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

    Neuronpedia

    INDEX
    Explanations

    references to specific minerals

    oai_token-act-pair · gpt-3.5-turbo

    references to minerals and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILLE
    -0.88
     Ended
    -0.78
    akening
    -0.75
    lihood
    -0.73
    orld
    -0.72
    earable
    -0.72
    isSpecialOrderable
    -0.69
    "]=>
    -0.68
    soType
    -0.67
    ATA
    -0.67
    POSITIVE LOGITS
    ogical
    1.26
    ogy
    1.01
    istry
    0.99
    itions
    0.98
     minerals
    0.94
    ically
    0.90
    anguage
    0.86
     baths
    0.85
     mineral
    0.82
    ization
    0.82
    Act Density 0.016%

    No Known Activations