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

    Neuronpedia

    INDEX
    Explanations

    proposals and policies

    oai_token-act-pair · gpt-3.5-turbo

    proposals or legislative initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.66
    juries
    -0.63
     Shroud
    -0.60
    isphere
    -0.60
    nsics
    -0.60
    Occ
    -0.60
    gate
    -0.60
     Cooke
    -0.59
     Detect
    -0.59
     spor
    -0.58
    POSITIVE LOGITS
     proposal
    1.07
     proposals
    0.98
     proposed
    0.97
     proposes
    0.91
     proposing
    0.89
     vetoed
    0.86
     propose
    0.85
     advocated
    0.83
     incentiv
    0.82
     abolition
    0.80
    Act Density 1.323%

    No Known Activations