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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is speaking or quoting something

    oai_token-act-pair · gpt-3.5-turbo

    references to negative speech or statements made about others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Flickr
    -0.79
     Flickr
    -0.70
    edia
    -0.62
     Wikimedia
    -0.62
    ablished
    -0.62
     Mechanical
    -0.61
    lisher
    -0.61
     Flavoring
    -0.60
    ibal
    -0.59
    anding
    -0.59
    POSITIVE LOGITS
     aloud
    1.65
     loudly
    1.31
     goodbye
    1.23
     loud
    1.19
     louder
    1.04
     words
    0.96
     phrases
    0.93
     word
    0.92
     prayers
    0.92
    word
    0.92
    Act Density 0.197%

    No Known Activations