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

    Neuronpedia

    INDEX
    Explanations

    appreciation or acknowledgment phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing gratitude or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tweet
    -0.60
     âĸº
    -0.58
    ype
    -0.57
    OND
    -0.57
    tein
    -0.57
    abase
    -0.55
    onne
    -0.55
    notation
    -0.55
    naires
    -0.51
    rial
    -0.51
    POSITIVE LOGITS
     subscribing
    0.66
     Amen
    0.61
    ]=
    0.59
    issance
    0.55
    é¾į
    0.55
     CFR
    0.53
    æ©
    0.53
    Reilly
    0.53
    ]);
    0.52
     Tanz
    0.52
    Act Density 0.015%

    No Known Activations