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

    Neuronpedia

    INDEX
    Explanations

    words related to political policies and decisions

    oai_token-act-pair · gpt-3.5-turbo

    clauses introducing dependent clauses or relative clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.75
    ascript
    -0.73
    eware
    -0.72
    aciously
    -0.66
    irm
    -0.65
    enture
    -0.63
    illy
    -0.63
    idge
    -0.63
    Interstitial
    -0.63
    repeat
    -0.62
    POSITIVE LOGITS
     expires
    1.12
     involves
    1.04
     entails
    1.00
     would
    0.99
     includes
    0.99
     could
    0.99
     occurs
    0.98
     encompasses
    0.97
     threatens
    0.95
     excludes
    0.94
    Act Density 0.199%

    No Known Activations