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

    Neuronpedia

    INDEX
    Explanations

    mentions of strategy or plan either positively or negatively evaluated

    oai_token-act-pair · gpt-3.5-turbo

    references to strategies and strategic discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     postage
    -0.76
     Medals
    -0.73
     receipts
    -0.70
     accuser
    -0.68
    bucks
    -0.67
     overflow
    -0.66
    aques
    -0.66
     petitions
    -0.64
     Signs
    -0.63
     claimant
    -0.63
    POSITIVE LOGITS
     dictated
    1.13
     adapted
    1.02
     adopted
    1.01
     formulated
    1.01
     evolved
    0.99
     implemented
    0.99
     evolve
    0.98
     underpin
    0.97
     outlined
    0.96
     geared
    0.96
    Act Density 0.438%

    No Known Activations