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

    Neuronpedia

    INDEX
    Explanations

    statements expressing opposition or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but" indicating contrasts or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iosyncr
    -0.75
    èĢħ
    -0.70
    Synopsis
    -0.67
    incial
    -0.67
    ItemTracker
    -0.64
    result
    -0.63
    escription
    -0.63
    oufl
    -0.62
    built
    -0.62
    defined
    -0.62
    POSITIVE LOGITS
     hey
    1.46
     yeah
    1.41
     alas
    1.29
     yea
    1.18
     damn
    1.17
     honestly
    1.16
     anyways
    1.12
     suffice
    1.11
     luckily
    1.10
     congr
    1.10
    Act Density 0.165%

    No Known Activations