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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial and legal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cale
    -0.86
    ighthouse
    -0.85
    outhern
    -0.82
    etheless
    -0.80
    ensical
    -0.76
    omething
    -0.75
    ensor
    -0.75
    untled
    -0.74
    Ļ½
    -0.73
    ractor
    -0.72
    POSITIVE LOGITS
     holders
    1.06
     owners
    0.98
     makers
    0.98
    holders
    0.97
     replacements
    0.96
     registrations
    0.95
     rentals
    0.95
     equivalents
    0.94
     types
    0.91
     sizes
    0.91
    Act Density 0.750%

    No Known Activations