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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or characters associated with media content, particularly focusing on the word "itter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cephal
    -0.70
     Kingdoms
    -0.67
    urat
    -0.62
     routed
    -0.62
     arteries
    -0.60
    ilitation
    -0.58
    lez
    -0.58
     translate
    -0.57
     looting
    -0.57
    Ward
    -0.56
    POSITIVE LOGITS
    geist
    1.10
    bug
    0.99
    sburg
    0.95
    cair
    0.87
    mite
    0.83
    iver
    0.79
    bugs
    0.79
    eer
    0.78
    tainment
    0.77
    idge
    0.77
    Act Density 0.028%

    No Known Activations