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

    Neuronpedia

    INDEX
    Explanations

    geological features, specifically rocks

    oai_token-act-pair · gpt-3.5-turbo

    references to rocks and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.78
    oresc
    -0.72
    ersive
    -0.67
    uthor
    -0.67
    OHN
    -0.64
     Fraud
    -0.64
    iator
    -0.64
    Express
    -0.63
    orsche
    -0.62
     failings
    -0.62
    POSITIVE LOGITS
    lake
    1.06
    hill
    0.94
     formations
    0.90
    bending
    0.88
    castle
    0.85
    crete
    0.85
     quar
    0.83
     rocks
    0.81
    paper
    0.81
    falls
    0.80
    Act Density 0.036%

    No Known Activations