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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proposed actions or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "proposed" or related terms in the context of suggestions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.80
    oyal
    -0.79
    wood
    -0.77
    mone
    -0.75
    vin
    -0.75
    wr
    -0.72
    tesy
    -0.71
    ulu
    -0.70
    gi
    -0.70
    guard
    -0.68
    POSITIVE LOGITS
     proposals
    0.98
     proposing
    0.83
     amendments
    0.82
     proposal
    0.77
     revisions
    0.76
     decriminal
    0.73
    interstitial
    0.72
    eca
    0.70
     anew
    0.70
     proposed
    0.67
    Act Density 0.041%

    No Known Activations