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

    Neuronpedia

    INDEX
    Explanations

    personal narratives and emotional expressions

    oai_token-act-pair · gpt-3.5-turbo

    instances of expressions related to social interactions and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.55
    ],"
    -0.48
    atlantic
    -0.43
    "))
    -0.43
    "[
    -0.41
    ".[
    -0.40
    Following
    -0.40
    ]).
    -0.40
    ]),
    -0.40
    anch
    -0.40
    POSITIVE LOGITS
     however
    0.57
     though
    0.53
     meanwhile
    0.52
     tho
    0.46
    eday
    0.44
     Kappa
    0.44
     glim
    0.42
    !)
    0.41
     depends
    0.41
     sag
    0.41
    Act Density 4.812%

    No Known Activations