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

    Neuronpedia

    INDEX
    Explanations

    proposals being discussed or considered in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to formal proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    respect
    -0.74
    oyal
    -0.72
    cor
    -0.68
     Seas
    -0.66
    roots
    -0.66
    tesy
    -0.65
    akening
    -0.65
    abol
    -0.64
     Sul
    -0.64
    ells
    -0.62
    POSITIVE LOGITS
     proposals
    1.18
     proposal
    1.16
     proposing
    0.84
    osal
    0.78
     proposes
    0.78
    posal
    0.77
    interstitial
    0.76
     propose
    0.76
     sugg
    0.75
     proposed
    0.75
    Act Density 0.013%

    No Known Activations