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

    Neuronpedia

    INDEX
    Explanations

    references to formal proposals or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of proposals within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wood
    -0.78
    ocent
    -0.71
    vin
    -0.70
    cor
    -0.69
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.69
    si
    -0.66
    nie
    -0.66
    minster
    -0.66
    zona
    -0.64
    winter
    -0.63
    POSITIVE LOGITS
     proposals
    1.01
     proposal
    0.91
     proposing
    0.79
     decriminal
    0.72
     proposed
    0.71
    ļéĨĴ
    0.69
     proposes
    0.68
     sugg
    0.67
    eca
    0.67
     aimed
    0.67
    Act Density 0.021%

    No Known Activations