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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to various fields or industries

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to designations and categorization in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.85
    itably
    -0.73
     environmentalists
    -0.70
     uncertainties
    -0.70
     trivial
    -0.69
     skeptical
    -0.68
     dogged
    -0.68
     unfavorable
    -0.68
     repeated
    -0.66
    terday
    -0.66
    POSITIVE LOGITS
     Room
    1.22
     Zone
    1.16
     Engine
    1.12
     Meter
    1.10
     Graveyard
    1.10
     Manager
    1.10
     Module
    1.10
     Lounge
    1.09
     Desk
    1.08
     Reduction
    1.07
    Act Density 0.383%

    No Known Activations