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

    Neuronpedia

    INDEX
    Explanations

    phrases related to computing power and resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to computing resources and infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sym
    -0.77
    ICLE
    -0.73
    cause
    -0.65
     Cause
    -0.65
    ModLoader
    -0.63
    Rating
    -0.62
     Outbreak
    -0.61
    eries
    -0.61
    akeru
    -0.60
     lighthouse
    -0.60
    POSITIVE LOGITS
     expended
    1.16
     allocated
    1.15
     devoted
    1.11
     allotted
    1.10
     resources
    0.95
     available
    0.94
     wasted
    0.94
     invested
    0.92
     allocation
    0.90
     allocations
    0.88
    Act Density 0.383%

    No Known Activations