     Orlando
    -0.54
     ¶
    -0.54
     Babel
    -0.52
     Mex
    -0.52
    POSITIVE LOGITS
    etheless
    1.17
     nonetheless
    1.05
     nevertheless
    0.82
    interstitial
    0.70
     downright
    0.68
     darn
    0.68
     incre
    0.67
     conclud
    0.66
    ankind
    0.66
     damn
    0.64
    Act Density 0.159%

    No Known Activations