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

    Neuronpedia

    INDEX
    Explanations

    information related to technology products or tech news

    oai_token-act-pair · gpt-3.5-turbo

    expressions of indecision or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.81
    20439
    -0.75
    merce
    -0.68
     [+
    -0.65
     ILCS
    -0.65
    oplan
    -0.62
    osate
    -0.60
     )]
    -0.59
    Rated
    -0.59
    icrobial
    -0.58
    POSITIVE LOGITS
     kidding
    1.13
    ?!
    0.87
    ????
    0.85
     awfully
    0.80
    *.
    0.79
    !?
    0.78
    ????????
    0.77
     typo
    0.76
    ???
    0.76
     naughty
    0.74
    Act Density 0.677%

    No Known Activations