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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating detailed information or analysis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "detailed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enos
    -0.88
    aden
    -0.78
    eno
    -0.78
    corn
    -0.74
     Nicaragua
    -0.73
    ADS
    -0.72
    oi
    -0.72
    avis
    -0.70
    qqa
    -0.69
    ques
    -0.68
    POSITIVE LOGITS
     detail
    1.02
     descriptions
    0.94
     details
    0.90
    lly
    0.90
     representations
    0.87
     detailing
    0.87
     description
    0.86
     outline
    0.85
    bred
    0.83
     information
    0.83
    Act Density 0.022%

    No Known Activations